Способ обработки и анализа данных электрокардиограммы (ЭКГ)

Изобретение относится к обработке медицинских сигналов, в частности к диагностике заболеваний сердечно-сосудистой системы с использованием моделей нейронных сетей. Предложен способ обработки и анализа сигналов электрокардиографии (ЭКГ), который содержит следующие этапы: прием сигнала ЭКГ с целью предварительной обработки в виде передискретизации сигнала до 500 Гц и нормализации амплитуды до значений [0, 1]; устранение шумов и помех на сигнале ЭКГ с использованием полосового фильтра с конечной импульсной характеристикой; детектирование ключевых компонентов ЭКГ, таких как R-пики, с применением нескольких эвристических методов; проведение детального анализа сигнала ЭКГ для выявления и коррекции других зубцов ЭКГ, извлекаются характеристики: интервалы между зубцами и их амплитуды; расчет дополнительных статистических параметров; формирование входных векторов для нейронной сети: первый вектор с исходной фильтрованной ЭКГ размером 12×5000, второй вектор, состоящий из вычисленных 94 признаков; ...

Способ диагностики электрокардиосигнала на основе определения фрактальной размерности

Изобретение относится к медицине, а именно к функциональной диагностике в кардиологии. Предложен способ анализа электрокардиосигнала, в котором осуществляют регистрацию амплитудно-временных параметров кардиологических циклов электрокардиограммы в 12 отведениях посредством кардиографа и аппаратных и программных средств. Анализ электрокардиосигнала осуществляется путем получения фрактальной размерности ЭКС, полученной на основе оцифрованных амплитудно-временных параметров кардиосигнала в программной среде MatLAB, построения графика спектра мощности логарифмированных значений электрокардиосигнала и определения угла наклона аппроксимирующей прямой к этому графику, в результате чего выражается числовой эквивалент фрактальной размерности электрокардиосигнала, на основе которого формируется заключение о наличии отклонений в работе сердечно-сосудистой системы пациента. За счет возможности применения способа в диагностике и анализе электрокардиосигнала возможны выявление отклонений от нормы с учетом ...

웨어러블 심전도 신호 분석 방법

... 본 발명은 웨어러블 심전도 신호 분석 기술에 관한 것으로서, 일실시예에 따른 웨어러블 심전도 신호 분석 방법은 서버로부터 심전도 데이터를 서버로부터 수집하는 단계, 딥러닝 모델을 실행하는 단계, 상기 실행한 딥러닝 모델에 기반하여, 복수의 모듈들을 구분하여 로딩하는 단계, 상기 구분된 복수의 모듈에서 처리된 딥러닝 결과들을 산출하는 단계, 상기 산출된 딥러닝 결과들을 비교하는 단계, 상기 비교한 결과에 따라 오류 데이터에 대해 상기 딥러닝 모델을 업데이트하기 위해, 상기 딥러닝 모델을 실행하는 과정으로 분기하는 단계, 상기 비교한 결과를 표시하는 단계를 포함할 수 있다.

다양한 형식의 심전도 데이터 이용가능한 딥러닝기반 예측 시스템

... 본 발명은, 제1 내지 제N의 다양한 형식의 동일 심전도 데이터 중, 특정 저장 특성에 상응하는 형식으로 심전도 측정결과의 심전도 데이터를 저장하고 제공하는 심전도 측정부(110), 미리학습된 딥러닝 알고리즘을 통해서, 심전도 측정부(110)로부터 제공되는 특정 형식에 상응하는 심전도 데이터를 입력으로 하여 표현값을 예측하는 N개 이상 예측모델(121,122)과, 각 예측모델(121,122)의 표현값들을 합쳐서, 심전도 데이터에 상응하는 질환 유무의 예측값 및 심전도 데이터의 특정 형식에 상응하지 않는 다른 형식의 심전도 데이터를 예측하는 최종예측모델(123)로 구성되는, 예측부(120), 및 예측부(120)에 의해 예측된 예측값과, 다른 형식의 심전도 데이터를 출력하는 출력부(130)를 포함하여, 단일 예측모델을 구축하여, 심전도 데이터의 형식에 상관없이 개별 의료기관의 심전도측정기기별 특정 형식의 심전도 데이터로부터 질환의 예측 및 진단이 가능하도록 하는, 다양한 형식의 심전도 데이터 이용가능한 딥러닝기반 예측 시스템을 개시한다.

USING REVERSIBLE ELECTROPORATION ON CARDIAC TISSUE

In one embodiment, an electroporation method includes inserting a catheter having multiple electrodes into a chamber of a heart, applying an electrical field using at least two of the electrodes to tissue of the chamber of the heart at a given location within the chamber with an amplitude sufficient to cause reversible electroporation, but below a threshold for irreversible electroporation, and measuring an effect of the reversible electroporation on electrical activation signals in the tissue of the chamber of the heart in a vicinity of the location.

INTRACARDIAC DEVICE AND METHODS OF USE

Improvements to intracardiac devices such as intracardiac blood pump assemblies, and associated methods. In one example, the present technology includes systems and methods for pacing the heart, and/or performing cardiac ablation using electrodes mounted on a portion of the intracardiac device. In another example, the present technology includes systems and methods for detecting mural thrombi in a patient's heart using electrical sensors or ultrasonic phased arrays mounted on the intracardiac device. In another example, the present technology includes systems and methods for detecting tissue changes and reactions in heart tissue during treatment using one or more temperature sensors. In another example, the present technology includes an improved distal tip for use with an intracardiac device. In another example, the present technology includes systems and methods for maintaining an intracardiac device in a desired position within a patient's heart using magnets or ultrasonic phased arrays ...

Способ диагностики блокады передневерхней ветви левой ножки пучка Гиса

Изобретение относится к медицине, а именно к кардиологии, функциональной диагностике, и может быть использовано для диагностики блокады передневерхней ветви левой ножки пучка Гиса (БПВЛНПГ). Из ЭКГ в 12 отведениях, зарегистрированных синхронно, реконструируют ортогональные отведения ЭКГ, вектор кардиограммы в ортогональных плоскостях и трехмерную векторную петлю с построением графика скорости формирования петли. БПВЛНПГ устанавливают на основании следующих критериев: векторная петля во фронтальной плоскости сформирована против часовой стрелки с образованием двух экстремумов векторной петли, при этом второй экстремум направлен вверх, вправо и назад; кривая скорости формирования трехмерной векторной петли имеет 2-3 пика, в конечной части векторной петли пик скорости снижен относительно максимального пика в 2-2,5 раза и совпадает по времени со вторым экстремумом. Способ повышает точность диагностики БПВЛНПГ, обеспечивает возможность диагностировать БПВЛНПГ при сочетании с нижним инфарктом ...

СПОСОБ ПРОФИЛАКТИКИ НЕВРОЛОГИЧЕСКИХ ОСЛОЖНЕНИЙ ПРИ ХИРУРГИЧЕСКОЙ КОРРЕКЦИИ ИДИОПАТИЧЕСКОГО СКОЛИОЗА

Изобретение относится к медицине, а именно к травматологии, ортопедии, неврологии, хирургии. Перед операцией в наркозе в положении на животе выполняют запись электрокардиограммы (ЭКГ). Формируют динамический ряд значений интервала времени между соседними сердечными сокращениями (RR интервалов), которые отображают в виде ритмокардиограммы (РКГ). Проводят спектральный анализ ритмокардиограммы, по результатам которого оценивают соотношение низкочастотной (НЧ) и высокочастотной (ВЧ) составляющих общей мощности спектра. Аналогично выполняют запись ЭКГ и оценку значений НЧ/ВЧ в процессе проведения операции. При уменьшении соотношения НЧ/ВЧ на 50% относительно дооперационных показателей изменяют положение транспедикулярных винтов или уменьшают степень коррекции сколиоза до достижения дооперационных показателей НЧ/ВЧ. После окончания коррекции деформации позвоночника выполняют запись контрольной ЭКГ, оценку НЧ/ВЧ и при необходимости изменяют степень коррекции деформации позвоночника и/или положение ...

AUTOMATIC IDENTIFICATION OF ABNORMAL LAT DIFFERENCES

Apparatus, consisting of a catheter that is configured to be inserted into a chamber of a heart and that has one or more electrodes configured to contact myocardial tissue At multiple locations in the chamber. The one or more electrodes receive electrical signals responsive to a conduction wave traveling through the tissue. The apparatus includes a display and a processor that is configured to receive the electrical signals from the catheter and to render to the display, responsively to the electrical signals, a map of the chamber including an indication of local times of occurrence of the conduction wave at the multiple locations. The processor is also configured to calculate, responsively to the local times of occurrence, a velocity of the conduction wave between the locations and to mark on the map one or more areas of the chamber in which the velocity is below a preset threshold.

위전도를 활용한 스트레스 수준 분석 시스템 및 방법

... 본 발명의 일 실시예에 따른 위전도를 활용한 스트레스 수준 분석 방법은, 대상자의 위전도, 심전도 및 호흡신호를 각각 획득하는 단계; 획득한 위전도, 심전도 및 호흡신호를 각각 시간 영역 및 주파수 영역에서 분석하여 복수의 특징점을 추출하는 단계; 상기 복수의 특징점으로부터 일부의 특징점들만을 선별하여 특징점 데이터의 차원을 축소하는 단계; 및 선별된 특징점 데이터를 기계학습 분류기에 입력하여 스트레스 수준을 분석하는 단계를 포함할 수 있다.

APPARATUS AND METHOD FOR ESTIMATING BIOMETRIC INFORMATION

An apparatus for estimating biometric information is provided. According to one exemplary embodiment, the apparatus may include a sensor comprising an electrocardiogram (ECG) sensor configured to measure an ECG signal of a user and a pulse wave sensor configured to measure two or more pulse wave signals at two or more measurement sites of the user; and a processor configured to obtain biometric information based on the ECG signal and the two or more pulse wave signals measured by the sensor.

DETECTION AND PREDICTION OF HYPERTENSION INDUCED ORGAN DAMAGE USING ECG AND BLOOD PRESSURE DATA

Embodiments of the present disclosure provide systems and methods for diagnosing LVH based on a user's ECG data as well as blood pressure data. The user may record their ECG and blood pressure data using any appropriate ECG and blood pressure monitors, and may augment the ECG and blood pressure data with user characteristics such as user age, sex, diet, and previous medical history before transmitting the ECG and blood pressure data to a cloud storage system. A machine learning (ML) model implemented in the cloud storage system may analyze ECG data of the user using LVH diagnosis criteria, and augment the results of the ECG data analysis with the blood pressure data of the user to form a diagnosis. The diagnosis may indicate whether the user is suffering from LVH, as well as a severity of the LVH.

EMOTION ESTIMATION APPARATUS AND EMOTION ESTIMATION METHOD

An emotion estimation apparatus includes preparation biological information acquisition circuitry acquires, separately from subjects who are in a preparation space, first biological information indicating a physical state of each subject and analyzes the first biological information, preparation emotion information acquisition circuitry acquires emotion information indicating an emotion of each of the subjects, association construction circuitry constructs association information in which the first biological information and the emotion information corresponding to the first biological information are associated with each other, estimation biological information acquisition circuitry acquires second biological information indicating a physical state of any one subject of the subjects who is present in an estimation space, estimation circuitry extracts the emotion information associated in the association information with the first biological information that is equal to the second biological ...

Visualizing Performance of Catheter Electrodes

A system for electrophysiological measurement includes a probe having a distal end configured for insertion into a body cavity of a living subject and including an array of electrodes that are disposed along the distal end and are configured to contact tissue at multiple locations within the body cavity. A processor is configured to acquire signals from the electrodes over a period of time during which the probe moves within the body cavity, to compute, in response the signals, metrics that are indicative of a respective quality of contact between each of the electrodes and the tissue over the period of time, and to output an indication of the metrics to a user of the system.

CONTROL SYSTEM AND USER INTERFACE FOR AN ABLATION SYSTEM

ECG BASED METHOD PROVIDING ACQUIRED CARDIAC DISEASE DETECTION

STABLE CARDIAC SIGNAL IDENTIFICATION

СПОСОБ И СИСТЕМА АВТОМАТИЧЕСКОГО АНАЛИЗА ЭКГ

Изобретение относится к области автоматического анализа электрокардиограммы с помощью алгоритмов машинного обучения. Техническим результатом является повышение точности анализа ЭКГ. Технический результат заявляемого технического решения достигается тем, что в заявленном способе предусмотрена вычислительная система, содержащая три модели машинного обучения, при этом способ выполняет этапы, на которых: получают сигнал ЭКГ пациента; осуществляют предварительную обработку полученного сигнала; осуществляют обработку сигнала с помощью первой модели машинного обучения, причем в ходе указанной обработки осуществляется выделение временных координат QRS комплексов сигнала; с помощью второй модели машинного обучения на базе классификационной сверточной нейронной сети (CNN) осуществляют: обработку отрезков сигнала заранее заданного размера, центрированных по положению QRS-комплекса на основании временных координат, выделенных первой моделью МО; формирование усредненного вектора сердцебиения QRS-комплекса; осуществляют классификацию данных сердцебиения пациента с помощью третьей модели МО с помощью обработки упомянутых временных координат QRS комплексов сигнала, полученных первой моделью МО, и усредненного вектора сердцебиения QRS-комплекса, формируемого второй моделью МО. 2 н. и 4 з.п. ф-лы, 4 ил., 3 табл. РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 767 157 C2 (51) МПК G06N 3/08 (2006.01) A61B 5/346 (2021.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК G06N 3/08 (2021.08); A61B 5/346 (2021.08) (21)(22) Заявка: 2020124218, 21.07.2020 (24) Дата начала отсчета срока действия патента: Дата регистрации: (73) Патентообладатель(и): Общество с ограниченной ответственностью "СберМедИИ" (ООО "СберМедИИ") (RU) 16.03.2022 (43) Дата публикации заявки: 21.01.2022 Бюл. № 3 (45) Опубликовано: 16.03.2022 Бюл. № 8 2 7 6 7 1 5 7 R U (54) СПОСОБ И СИСТЕМА АВТОМАТИЧЕСКОГО АНАЛИЗА ЭКГ (57) Реферат: Изобретение относится к области второй модели ...

Способ исследования работы сердца при использовании вейвлет-преобразования электрокардиограмм и спектроскопии комбинационного рассеяния

Изобретение относится к медицине, а именно к способу исследования работы сердца при использовании вейвлет-преобразования электрокардиограмм (ЭКГ) и спектроскопии комбинационного рассеяния. При этом получают и обрабатывают ЭКГ при использовании вейвлет-преобразования с предварительной фильтрацией высокочастотных шумов. Анализируют распределение чувствительных детализирующих коэффициентов вейвлет-преобразования. Определяют характеристические зоны коэффициентов и значения коэффициентов для здоровых людей и людей с заболеваниями сердца. Подключают второй измерительный канал – проводят спектроскопию комбинационного рассеяния при неинвазивном лазерном воздействии на кожный покров пациента с отслеживанием отклика на это воздействие. Вейвлет-преобразование осуществляют с возможностью менять по запросу материнскую функцию. При обработке ЭКГ проводят выделение и визуализацию по заданному критерию областей коэффициентов с измененными в ходе лазерного воздействия признаками. Выделяют признаковое пространство ...

КОМПЬЮТЕРИЗИРОВАННЫЙ СПОСОБ НЕИНВАЗИВНОГО ВЫЯВЛЕНИЯ НАРУШЕНИЙ УГЛЕВОДНОГО ОБМЕНА ПО ВАРИАБЕЛЬНОСТИ СЕРДЕЧНОГО РИТМА И НОСИМОЕ АВТОНОМНОЕ УСТРОЙСТВО ДЛЯ ЕГО РЕАЛИЗАЦИИ

Группа изобретений относится к медицине, а именно к компьютеризированным способам неинвазивного выявления нарушения углеводного обмена (НУО) по вариабельности сердечного ритма (ВСР) пациента, носимым автономным устройствам для их осуществления, а также к способу скрининга населения для выявления лиц с признаками НУО по ВСР. Осуществляют съем кардиосигнала ЭКГ и/или ФПГ. Определяют в сигнале последовательность временных отметок. В полученной последовательности определяют интервалы времени между соседними временными отметками и получают кардиоинтервалограмму (КИГ), характеризующую ВСР. Осуществляют преобразование КИГ путем удаления линейного тренда значений для получения преобразованной кардиоинтервалограммы (ПКИГ), характеризующей нелинейные колебания сердечного ритма. Производят расчет для каждой ПКИГ статистических и спектральных параметров ВСР. Осуществляют компьютерную обработку статистических и спектральных параметров ВСР. Сопоставляют статистические и спектральные параметры ВСР с эталонными ...

Малогабаритная двухдиапазонная антенна для имплантируемого кардиомонитора

Изобретение относится к изделиям медицинской техники, а именно к имплантируемым кардиомониторам. Двухдиапазонная антенна для имплантируемого кардиомонитора с планарной структурой состоит из комбинации инвертированной F-антенны с монопольной антенной в форме прямоугольного меандра. Антенна выполнена на многослойной печатной плате имплантируемого кардиомонитора в виде структуры из трех изолированных проводящих слоев с металлизированными проходными отверстиями. Обеспечивается малогабаритная антенна, работающая в двух диапазонах частот, с формой и размером, определяемыми небольшими габаритами радиопрозрачного отсека для размещения антенны. Благодаря включению конструктивных элементов антенны в состав многослойной печатной платы кардиомонитора упрощается его сборка и повышается надежность за счет исключения дополнительного узла сборки. 6 ил.

Способ дифференциальной диагностики нарушений ритма сердца у детей с тяжелой формой коклюша

Изобретение относится к области медицины, а именно педиатрии, инфектологии, кардиологии. Осуществляют оценку электрокардиографических показателей на основании проведения ЭКГ. При появлении задержки дыхания на фоне коклюша проводят суточное кардиореспираторное мониторирование и при выявлении аритмий сопоставляют их с эпизодами задержки дыхания. Дифференциальную диагностику выполняют в зависимости от патогенеза аритмий: в случае зависимости критической брадикардии, асистолии от задержки дыхания при ЧСС менее 60 ударов в минуту диагностируют патологическую рефлекторную брадикардию, асистолию. При некритической брадикардии на фоне задержки дыхания - ЧСС более 60 ударов в минуту - вагусзависимую брадикардию. При отсутствии связи аритмий с задержкой дыхания исключают их рефлекторный вагусзависимый характер. Способ позволяет выявить и провести дифференциальную диагностику нарушений ритма сердца у детей для определения тактики лечения и последующего наблюдения за данным пациентом кардиологом. 3 ...

Способ прогнозирования наджелудочковых нарушений ритма сердца у пациентов, находящихся на хроническом гемодиализе

Изобретение относится к медицине, а именно к кардиологии. У пациентов старше 60 лет, находящихся на хроническом гемодиализе не менее 12 месяцев по схеме 2/2/3, проводят суточное мониторирование ЭКГ с подсчетом количества наджелудочковых экстрасистол, определяют по данным ЭхоКГ индекс массы левого желудочка сердца и фракцию выброса левого желудочка по методике Симпсона. Если по данным суточного мониторирования ЭКГ количество наджелудочковых экстрасистол более 70 в час, по данным ЭхоКГ индекс массы левого желудочка сердца более 119 г/м2, фракция выброса левого желудочка по методике Симпсона менее 49%, прогнозируют у пациента развитие наджелудочковых нарушений ритма сердца в виде фибрилляции предсердий. Способ позволяет повысить точность прогнозирования ФП, выделить приоритетную группу пациентов с хронической болезнью почек и с нарушениями ритма сердца для диспансерного наблюдения и назначения персонифицированного лечения, что обеспечит назначение адекватной терапии для предотвращения ФП и ...

딥러닝 알고리즘을 기반으로 하는 심전도 생성 시스템 및 그 방법

... 본 발명은 딥러닝 알고리즘을 기반으로 하는 심전도 생성 시스템 및 그 방법 에 관한 것이다. 본 발명에 따르면, 딥러닝 알고리즘을 기반으로 하는 심전도 생성 시스템은 복수의 환자에 의해 측정된 12 유도 심전도를 입력받는 데이터 입력부, 상기 입력된 12 유도 심전도로부터 학습 데이터를 추출하는 데이터 추출부, 상기 추출된 학습 데이터를 복수의 학습 모델에 입력하여 심전도에 대한 특성을 학습시키는 학습부, 상기 측정대상자로부터 1개 이상의 기준 심전도를 입력받고, 상기 입력된 기준 심전도를 학습이 완료된 복수의 학습 모델에 입력하여 가상 심전도를 생성하는 심전도 생성부, 그리고 상기 기준 심전도와 생성된 가상 심전도를 상호 동기화하며, 동기화된 기준 심전도 및 가상 심전도에 대한 파형을 출력하는 제어부를 포함한다.

실시간 측정을 위해 서로 다른 샘플링 주파수와 필터 기법을 이용한 심전도 신호의 특징 비교 방법 및 장치

... 실시간 측정을 위해 서로 다른 샘플링 주파수와 필터 기법을 이용한 심전도 신호의 특징 비교 방법 및 장치가 제시된다. 본 발명에서 제안하는 실시간 측정을 위해 서로 다른 샘플링 주파수와 필터 기법을 이용한 심전도 신호의 특징 비교 방법은 심전도 신호의 노이즈를 제거하기 위한 필터의 차수 및 이동 지연 간격을 포함하는 고역 통과 필터 및 저역 통과 필터의 파라미터를 설정하는 단계, 복수의 서로 다른 샘플링 주파수를 이용하여 심전도 신호를 추출하는 단계 및 상기 추출된 심전도 신호에 대해 상기 고역 통과 필터 및 저역 통과 필터를 적용하기 전과 후 및 상기 복수의 서로 다른 샘플링 주파수에 관하여 비교 분석하는 단계를 포함한다.

2유도 심전도 데이터를 이용한 복수개의 표준 심전도 데이터 생성 시스템

... 본 발명은, 2유도 이상의 표준유도 심전도를 측정하여 심전도 데이터를 생성하는 심전도 측정부(110), 미리학습된 원칙기반 알고리즘(121)을 통해, 2유도 이상의 표준유도 심전도 데이터의 특성정보를 식별하고 연산하여 3차원공간 상에서의 복수의 잔여 유도 심전도 데이터를 합성하여 복수 유도 심전도 데이터를 생성하는, 심전도 생성부(120), 및 심전도 측정부(110)에 의해 측정된 실제 심전도 데이터와, 심전도 생성부(120)에 의해 생성된 복수 유도 심전도 데이터를 출력하는 출력부(130)를 포함하여, 원칙기반 알고리즘(121)을 이용하여 2유도 이상의 심전도 데이터로부터 복수개의 표준유도 심전도 데이터를 생성할 수 있는, 2유도 심전도 데이터를 이용한 복수개의 표준 심전도 데이터 생성 시스템을 개시한다.

PHONOCARDIOGRAM (PCG) SIGNAL PROCESSING SYSTEMS AND METHODS FOR DETERMINING CARDIAC TISSUE AND VALVULAR BLOOD FLOW PARAMETERS

A non-invasive, passive, and fully automated heart-sound-based system and method that provides estimates for blood velocity, tissue motion, and cardiac chamber size parameters for cardiac assessment is provided. The system uses a computer processor and software to receive PCG acoustic signals from one or more sensors and simultaneously receive electrocardiogram (ECG) signals from one or more sensors that are attached to a patient. The phonocardiogram (PCG) processing system and methods compute proxy metrics for echocardiographic parameters of cardiac tissue motion and valvular blood flow for evaluation.

METHOD FOR CHARACTERIZING ACTIVATION OF AN ANATOMICAL TISSUE SUBJECTED TO CONTRACTION

This disclosure relates to a method for characterizing activation of an anatomical tissue subjected to contraction, aiming at providing a characterization of the contraction itself in a quantitative manner which is accurate and repeatable. The invention proposes an analysis of the activation of the anatomical structure based on instantaneous spectral contents of an activity signal from which an identification of peaks of dominant frequency characterizing the contraction throughout the anatomical tissue results. An evolution of a spatial distribution of peaks of dominant frequency throughout the anatomical tissue over time can also be monitored. The disclosure finds particular advantageous applications in provision of a mapping of activation of the anatomical tissue in order to identify a possible dysfunction, such as an arrhythmia in a cardiac tissue.

СПОСОБ ИССЛЕДОВАНИЯ СИНХРОНИЗМА КАРДИОРЕСПИРАТОРНОЙ СИСТЕМЫ

Изобретение относится к области медицины, а именно пульмонологии, и может быть использовано для исследования синхронизма кардиореспираторной системы. Осуществляют параллельную запись электромиосигнала дыхательных мышц x(t) и кардиосигнала y(t) на апертуре 60…120 секунд. Определяют дискретные оконные преобразования Фурье в N-m1 окнах этих сигналов, где N - число дискретных отсчетов на апертуре наблюдения сигналов, m1 - число отсчетов в окне. Амплитудные спектры Xi и Yi дискриминируются по частоте путем удаления из спектров отсчетов частот, которые лежат ниже или выше полосы частот, занимаемой ритмом дыхания. Над селектированными частотными отсчетами оконного преобразования Фурье осуществляют амплитудную дискриминацию, заключающуюся в том, что спектральные коэффициенты, величина которых ниже заданного порога, обнуляются, а затем для каждой пары отсчетов оконного преобразования Фурье с номером n определяются показатели кардиореспираторного синхронизма по заявленной формуле. Способ обеспечивает ...

Способ многофакторного прогнозирования хронической сердечной недостаточности после первичного инфаркта миокарда с подъемом сегмента ST в течение 48-недельного наблюдения

Изобретение относится к медицине, а именно кардиологии. После первичного инфаркта миокарда с подъемом сегмента ST (ИМпST) на 7, или на 8, или на 9 сутки после осуществляют 24-часовое мониторирование электрокардиограммы и определяют турбулентность сердечного ритма (ТСР). При эхокардиографии определяют конечный систолический размер левого желудочка (КСР) и глобальную продольную деформацию (GLS). Затем рассчитывают риск (h) развития хронической сердечной недостаточности (ХСН) на 6, 11, 12, 16, 24 и 48 неделях постинфарктного периода по оригинальной формуле. При величине h превышающей 1,0, прогнозируют прогрессирование ХСН, при h менее 1,0 делают заключение о стабильном течении постинфарктного периода. Способ позволяет осуществить выявление прогрессирования течения ХСН и выявить больных после перенесенного инфаркта, которым может потребоваться мероприятия, направленные на предотвращения неблагоприятного исхода. 2 пр., 5 табл.

Способ определения гемодинамических параметров на основе многоканальной электроимпедансной компьютерной кардиографии

Изобретение относится к медицине, а именно к способу определения гемодинамических параметров, таких как ударный выброс сердца и минутный объём крови сердца, на основе многоканальной электроимпедансной компьютерной кардиографии посредством регистрации электрофизиологических сигналов с грудной клетки. Для регистрации сигналов используют импедансный измерительный преобразователь, который пропускает переменный электрический ток с частотой от 10 кГц до 100 МГц и амплитудой от 0,01 до 10 мА с использованием токовых электродов, расположенных на поверхности кожных покровов через грудную клетку. Определяют электрический импеданс и используют его изменение при сокращении сердца совместно с сигналом электрокардиограммы совместно. Радиальные электродные каналы расположены вдоль границы проекции стенок желудочков на грудную клетку. Дополнительный торакальный электродный канал для оценки пульсового кровенаполнения мягких тканей расположен вертикально вдоль позвоночного столба на грудной клетке в 10 см ...

Method and system for correcting heartrate values derived from a heart rate signal

The method is performed by a computing apparatus. A processor obtains, from a memory, a first valid pair of values comprising a heartrate value and a timestamp (S401). The processor receives, from a communicator, a pair of values comprising a heartrate value and a timestamp occurring after the timestamp obtained from memory (S402). The processor determines whether the received pair of values satisfy a validity criterion (S403). If so, the received pair of values are set as a second valid pair of values and used with the first valid pair of values to create an intermediate pair of values (S404). The intermediate pair of values comprises a heartrate value and an intermediate timestamp between the timestamps for the valid pairs of values. The original heart rate value associated with the intermediate timestamp is replaced with a corrected heart rate value that better reflects the heart rate signal.

인공신경망을 이용한 비정상 심전도 판단 방법

... 본 발명은 인공신경망을 이용한 비정상 심전도 판단 방법에 관한 것으로서, 피험자의 심전도(Electrocardiogram, ECG)가 입력되는 입력단계; 및 입력된 상기 심전도에 표준 12유도 심전도(12-Lead ECG)의 데이터를 기반으로 학습된 DCNN(Deep Convolutional Neural Network)를 적용함으로써 상기 심전도를 정상 또는 비정상으로 분류하는 분류단계를 포함한다. 본 발명에 따르면, 피험자의 심전도의 정상 또는 비정상을 신속하고 정확하게 판단할 수 있는 효과가 있다.

심전도 판독문 제공 시스템 및 그 방법

... 본 발명은 심전도 판독문 제공 시스템 및 그 방법에 관한 것이다. 본 발명에 따르면, 심전도 판독문 제공 시스템은 심전도와 상기 심전도를 판독한 답지 판독문을 수집하는 데이터 수집부, 학습모델을 구축하고, 상기 수집된 심전도 및 답지 판독문을 기 구축된 학습 모델에 입력하여 학습시키는 학습부, 상기 학습 모델로부터 출력된 결과 판독문과 상기 답지 판독문을 상호 비교하여오차를 산출하고, 산출된 오차를 이용하여 상기 학습 모델을 업데이트하는 제어부, 그리고 판독하고자 하는 심전도를 입력받고, 입력된 심전도를 학습이 완료된 학습 모델에 입력하여 판독문을 생성하는 판독문 생성부를 포함한다. 이와 같이 본 발명에 따르면, 심전도 판독에 숙련되지 못한 의사나, 판독문 작성이 어려운 의사 또는 의원 등에 가이드라인을 제시할 수 있으므로, 심전도 판독에 숙련되지 못한 의사의 심전도 판독 오류 가능성을 줄일 수 있고, 짧은 시간에 많은 수의 환자를 진료해야 하는 의료 현장에서 심전도 판독문 작성에 드는 시간과 비용을 줄일 수 있다.

BIO INFORMATION MEASUREMENT DEVICE AND BIO INFORMATION MEASUREMENT METHOD

A bio information measurement device and a bio information measurement method are provided. The bio information measurement device includes: a heart information acquisition unit for acquiring heart information; a brainwave information acquisition unit for acquiring brainwave information; a control unit for acquiring heart-brain synchronization information on the basis of the heart information and the brainwave information; and a display unit for displaying the heart-brain synchronization information. According to the present invention, it is possible to provide a health index reflecting the influence of both the automatic nervous system and the central nervous system. 1. A bio information measurement device comprising:a heart information acquisition unit configured to acquire heart information and including a photoplethysmograph (PPG) sensor or an electrocardiograph (ECG) sensor;a brainwave information acquisition unit configured to acquire brainwave information and including a brainwave measurer; anda controller configured to acquire heart-brain synchronization information on a basis of the heart information and the brainwave information,wherein the controller is further configured to acquire a heart coherence on a basis of the heart information, wherein the heart coherence is an index indicative of a rate of change of a pulse waveform acquired by the heart information acquisition unit and has a value from 0 to 1,wherein the controller is further configured to acquire on a basis of the brainwave information:i) a brainwave coherence among a plurality of brainwave waveforms, wherein a brainwave coherence is an index indicative of a degree of coincidence of frequency spectrums of the plurality of brainwave waveforms and has a value from 0 to 1,ii) a phase relation among a plurality of brainwave waveforms,iii) a degree of symmetry among a plurality of brainwave waveform, oriv) a power of brainwave, on a basis of the brainwave information,wherein the power of brainwave ...

Detection and Response to Arousal Activations

Arousal events can be determined for a user associated with a wearable device, such as a user wearing a wearable computing device including one or more sensors. The one or more sensors may obtain EDA information that may determine a sympathetic nervous system response of the user, which may be responsive to an arousal event or an activation. Detection of events that increase the EDA response may provide information to the user regarding arousal events and provide recommendations to the user to address the arousal events to decrease their response.

Method and device for the technical support of the analysis of signals acquired by measurement, the signals having a time- and space-dependent signal characteristic

A method enables analysis of (e.g. bioelectric) signals acquired by measurement. The method provides N signals U for an observation space and each has a time- and space-dependent signal characteristic U. Digitized signals for a time period T have M time points and define an M×N matrix with M tuples of N signal values each. Signal values acquired at time t form an N-tuple Ūt=(U1, . . . , UN)tin a signal space. The method acquires all combinations of k tuples from the M tuples, and calculates distances between all tuples. Distance values are calculated and define edge lengths of a (k−1) simplex (SIM) with one simplex assigned to each combination of k time points. Quantity characteristics of the simplex (SIM) are encoded into color values (COL), and displays the colors in a combinatorial time lattice (CTL). Each lattice point (GP) is displayed with the color encoded for the assigned simplex.

Способ скрининговой электрокардиографической диагностики гипертрофии левого желудочка у мужчин с артериальной гипертензией

Изобретение относится к области медицины, а именно, к кардиологии. Выполняют регистрацию и анализ у пациента амплитуды зубцов комплекса QRS с установлением критерия RaVL, и корнельского вольтажного индекса: RaVL + SV3. При этом для диагностики используют одновременно оба диагностических критерия: и критерий RaVL, выраженный в мм, и корнельский вольтажный индекс: RaVL + SV3, также выраженный в мм. После чего диагностируют наличие или отсутствие ГЛЖ (р) у мужчин с артериальной гипертензией по математической формуле, с использованием ранее полученных диагностических критериев. При значении р равном или более 0,5 диагностируют у пациента наличие ГЛЖ, а при значении р менее 0,5 - отсутствие ГЛЖ. Способ позволяет эффективно и быстро, с высокой чувствительностью провести скрининговую диагностику ГЛЖ с помощью ЭКГ у мужчин с артериальной гипертензией, за счет использования совокупности объективных информационных показателей, в том числе имеющих противоречивые значения в отношении нормы. 4 табл.

Способ определения типа полоролевой идентичности на основании объективных характеристик сердечно-сосудистой системы

Изобретение относится к медицине, а именно к патологической физиологии и психофизиологии, и может быть использовано для определения типа полоролевой идентичности (ПРИ) на основании объективных характеристик сердечно-сосудистой системы. С помощью реографии и ритмокардиографии определяют значения ударного объема кровотока, минутного объема кровотока, ударного индекса, систолического индекса, частоты сердечных сокращений, коэффициента интегральной тоничности, среднеквадратичного отклонения последовательного ряда RR-интервалов, квадратного корня суммы разностей последовательного ряда RR-интервалов, доли соседних RR-интервалов, которые различаются более чем на 50 мс, индекса вегетативного равновесия, вегетативного показателя ритма, показателя адекватности процессов регуляции, индекса напряжения, показателя активности регуляторных систем. Затем на основании полученных данных определяют дискриминантные функции f1 и f2 по заданным формулам. Выбирают исходные коэффициенты дискриминантных функций ...

MANSCHETTE UND ELEKTROKARDIOGRAFISCHE MESSVORRICHTUNG

Es werden eine Manschette und eine elektrokardiografische Messvorrichtung bereitgestellt, bei denen keine große Anzahl von Elektroden bereitgestellt werden muss. Die Manschette (20) schließt einen Manschettenkörper (21), der um einen Oberarm (5) in einer Umfangsrichtung des Oberarms (5) wickelbar ist, und eine Elektrodenanordnung (30), einschließlich einer Vielzahl von Elektroden (31), die an einer Innenoberfläche (24) des Manschettenkörpers (21) befestigt und in einer Richtung (X), die eine Längsrichtung des Manschettenkörpers (21) ist, nebeneinander angeordnet sind, ein, wobei die Anzahl der Vielzahl von Elektroden (31) mehr als N+2 beträgt, wobei N eine Anzahl von Elektroden ist, die erforderlich sind, um elektrokardiografische Informationen zu erhalten, wobei die Elektroden, gezählt von einer ersten Elektrode (31A), die sich an einem ersten Ende in der Richtung (X) befindet, durch Zählen einschließlich der ersten Elektrode (31A), zu der (N+1). Elektrode (31) in der Richtung (X) in gleichen ...

Methods and systems for forecasting epileptic events

A method comprises determining historical data associated with a subject experiencing epileptic events over a first time period, the historical data comprising non-EEG physiological data recorded over the first time period, and a time at which epileptic events occurred during the first time period. The method further comprises extracting from the non-EEG physiological data, one or more temporal models indicative of a subject specific cycle; and generating one or more temporal probabilistic models based on the respective one or more temporal models, the non-EEG physiological data, and the times at which each epileptic event occurred, wherein each temporal probabilistic model is representative of a probability of future seizure activity in each of a plurality of time windows. The method further comprises providing the one or more temporal probabilistic models for determining an estimate of seizure probability in the subject for one or more of the plurality of time windows.

AN ARTIFICIAL INTELLIGENCE BASED HEART RATE MONITORING SYSTEM FOR SPORTS TRAINING

AN ARTIFICIAL INTELLIGENCE BASED HEART RATE MONITORING SYSTEM FOR SPORTS TRAINING The present invention relates to an artificial intelligence based heart rate monitoring system for sports training The system involves front end hardware based on IoT that can be operated using smart application along with Al platform and cloud database for detection of cardiac rate. The proposed invention is able to detect heart rate. Herein an ECG patch consisting of wearable analog front end circuit with a Bluetooth module able to detect ECG signals. Real time ECG signal is displayed on the smart devices. ECG signals recorded from the wearable ECG patch is sent to cloud database where ECG signals of each of the user is stored, acting as a big data database for the Artificial Intelligence for detecting heart rate. -~1 - -r .o.s...1 lbu Am Figure 1 ...

심리생리학적 지표 측정을 통한 공격성 특질 분석 및 모니터링 시스템

... 심리생리학적 지표 측정을 통한 공격성 분석 및 모니터링 시스템에 대해 개시한다. 심리생리학적 지표 측정을 통한 공격성 분석 및 모니터링 시스템은, 심리학적 공격성 지표 데이터베이스를 생성하고, 측정된 생체 신호와 심리학적 공격성 지표의 상관관계에 대한 분석 결과를 제공하고, 상기 생체 신호와 심리학적 공격성 지표의 상관관계에 기초하여 생체신호 기반의 심리학적 공격성의 하위 특질에 대한 정량화 기준을 생성하고, 상기 생체 신호 기반의 심리학적 공격성을 진단 및 분석하고, 심리학적 공격성 진단 결과 및 공격성 완화 솔루션과 관련된 진단 결과를 제공하는 서버 스테이션과 및 공격성 모니터링 전용 헤드셋형 뇌파-심전도 측정 장치를 통해 심전도 및 Fp2 및 F8 채널에서 뇌파를 측정하고, 측정된 뇌파 및 심전도 신호를 상기 서버 스테이션으로 전달하고 상기 서버 스테이션으로부터 진단 결과를 수신하는 유저 스테이션을 포함한다.

딥러닝 기반 심전도 데이터의 노이즈 제거 시스템

... 본 발명은, 피검진자의 신체로부터 각 유도별 심전도 데이터를 측정하는 심전도 측정부(110), 및 다수의 심전도 데이터를 기반으로, 노이즈가 적은 각 유도별 심전도 데이터 및 각 유도별 심전도 데이터의 고유 스타일의 학습데이터셋을 미리 학습하여 구축된 심전도 생성 딥러닝 알고리즘(121)을 통해, 피검진자의 특성 및 측정방식의 특성을 반영하여, 심전도 측정부(110)에 의해 측정된 심전도 데이터로부터 고유 스타일을 추출하고, 추출된 고유 스타일을 통해 노이즈가 포함되지 않는 특정 유도 스타일의 심전도 데이터로 변환하여 생성하는, 스타일기반 심전도 생성부(120)를 포함하여, 노이즈가 제거된 심전도 데이터를 생성하여 질환 진단 예측의 정확도를 높일 수 있는, 딥러닝 기반 심전도 데이터의 노이즈 제거 시스템을 개시한다.

심전도 신호 분석 시스템 및 이를 이용한 심전도 신호 분석 방법

... 본 발명은 심전도 신호 분석 시스템 및 이를 이용한 심전도 신호 분석 방법에 관한 것으로서, 상기 심전도 신호 분석 시스템은 심전도 신호를 입력받는 심전도 입력모듈과, 상기 심전도 입력모듈에서 제공되는 심전도 신호를 분석하여 해당 심전도 신호에 대한 스펙트럼 영상을 생성하는 신호분석부를 구비한다. 본 발명에 따른 심전도 신호 분석 시스템 및 이를 이용한 심전도 신호 분석 방법은 입력된 심전도 신호를 분할하고, 분할된 심전도 신호에 대한 고차 스펙트럼 영상을 생성하므로 불규칙적인 근육 활동과 사용자의 움직임 및 호흡에 의해 잡음에 대한 영향을 최소화시켜 분석의 정확성을 향상시킬 수 있는 장점이 있다.

뇌파 측정 위치에 기초한 섬망 발생 가능성 산출 장치 및 방법

... 뇌파 측정 위치에 기초한 섬망 발생 가능성 산출 장치 및 방법이 제공된다. 상기 장치는 피진단자의 머리에 착용 가능하도록 형성된 제1 측정모듈을 이용하여 상기 피진단자의 뇌파를 측정하는 측정부 및 상기 측정된 뇌파를 분석하여 뇌파 이상 여부를 판단하고, 상기 판단 결과에 기초하여 상기 피진단자의 섬망 발생 가능성을 산출하는 제어부를 포함한다.

데이터에 기반하여 기능성식품을 추천하는 방법 및 장치

... 본 발명은 개인 차를 고려한 민감도 관계식을 이용하여 기능성성분에 대한 민감도를 예측하고, 다양한 특성변수를 활용한 관계식을 통해 민감도를 예측하는 데이터에 기반하여 기능성식품을 추천하는 방법 및 장치를 제공한다.

WAVEFORM-BASED HEMODYNAMIC INSTABILITY WARNING

A controller (150) for waveform-based hemodynamic instability warning includes a memory (151) that stores instructions and a processor (152) that executes the instructions. The controller (150) implements a process that includes receiving, via a first interface (153) that interfaces at least one electrocardiogram monitor (155) monitoring a patient, electrocardiogram waves; identifying (880) heart beats from the electrocardiogram waves; separating the plurality of heart beats into first temporal windows; extracting features of the heart beats in each of the first temporal windows as first extracted features for each first temporal window; generating, based on the first extracted features, generated features across a second temporal window that includes a plurality of the first temporal windows; applying trained artificial intelligence to the generated features; predicting hemodynamic instability for the patient based on applying the trained artificial intelligence to the generated features ...

ACTIVE IMPLANTABLE MEDICAL DEFIBRILLATION DEVICE, COMPRISING MEANS FOR DISCRIMINATING BETWEEN EXTERNAL NOISE AND PROBE BREAKAGE AND FOR CHARACTERIZING TACHYARRHYTHMIAS

This disclosure relates to active implantable medical devices. Some such devices include a pulse generator and at least one detection electrode. A processor of the pulse generator is configured to collect via the detection electrode at least two EGM signals, combine the EGM signals into two time components, and combine the components into a single 2D parametric characteristic representing the cardiac cycle. During a tachyarrhythmia episode, the device stores the consecutive values of the cycle-to-cycle variation in the amplitude of one EGM signal, distributes same into a plurality of classes each corresponding to an amplitude interval, and performs a statistical analysis of the totals for each class so as to output, selectively, on the basis of at least one predetermined criterion applied to the distribution of the amplitude variations into the various classes, an indicator of a suspected extracardiac artifact or an indicator of tachyarrhythmia.

Smart wristband for multiparameter physiological monitoring

An ergonomically designed smart wristband for clinical-grade multiparameter monitoring is disclosed. The smart wristband incorporates multiple sensors including custom-designed reflective arterial pulse sensors, a thermopile sensor, and electrocardiogram (ECG) electrodes. When the smart wristband is worn on the wrist, the biosensors contact the skin. The smart wristband may tether wirelessly to a mobile or any other computing device to continuously acquire and stream information like arterial pulse waveform and temperature data. Algorithms running on the computing device or onboard microprocessor analyze the acquired data to report parameters like blood pressure, body temperature, respiration, and blood oxygen. The device can also operate in a fully-standalone mode to accomplish continuous multiparameter physiological monitoring, analysis, and reporting. Whenever the user touches an electrode on the device with a finger of the other hand, an ECG signal is additionally acquired for monitoring ...

INCORPORATING A CONFIDENCE LEVEL INTO AN ELECTROPHYSIOLOGICAL (EP) MAP

A method includes receiving (i) a modeled surface of at least a portion of a heart and (ii) multiple EP values measured at multiple respective positions in the heart. Multiple regions are defined on the modeled surface and, for each region, a confidence level is estimated for the EP values whose positions fall in the region. The modeled surface is presented to a user, including (i) the EP values overlaid on the modeled surface, and (ii) the confidence level graphically visualized in each region of the modeled surface.

BYSTANDER ATRIUM DETECTION USING CORONARY SINUS (CS) SIGNALS

An atrial flutter identification method includes placing a catheter comprising multiple electrodes in a coronary sinus (CS) of a heart of a patient, so that some of the electrodes overlap a left atrium (LA) of the heart and some of the electrodes overlap a right atrium (RA) of the heart. Intra cardiac (IC) electrophysiological (EP) signals are acquired with the electrodes. Respective signal-stability measures are estimated over the signals acquired by the electrodes overlapping the LA and over the signals acquired by the electrodes overlapping the RA. When one of the signal-stability measures is above a first threshold while the other of the signal-stability measures is below a second threshold, an atrium is indicated, that corresponds to a highest among the signal-stability measures as a source of atrial flutter.

Способ прогнозирования антиаритмической эффективности операции реваскуляризации миокарда у больных ишемической болезнью сердца с желудочковыми аритмиями, спровоцированными ишемией миокарда

Изобретение относится к медицине, а именно к кардиологии. На дооперационном этапе проводят топическую диагностику очага аритмии, для чего на поверхности грудной клетки пациента закрепляют регистрирующие электроды для проведения поверхностного неинвазивного электрофизиологического картирования сердца (НЭФКС) и выполняют пробу с физической нагрузкой (ФН), после чего, регистрируя многоканальную ЭКГ с поверхности торса пациента, при достижении критериев положительной пробы с ФН пациента переводят в горизонтальное положение и продолжают регистрировать многоканальную ЭКГ в течение восстановительного периода. Выполняют КТ или МРТ грудной клетки пациента с закрепленными электродами, осуществляют обработку результатов ЭКГ, КТ или МРТ грудной клетки. Определяют место расположения очага аритмии, зарегистрированной на фоне пробы с ФН, и сопоставляют его с зоной кровоснабжения КА с гемодинамически значимым стенозом, полученной по результатам коронароангиографии (КАГ), и при совпадении локализации очага ...

АВТОМАТИЧЕСКОЕ ОПРЕДЕЛЕНИЕ МЕСТОПОЛОЖЕНИЯ ФОКАЛЬНОГО ИСТОЧНИКА ПРИ МЕРЦАТЕЛЬНОЙ АРИТМИИ (МА)

FIELD: medicine. SUBSTANCE: group of inventions relates to medicine, namely to a method for automatic location of focal arrhythmogenic activity and a system for implementation thereof. The observation data containing a set of electrophysiological (EP) signals measured by the electrodes is therein received by means of electrodes in the heart. For each observation data, the corresponding direction of arrival (DOA) and the corresponding distance relative to the electrodes emitting the set of EP signals are estimated. The observation data is aggregated forming a statistical distribution as a function of the calculated DOA and the distance. A statistical test is used to confirm whether the statistical distribution is consistent in accordance with a predetermined consistency criterion. Based on the statistical distribution, the calculated location in the heart of the focal source of arrhythmogenic activity generating the received EP signals is obtained when the statistical distribution of the observation data is confirmed to be consistent. The calculated location of the focal source is superimposed on the anatomical map of the heart. The user is notified that the location of the focal arrhythmogenic activity has not been identified when the statistical distribution of the observation data is confirmed to be contradictory. EFFECT: clinical outcome of catheter-based arrhythmia treatment is improved due to the reduction of error and the increase in the accuracy of estimation of the DOA. 26 cl, 12 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (51) МПК A61B 5/318 A61B 5/339 A61B 5/346 A61B 18/14 (11) (13) 2 755 381 C1 (2021.01) (2021.01) (2021.01) (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК A61B 5/318 (2021.08); A61B 5/339 (2021.08); A61B 5/346 (2021.08); A61B 18/14 (2021.08); A61B 5/361 (2021.08); A61B 5/363 (2021.08); A61B 5/6869 (2021.08) (21)(22) Заявка: 2020127608, 19.08.2020 19.08.2020 (73) Патентообладатель(и): БАЙОСЕНС ...

Способ определения риска развития папиллярного рака щитовидной железы

Изобретение относится к медицине, а именно к онкологии, и может быть использовано для дооперационной дифференциальной диагностики рака. Снимают электрокардиограммы с помощью трехэлектродного кабеля с расположением двух электродов на грудную клетку пациента в области 4-го межреберья слева и справа от грудины и третьего электрода в области проекции сердца с чувствительностью электрокардиосигнала 1000±3 Гц. При этом выполняют последовательно три пробы: проба рА, фоновая проба Ph, затем проба, при которой делают глубокий вдох, задерживают дыхание и делают обычный выдох. Затем определяют показатели SDNN, ARA, σs, σm для каждой пробы: при значениях показателей во всех трех пробах для σs и σm ≤ 0.01 с, для SDNN ≤ 0.015 с, для ARA ≤ 0.02 с, диагностируют высокий риск развития папиллярного рака щитовидной железы. Данный способ дооперационной дифференциальной диагностики папиллярного рака щитовидной железы является неинвазивным, обеспечивает высокую степень достоверности. 3 табл., 2 ил., 3 пр.

System for identifying cardiac conduction patterns

A system for diagnosing an arrhythmia of a patient comprises: a diagnostic catheter for insertion into the heart of the patient, the diagnostic catheter configured to record anatomic and electrical activity data of the patient; and a processing unit. The processing unit is configured to receive the recorded electrical activity data, and correlate the electrical activity data to the anatomic data. The processing unit comprises an algorithm configured to analyze the electrical activity at a location correlating to the anatomic data.

웨어러블 다중 생체 신호 측정장치

본 발명은 웨어러블 다중 생체 신호 측정장치에 관한 것으로, 하나 이상의 외부 포트를 갖는 본체; 상기 본체에 연결되어 사용자의 손목에 감겨지는 손목 밴드; 및 상기 외부 포트에 착탈 가능하게 연결되는 하나 이상의 외장 센서를 포함한다. 상기 본체는 생체 신호를 측정하는 하나 이상의 내장 센서; 상기 내장 센서 또는 상기 외장 센서로부터 얻어진 다중 생체 신호를 외부로 전송하는 무선 통신부; 상기 다중 생체 신호 측정을 지시하는 알림 메시지를 표시하고 사용자 데이터를 입력 받는 사용자 인터페이스부; 상기 내장 센서의 출력 신호를 증폭하고 디지털 신호로 변환하고, 상기 외장 센서와 상기 외부 포트의 연결 유무를 감지하여 상기 외장 센서가 상기 외부 포트에 연결될 때 상기 외부 포트와 동일한 생체 신호를 측정하는 내장 센서를 비활성화하는 센서 제어부; 및 상기 센서 제어부로부터의 다중 생체 신호 데이터를 상기 무선 통신부에 공급하고, 상기 무선 통신부로부터 수신된 알림 메시지를 상기 사용자 인터페이스부의 디스플레이로 전송하는 중앙 제어부를 포함한다.

생체 데이터 측정 및 판독 시스템

... 본 발명은 생체 데이터 측정 및 판독 시스템에 관한 것으로, 생체 데이터 측정 및 판독 시스템은 사용자가 자신의 생체 데이터를 자가 측정하는 측정 시스템; 및 상기 측정 시스템으로부터 수신된 데이터를 바탕으로 질환 예측, 감염병 위험 예측 및 중증도를 판독하여 판독 결과를 생성하는 판독 시스템을 포함한다.

NEURAL-NETWORK BASED ELECTROCARDIOGRAPHY MONITOR AND ASSOCIATED METHODS

Systems and methods detect cortical arousal events from a single time-varying ECG signal that is obtained via single-lead ECG. A pre-trained deep neural network transforms the ECG signal into a sequence of cortical-arousal probabilities. The deep neural network includes an inception module, a residual neural network, and a long short-term memory neural network to identify structure in the ECG signal that distinguishes periods of cortical arousal from periods without cortical arousal.

Determination of health status of systems equipped with sensors

A method for determining a health status of a system of interest is proposed. The method comprises acquiring (S1) a time series, extracting (S2) subsequences, selecting (S3) a set of subsequences, classifying (S4) the subsequences of the set into several groups on the basis of at least one criterion of resemblance to at least one reference subsequence, and constructing (S5) a normal operating model of the system of interest. The construction includes, for each group, a modeling (S51) of a representative subsequence and a determination (S52) of an associated weight. The normal model is defined by the modeled subsequences and the associated weights. The method further includes an attribution (S6) of a normality score to each subsequence extracted by comparison with the normal model, an identification (S7) of at least one abnormal subsequence, and a determination (S8) of the health status of the system of interest.

ELECTROCARDIOGRAM ANALYSIS SYSTEM

To provide an electrocardiogram analysis system capable of determining the need for an electric shock to a patient undergoing cardiopulmonary resuscitation (CPR) with a higher accuracy. An electrocardiogram analysis system includes electrocardiogram (ECG) signal acquiring means 11, ECG signal sampling means 12, ECG spectrogram transforming means 13, impedance signal acquiring means 21, impedance signal sampling means 22, impedance spectrogram transforming means 23, a convolutional neural network (CNN) 4 including an input layer 4I, an output layer 4O, sample data accumulation means 4L, and sample data input means 4T, and electric shock indication reporting means 5. The CNN is a priori provided with sample data including sample ECG spectrograms and sample impedance spectrograms obtained from a large number of subjects, and sample response data on the need for an electric shock, and is optimized by self-learning the sample data.

SYSTEM FOR GENERATING AN ALERT FOR A SYSTEMIC INFECTION

VISUALIZATION OF ARRHYTHMIA DETECTION BY MACHINE LEARNING

Techniques are disclosed for explaining and visualizing an output of a machine learning system that detects cardiac arrhythmia in a patient. In one example, a computing device receives cardiac electrogram data sensed by a medical device. The computing device applies a machine learning model, trained using cardiac electrogram data for a plurality of patients, to the received cardiac electrogram data to determine, based on the machine learning model, that an episode of arrhythmia has occurred in the patient and a level of confidence in the determination that the episode of arrhythmia has occurred in the patient. In response to determining that the level of confidence is greater than a predetermined threshold, the computing device displays, to a user, a portion of the cardiac electrogram data, an indication that the episode of arrhythmia has occurred, and an indication of the level of confidence that the episode of arrhythmia has occurred.

AUTOMATIC IDENTIFICATION OF A LOCATION OF FOCAL SOURCE IN ATRIAL FIBRILLATION (AF)

A method includes receiving, via a plurality of electrodes in a heart, a collection of acquisitions, each including a set of electrophysiological (EP) signals measured by the electrodes. A respective direction of arrival (DOA) and a respective distance relative to the electrodes from which the set of EP signals originated are estimated for each acquisition. The acquisitions are aggregated, to form a statistical distribution of the acquisitions as a function of estimated DOA and distance. Using a statistical test, it is checked whether the statistical distribution is consistent, in accordance with a predefined consistency criterion. If the statistical distribution is found consistent, an estimated location in the heart of a focal source of an arrhythmogenic activity that generated the received EP signals is derived from the statistical distribution. The estimated location of the focal source is overlaid on an anatomical map of at least a portion of the heart.

ELECTROCARDIOGRAM DATA PROCESSING SERVER, METHOD FOR PROCESSING ANALYSIS TASKS FOR SIGNAL SECTIONS CORRESPONDING TO ANALYSIS CONDITION, AND COMPUTER PROGRAM

A method of processing analysis tasks for signal sections corresponding to an analysis condition includes (i) generating output data that includes a plurality of pieces of label information regarding sections of electrocardiogram signal in conjunction with one another; (ii) based on the output data, displaying pre-stored past medical history information regarding the first target object on a separate region, by using the electrocardiogram signal and classification data regarding the electrocardiogram signal; (iii) transmitting the output data to a medical staff terminal; (iv) determining one or more sections of the electrocardiogram signal corresponding to all or a part of the analysis condition as a first section of interest to be analyzed; (v) calculating an expected analysis time for analyzing the first section of interest; (vi) transmitting information regarding the expected analysis time to the medical staff terminal; and (viii) generating an analysis request signal regarding the electrocardiogram ...

A METHOD AND SYSTEM FOR PACING PULSE DETECTION AND PACING ARTIFACT REJECTION

BIOLOGICAL FEATURE INFORMATION DETECTION APPARATUS AND ELECTRONIC DEVICE

LEAD POSITIONING FOR AN IMPLANTABLE PULSE GENERATOR

METHOD AND SYSTEM FOR PREDICTING DISEASES OF THE ELDERLY AND PROVIDING SERVICES

The present disclosure provides a method for predicting diseases of the elderly and providing services. The method includes the steps of: receiving health data collected from a user terminal; generating first prediction data for a first disease using the received health data; generating second prediction data for a second disease using the received health data; calculating the user's likelihood of falling based on the collected health data; and, if the calculated likelihood of the user falling is greater than or equal to a preset threshold, transmitting a falling warning message to a guardian terminal.

단일유도 심전도기기를 활용한 건강상태 예측 시스템

... 본 발명은, 2전극을 구비하여, 2개 이상의 전기축의 심전도를 시차를 두고 각각 측정하여 비동기 심전도 데이터는 획득하는 단일유도 심전도 측정부(110), 및 동일 전기축에서 측정된 표준유도 심전도 및 표준유도 심전도에 상응하는 질환의 유무와 질환의 정도를 매칭한 표준 복수 심전도 데이터셋을 학습하여 미리 구축된 진단 알고리즘(121)을 통해, 단일유도 심전도 측정부(110)로부터 입력된 비동기 심전도 데이터로부터 질환의 유무와 질환의 정도를 예측하는, 예측부(120)를 포함하여, 단일유도 심전도기기에 의해 측정된 2유도 이상의 비동기 심전도 데이터로부터 질환을 예측할 수 있는, 단일유도 심전도기기를 활용한 건강상태 예측 시스템을 개시한다.

심장-표정 동기화 기반 감성 인식 방법 및 시스템

... 본 개시는 심장-표정 움직임 동기화 기반 감성 인식 방법 및 시스템을 제시한다. 평가방법은 피험자의 안면 영상 및 심장 정보를 추출하고, 안면 영상에서 얼굴 영역에 정의된 AU(Action Unit)의 미세움직임(Micro-movement) 데이터를 추출하고, 심장 정보로부터 얻어지는 심장 박동 특성 신호에 동기화 하여 상기 미세 움직임 데이터로부터 HEMM(Heart-Evoked Micro-Movement) 데이터를 추출하고, HEMM 데이터로부터 AU의 움직임에 대한 특성 파라미터를 하나 또는 그 이상 추출하고, 그리고 상기 특성 파라미터를 이용해 상기 피험자의 감성을 평가한다.

Heart rhythm detection method and system using radar sensor

A heart rhythm detection method and system by using radar sensor is capable of collecting an original signal using a radar sensor toward at least one subject, and converting the original signal to a two dimensional image information (i.e., spectrogram) using the concept of image vision. Then, the neural network automatically learns which heartbeat frequency should be focused on and which heartbeat frequency should be filtered out in the two dimensional image information through deep learning, so that the heartbeat frequencies can be extracted effectively.

PHYSIOLOGICAL MONITORING SYSTEM FOR A NEONATE AND A NEONATAL BLANKET POWERING A WIRELESS PHYSIOLOGICAL SENSOR

A CATHETER FOR CARDIAC AND RENAL NERVE SENSING AND MEDIATION

An electrophysiology catheter includes: a catheter with a movable catheter tip; electrodes provided on or in an electrode region in a most distal portion of the catheter tip; sensing and amplification circuitry communicated with the electrodes, the sensing and amplification circuitry communicated with digitizing circuitry disposed in a circuitry region in a least distal portion of the catheter tip for locally sensing tissue-based electrophysiological signals and for bidirectionally communicating digital data signals to and from the circuitry; a flexible bending region of the catheter tip between the most and least distal portions of the catheter tip; a flexible sheath communicated to the sensing and amplification circuitry and digitizing circuitry for transmission of signals thereon; and a handle communicated with the sheath for bidirectionally communicating signals through the sheath between the catheter tip and external mapping station, and for controlling movement of the catheter tip ...

A PORTABLE REAL TIME ECG MONITORING SYSTEM

The present invention relates to a portable real time ECG monitoring system. The designed system is a portable device having a small analog front end circuit, a microcontroller unit (Arduino Mega2560), and display and storage unit. The proposed system acquires the signals using sensor/electrodes placed on the surface of the skin and display these real time signals on TFT LCD screen. The microcontroller programs also calculate and display heart rate. The device is equipped with a memory card that stores a person's ECG data for further analysis. The developed prototype is capable of acquiring and displaying the real time ECG data with continues monitoring of Heart rate of a person and the ECG signals can also be recorded in the memory card that can be visualized by a cardiologist.

영상 및 심전도를 이용한 감정 인식 시스템

... 본 발명은 영상 및 심전도를 이용한 감정 인식 시스템에 관한 것으로서, 측정 대상자의 얼굴을 촬영하는 촬영부와, 상기 측정 대상자의 생체정보를 측정할 수 있도록 상기 측정 대상자에 착용되는 웨어러블 디바이스와, 상기 촬영부에서 촬영된 상기 사용자의 얼굴 영상 및 상기 웨어러블 디바이스에서 제공되는 상기 생체정보를 분석하여 해당 측정 대상자의 감정 상태를 판별하는 감정 판별부를 구비한다. 본 발명에 따른 영상 및 심전도를 이용한 감정 인식 시스템은 측정대상자의 얼굴 영상 및 심전도에 대한 정보를 토대로 해당 측정대상자의 감정 상태를 판별하므로 판별 정보에 대한 신뢰도 및 정확도가 비교적 높다는 장점이 있다. 또한, 본 발명은 감정 판별을 위한 신경망 모델을 구축하는데 있어서, 얼굴 영상 및 심전도에 대한 데이터를 시퀀스 형태로 저장하여 분석하므로 보다 많은 수의 유의미한 데이터를 획득할 수 있어 감정 인식률이 향상되는 장점이 있다.

2개 유도의 비동시적 심전도를 기반으로 하는 동시적 심전도 생성 방법

... 본 발명은 2개 유도의 비동시적 심전도를 기반으로 하는 동시적 심전도 생성 방법에 관한 것이다. 본 발명에 따르면, 동시적 심전도를 생성하는 방법은 유도 심전도 기구로부터 비동시적으로 측정된 복수의 심전도 데이터를 획득하는 단계, 상기 획득한 복수의 심전도 데이터를 기준 심전도 데이터와 참조 심전도 데이터로 분류하고, 상기 참조 심전도 데이터를 비트 별로 구분하여 복수의 참조 단위 심전도 데이터로 변환하는 단계, 상기 기준 심전도 데이터로부터 심전도 유도와 관계없는 시간의 제1 특성값을 추출하고, 상기 복수의 참조 단위 심전도 데이터로부터 심전도 유도와 관계없는 시간의 제2 특성값을 추출하는 단계, 그리고 상기 기준 심전도 데이터에 기준점을 설정하고, 상기 설정된 기준점을 기준으로 상기 복수의 참조 단위 심전도 데이터를 배열하여 동기화된 가상의 심전도를 생성하는 단계를 포함한다.

자율신경계 모니터링 기반 인체 패치형 센서를 이용한 백신 부작용 조기 검출 장치 및 방법

... 본 발명은 자율신경계 모니터링 기반 인체 패치형 센서를 이용한 백신 부작용 조기 검출 장치 및 방법에 관한 것으로서, 보다 구체적으로는 자율신경계 모니터링 기반 인체 패치형 센서를 이용한 백신 부작용 조기 검출 장치로서, 백신 접종자의 백신 부작용을 탐지하기 위해 백신을 맞은 사용자의 심전도를 측정하기 위한 ECG 기기; 상기 ECG 기기와 연동하여 백신을 맞은 사용자의 측정된 심전도를 수집하여 서버로 전송하기 위한 스마트 기기; 및 상기 스마트 기기로부터 전송받은 백신을 맞은 사용자의 심전도의 결과를 분석하고, 그에 따른 백신 부작용 증상을 판단하는 서버를 포함하는 것을 하는 것을 그 구성상의 특징으로 한다. 또한, 본 발명의 특징에 따른 자율신경계 모니터링 기반 인체 패치형 센서를 이용한 백신 부작용 조기 검출 방법은, 자율신경계 모니터링 기반 인체 패치형 센서를 이용한 백신 부작용 조기 검출 방법으로서, (1) ECG 기기가 백신을 맞은 사용자의 심전도를 측정하는 단계; (2) 스마트 기기가 상기 ECG 기기와 연동하여 측정된 심전도를 수집하여 서버로 전송하는 단계; 및 (3) 서버가 상기 스마트 기기로부터 전송받은 심전도의 결과를 분석하고, 그에 따른 백신 부작용 증상을 판단하는 단계를 포함하는 것을 그 구성상의 특징으로 한다. 본 발명에서 제안하고 있는 자율신경계 모니터링 기반 인체 패치형 센서를 이용한 백신 부작용 조기 검출 장치 및 방법에 따르면, 백신 접종자의 백신 부작용을 탐지하기 위해 백신을 맞은 사용자의 심전도를 측정하기 위한 ECG 기기와, ECG 기기와 연동하여 백신을 맞은 사용자의 측정된 심전도를 수집하여 서버로 전송하기 위한 스마트 기기와, 스마트 기기로부터 전송받은 백신을 맞은 사용자의 심전도의 결과를 분석하고, 그에 따른 백신 부작용 증상을 판단하는 서버를 포함하여 구성함으로써, 백신 접종자의 심장질환의 모니터링을 통해 백신을 맞는 사용자의 백신 부작용을 검출하고, 이를 기초로 사용자에게 경고하여 병원에서 정밀 검사를 받을 수 있도록 ...

Incorporating a confidence level into an electrophysiological (EP) map

A method includes receiving (i) a modeled surface of at least a portion of a heart and (ii) multiple EP values measured at multiple respective positions in the heart. Multiple regions are defined on the modeled surface and, for each region, a confidence level is estimated for the EP values whose positions fall in the region. The modeled surface is presented to a user, including (i) the EP values overlaid on the modeled surface, and (ii) the confidence level graphically visualized in each region of the modeled surface.

Methods and systems for estimation of residual ECG noise level and adaptive noise threshold

A system including a means for estimating the residual noise level in electrocardiogram (ECG) signals is disclosed. The disclosed system and methods may be used in an electrocardiograph devices. According to an exemplary embodiment of the present invention, a plurality of electrodes positioned in proximity to a cardiac structure may measure an electrical signal of the cardiac structure to produce the ECG signal. The system may segment the ECG signal into a plurality of segments. For each of the plurality of segments, the linear trend energy and/or direct current (DC) energy may be removed from the segment, and the estimated noise energy of the segment may be calculated. A subset of the plurality of segments with a minimum estimated noise energy may be selected. The residual noise energy of the ECG signal may be estimated by calculating an average of the estimated noise energy over the subset of segments.

ELECTROCARDIOGRAM ANALYSIS SYSTEM

To provide an electrocardiographic analysis system capable of determining the need for an electric shock to a patient undergoing cardiopulmonary resuscitation (CPR) with a higher accuracy. An electrocardiographic analysis system includes electrocardiogram (ECG) signal acquiring means 11, ECG signal sampling means 12, ECG spectrogram transforming means 13, impedance signal acquiring means 21, impedance signal sampling means 22, impedance spectrogram transforming means 23, a convolutional neural network (CNN) 4 including an input layer 41, an output layer 4O, sample data accumulation means 4L, and sample data input means 4T, and electric shock indication reporting means 5. The CNN is a priori provided with sample data including sample ECG spectrograms and sample impedance spectrograms obtained from a large number of subjects, and sample response data on the need for an electric shock, and is optimized by self-learning the sample data. [Selected Drawing] Fig. 1 ...

전기적 바이오 시그널 데이터를 수치 벡터로 변환하는 방법 및 장치, 이를 이용하여 질병을 분석하는 방법 및 장치

... 실시예들은 전기적 바이오 시그널 데이터 특히 단일 채널 혹은 다채널의 심전도 신호 또는 상기 심전도 신호에 기초하여 얻어진 흑백 혹은 컬러 심전도 이미지에 딥러닝 알고리즘을 이용하여 수치적 벡터정보를 추출하는 방법 및 장치, 이를 이용하여 질병을 분석, 예측, 질병에 관한 진단 보조 정보를 제공하는 방법 및 장치에 관련된다.

딥러닝 모델을 이용한 수면 무호흡 환자로부터 관상동맥질환 위험도를 예측하는 방법 및 장치

... 본 발명은 딥러닝 모델을 이용한 수면 무호흡 환자로부터 관상동맥질환 위험도를 예측하는 방법 및 장치에 관한 것으로, 보다 구체적으로는 수면 무호흡 환자로부터 산소 포화도(oxygen saturation) 및 심전도(electrocardiogram, ECG) 측정 데이터를 수득하는 단계; 상기 산소 포화도 및 심전도 측정 데이터를 딥러닝 모델의 입력으로 이용하여 환자의 관상동맥질환 위험도를 예측하는 단계; 및 상기 관상동맥질환 위험도에 대한 정보를 제공하는 단계를 포함하는 관상동맥질환 위험도 예측 방법 및 장치에 관한 것이다. 본 발명의 일 실시예에 따른 관상동맥질환 예측 방법 및 장치는 수면시간 동안 지속적으로 모니터링된 생체신호 중에서 쉽게 수득할 수 있는 심전도와 산소포화도만을 선택하여 딥러닝 분석에 활용하여 사용자의 관상동맥질환의 위험도를 보다 정확하게 예측할 수 있다.

Glucose monitoring system

Disclosed herein are systems and methods for non-invasively monitoring blood glucose levels with a level of accuracy that is high enough to replace invasive methods such as finger prick devices and others. In some examples, glucose values are determined using a patient's electrocardiogram (ECG) signals. Additionally, glucose values may additionally be determined using an impedance spectroscopy based method and then combined with glucose values determined using an ECG waveform to output a blood glucose value.

METHOD AND APPARATUS FOR ANALYZING ELECTROCARDIO SIGNAL, AND SIGNAL RECORDER AND THREE-DIMENSIONAL MAPPING SYSTEM

Disclosed relates to a method and an apparatus for analyzing an ECG signal, an electrophysiological signal recorder, a three-dimensional mapping system, and a computer device. The method includes: acquiring (S202) N first intracardiac electrical signals in a region of interest or at a reference point/in a reference region; generating (S204) a first comparison signal spectrogram according to the N first intracardiac waveforms; acquiring (S206) M second intracardiac electrical signals at the point of interest to acquire M second intracardiac waveforms; generating (S208) a second comparison signal spectrogram according to the M second intracardiac waveforms; performing (S210) a comparative analysis on the first comparison signal spectrogram and the second comparison signal spectrogram and generating a comparative analysis result; and outputting (S212) prompt information indicating whether the point of interest is a focal point according to the comparative analysis result.

Magnetically Oriented Fiber Optic Three-Dimensional Shape

Disclosed herein are systems and methods for providing tracking information of a medical instrument using optical fiber technology in combination with magnetic sensing technology. The medical device includes an optical fiber. The medical device further includes magnetic elements. A magnet field sensor can be configured to detect magnetic fields defined by the magnetic elements, and to provide electrical signals in accordance with the detection of the magnetic fields to a console. The operations of the console include (i) processing the reflected light signals to determine a physical state of the optical fiber, (ii) processing the electrical signals to determine the positions of the magnetic elements, and (iii) combining the physical state of the medical device with the positions of the one or more of the plurality of magnetic elements to determine at least one of a position, a shape, and an orientation of the medical device within the patient body.

ELECTRONIC DEVICE AND METHOD FOR PREDICTING BLOCKAGE OF CORONARY ARTERY

An electronic device and a method for predicting a blockage of a coronary artery are provided. The method includes: obtaining multiple pieces of electrocardiogram (ECG) data respectively corresponding to a coronary artery set; generating multiple first probabilities corresponding to the multiple pieces of electrocardiogram data respectively according to the multiple pieces of electrocardiogram data and a first phase model, generating a first determined result according to the multiple first probabilities, and selecting a first data subset corresponding to a first probability subset from the multiple pieces of electrocardiogram data in response to each one in the first data subset of the multiple first probabilities being greater than a first threshold; generating multiple second probabilities corresponding to the first data subset according to the first data subset and a second phase model, and generating a second determined result according to the multiple second probabilities.

SYSTEM AND METHOD FOR ASSESSING CONDITIONS OF VENTILATED PATIENTS

Method of preparing training data for use in training a health event identification machine-learning model

Training data for use in training a health event identification machine learning model for identifying a health event in a cardiac signal, such as atrial or ventricular fibrillation, includes obtaining a cardiac signal S101 such as an ECG with a temporal sequence of heart activity values (fig 8), labelling the signal with an annotation (A, fig 8) indicative of the presence or absence of a cardiac event and an annotation index indicative of the cardiac activity value associated with the annotation S102 and generating a first dataset from the signal S103, with R cardiac activity values before the annotation index and S values after the annotation index. An offset value is applied to the annotation index to form a shifted annotation index S104, and a second dataset generated (fig 10) with the shifted annotation index (A, fig 10), R values before the shifted annotation index and S values after the shifted annotation index, and where one of the R or S cardiac activity values is the value of ...

우울증 진단을 위한 다중지표 기반의 인공지능을 이용한 데이터 처리 방법

... 본 발명은, 피험자로부터 수집된 데이터를 저장하는 단계, 수집된 데이터를 로딩하여 전처리하는 전처리 단계, 전처리 단계로 생성된 수정데이터를 근거로 이미지화여 히트맵(heatmap)을 생성하는 단계, 히트맵을 이용하여 인공지능을 학습시키는 단계 및 갱신된 히트맵을 근거로 학습된 인공지능을 이용하여 우울증의 전조 및 동반 증상여부를 판단하는 단계를 포함하며, 피험자로부터 수집된 데이터는, 피험자와의 대화로 획득되는 음성 데이터, 피험자의 생체 데이터 및 피험자의 활동 데이터를 포함하는 우울증 진단을 위한 다중지표 기반의 인공지능을 이용한 데이터 처리 방법에 관한 것이다.본 발명에 따른 우울증 진단을 위한 다중지표 기반의 인공지능을 이용한 데이터 처리 방법은 피험자로부터 획득되는 다중지표, 즉 음성 데이터, 생체 데이터 및 활동 데이터를 기반으로 인공지능을 학습시키고 이를 이용하여 우울증의 전조 및 동반증상 여부를 판단할 수 있으므로 진단 정확도를 향상시킬 수 있는 효과가 있다. 또한 피험자가 전문의에 의한 문진이 없이도 일상생활 중에 우울증 여부를 진단할 수 있으므로 전임상 단계(Pre clinical stage)에서 미리 우울증을 판단하고 치료 시기를 앞당길 수 있는 효과가 있다.

전기적 바이오 시그널 데이터를 수치 벡터로 변환하는 방법 및 장치, 이를 이용하여 질병을 분석하는 방법 및 장치

... 실시예들은 전기적 바이오 시그널 데이터 특히 단일 채널 혹은 다채널의 심전도 신호 또는 상기 심전도 신호에 기초하여 얻어진 흑백 혹은 컬러 심전도 이미지에 딥러닝 알고리즘을 이용하여 수치적 벡터정보를 추출하는 방법 및 장치, 이를 이용하여 질병을 분석, 예측, 질병에 관한 진단 보조 정보를 제공하는 방법 및 장치에 관련된다.

생체 정보 측정을 위한 웨어러블 장치 및 방법

일 실시 예에 따른 웨어러블 장치는, 제1 전극 및 상기 제1 전극과 구별되는 제2 전극을 포함하는 심전도 센서, 제1 전극 또는 제2 전극 중 적어도 하나와 전기적으로 연결되는 캐패시턴스 보정 회로, 캐패시턴스 보정 회로의 캐패시턴스 값을 보정하기 위한 제어 데이터를 저장하는 메모리 및 심전도 센서 및 캐패시턴스 보정 회로와 전기적으로 연결되는 적어도 하나의 프로세서를 포함하고, 적어도 하나의 프로세서는 제어 데이터에 기초하여 제어 신호를 생성하고, 제어 신호에 기초하여 캐패시턴스 보정 회로의 캐패시턴스 값이 보정된 상태에서 심전도 센서를 이용하여 심전도 신호를 획득할 수 있다.

고령층의 질환을 예측하여 서비스를 제공하는 방법 및 시스템

... 본 개시는 고령층의 질환을 예측하여 서비스를 제공하는 방법을 제공한다. 이 방법은 사용자 단말로부터 수집된 건강 데이터를 수신하는 단계, 수신된 건강 데이터를 이용하여 제1 질환에 대한 제1 예측 데이터를 생성하는 단계, 수신된 건강 데이터를 이용하여 제2 질환에 대한 제2 예측 데이터를 생성하는 단계, 수집된 건강 데이터에 기초하여 사용자의 낙상 가능성을 산출하는 단계, 산출된 사용자의 낙상 가능성이 미리 설정된 임계값 이상인 경우 보호자 단말로 낙상 주의 메시지를 전송하는 단계를 포함한다.

Apparatus and method for estimating biometric information

An apparatus for estimating biometric information is provided. According to one exemplary embodiment, the apparatus may include a sensor comprising an electrocardiogram (ECG) sensor configured to measure an ECG signal of a user and a pulse wave sensor configured to measure two or more pulse wave signals at two or more measurement sites of the user; and a processor configured to obtain biometric information based on the ECG signal and the two or more pulse wave signals measured by the sensor.

APPARATUS AND METHOD FOR ESTIMATING BIOMETRIC INFORMATION

ELECTROCARDIOGRAM VISUALIZATION METHOD AND DEVICE USING DEEP LEARNING

Disclosed are a method and apparatus for visualizing an electrocardiogram using deep learning. The present embodiment provides a method and apparatus for visualizing an electrocardiogram, the method and apparatus which analyze an electrocardiogram using a deep learning algorithm for accurate arrhythmia determination as a real-time operation algorithm for monitoring a bedridden patient in order to solve the manpower shortage of medical staff, and then visually output it in real time so that a visual help may be provided for medical staff.

Automatic identification of abnormal LAT differences

Apparatus, consisting of a catheter that is configured to be inserted into a chamber of a heart and that has one or more electrodes configured to contact myocardial tissue 5 at multiple locations in the chamber. The one or more electrodes receive electrical signals responsive to a conduction wave traveling through the tissue. The apparatus includes a display and a processor that is configured to receive the electrical signals from the catheter and to 10 render to the display, responsively to the electrical signals, a map of the chamber including an indication of local times of occurrence of the conduction wave at the multiple locations. The processor is also configured to calculate, responsively to the local times of occurrence, 15 a velocity of the conduction wave between the locations and to mark on the map one or more areas of the chamber in which the velocity is below a preset threshold. co-/J -E < 0 ui- z r C/) uj ) z 0 0 o 0j w\ cc -1 (.0 cm m, ...

심전도 해석 매칭지원 서비스 시스템

... 본 발명은 개인 심전도를 적시에 실시간 분석하도록 지원하는 심전도 해석 매칭지원 서비스 시스템에 관한 것으로, 환자의 모바일 통신 단말기에 설치되어 실행되되, 웨어러블 심전도 측정기로부터 수신한 심전도 측정 데이터를 전송하여 판독 요청하고 판독 결과를 전송받아 표시하는 환자용 서비스 앱 모듈과, 상기 환자용 서비스 앱 모듈로부터 전송된 심전도 측정 데이터를 딥러닝 학습된 인공 지능망 모델을 이용해 판독하고, 그 판독 결과에 따라 사전 등록된 의료진을 선별하여 상기 심전도 측정 데이터를 판독하도록 지원하는 환자 의료진 매칭 서버를 포함함을 특징으로 한다.

딥러닝기반의 심전도 판독 시스템

... 본 발명은, 각 의료기관별 심전도데이터 및 심전도데이터에 상응하는 개인식별정보를 저장하며, 심전도데이터를 비식별화시켜 제공하는 하나 이상의 내부 서버(110), 각 의료기관별로, 내부 서버(110)로부터 비식별화된 심전도데이터를 단방향으로 전송받아 학습데이터 세트로 로컬 학습하여, 비식별화된 심전도데이터로 인한 예측결과를 도출하는 해당 로컬 모델을 각각 생성하는 하나 이상의 로컬 서버(120), 및 로컬 서버(120)로부터 로컬 모델을 전송받아 통합하여 글로벌 모델을 생성하고, 글로벌 모델을 로컬 서버(120)로 전송하여 검증하고, 검증된 글로벌 모델의 민감도와 특이도와 정확도값을 수신하는, 중앙 서버(130)를 포함하여, 각 의료기관별로 분산된 심전도데이터를, 개인정보 유출없이, 이용하여 딥러닝 모델을 구축하는, 딥러닝기반의 심전도 판독 시스템을 개시한다.

반려동물 케어 서비스 제공 장치 및 방법

... 본 발명은 반려동물이 안정한 상태를 유지하도록 반려동물이 시청할 수 있는 동영상을 제공하는 반려동물 케어 서비스 제공 장치 및 방법에 관한 것이다. 본 발명의 일 실시 예에 따른 반려동물 케어 서비스 제공 방법은, 반려동물보호자가 구비한 반려동물보호자 단말기로부터 반려동물이 시청하도록 촬영된 반려동물 시청용 동영상을 수신하는 단계와, 기설정된 조건을 만족함에 따라, 반려동물 시청용 동영상을 디스플레이 장치로 전송하여 재생하는 단계를 포함할 수 있다.

Systems and methods for determining location of an access needle in a subject

Systems and methods for epicardial electrophysiology and other procedures are provided in which the location of an access needle may be inferred according to the detection of different pressure frequencies in separate organs, or different locations, in the body of a subject. Methods may include inserting a needle including a first sensor into a body of a subject, and receiving pressure frequency information from the first sensor. A second sensor may be used to provide cardiac waveform information of the subject. A current location of the needle may be distinguished from another location based on an algorithm including the pressure frequency information and the cardiac waveform information.

Sensor system and method for continuous and wireless monitoring and analysis of heart sounds, circulatory effects and core temperature in organisms

A system and method for continuous readout is provided. The object of the invention is achieved by a contact surface for attaching to a surface of an organism, a sensor system in thermal, mechanical and electrical contact with the contact surface, a radio chip operatively connected to the sensor, wherein the radio chip will respond to an induced signal from a reader by reading data from the sensor and transmit said data, and method for operating the sensor wherein the data from the sensor system is compensated for environmental effects using comprising a second sensor for detecting at least one property from the group comprising ambient temperature, pressure, flow, level, proximity, displacement, bio, image, gas, chemical, acceleration, orientation, humidity, moisture, impedance, capacitance, force, electric, magnetic and mass, thus forming compensated data.

Circuits for mobile ecg system

A mobile ECG system includes: a multiplexor, the multiplexor comprising an input port connected with a plurality of electrodes, two output ports, and a control port; a digital detection module being connected with one output port of the multiplexor; an analog detection module being connected with the other output port of the multiplexor and configured to detect a heart beat without utilizing any portion of the digital detection module; and a processor being connected with the control port of the multiplexor and configured to receive an electrical signal and control the multiplexor through the control port to selectively transmit output of all of the electrodes to the analog detection module or the digital detection module based on the electrical signal.

Method and system for pacing pulse detection and pacing artifact rejection

A method and system for detecting pacing pulses originating from implanted pacemaker using surface Electrocardiogram (ECG) signals measured at a relatively low sampling rate and also rejecting the pacing artifacts from the recorded surface ECG signals.

Detection of activation in electrograms using neural-network-trained preprocessing of intracardiac electrograms

A method includes collecting a plurality of bipolar electrograms and respective unipolar electrograms of patients, the electrograms including annotations in which one or more human reviewers have identified and marked a window-of-interest and one or more activation times inside the window-of-interest. A ground truth data set is generated from the electrograms, for training at least one electrogram-preprocessing step of a Machine Learning (ML) algorithm. The ML algorithm is applied to the electrograms, to at least train the at least one electrogram-preprocessing step, so as to detect an occurrence of an activation in a given bipolar electrogram within the window-of-interest.

Medical imaging with ecg triggering

A method is for medical imaging of a patient using a medical imaging system with ECG triggering. In an embodiment, the method includes capturing a respiration signal of the patient including n respiration cycles; concurrently capturing an ECG signal of the patient including m heartbeat intervals; determining a respiration-dependent heartbeat model based upon the n respiration cycles and the m heartbeat intervals; specifying at least one trigger time-point based upon the respiration-dependent heartbeat model; and starting the medical imaging at the specified trigger time-point.

Detection and Response to Arousal Activations

Arousal events can be determined for a user associated with a wearable device, such as a user wearing a wearable computing device including one or more sensors. The one or more sensors may obtain EDA information that may determine a sympathetic nervous system response of the user, which may be responsive to an arousal event or an activation. Detection of events that increase the EDA response may provide information to the user regarding arousal events and provide recommendations to the user to address the arousal events to decrease their response. 1. A method for utilizing a wearable computing device to detect an arousal event of a user , comprising:receiving, from one or more sensors on the wearable computing device, data indicative of the arousal event;classifying the data indicative of the arousal event into a plurality of bins, the plurality of bins corresponding to periods of time;determining at least one bin of the plurality of bins exceeds a threshold; andin response to the at least one bin exceeding the threshold, providing, via a display screen of the wearable computing device, a notification to the user identifying the arousal event.2. The method of claim 1 , wherein the arousal event is caused by a sympathetic nervous system response of the user.3. The method of claim 2 , wherein the notification comprises a recommendation for the user as to how to lower the sympathetic nervous system response.4. The method of claim 1 , wherein the data indicative of the arousal event comprises electrodermal activity (EDA) data captured using the one or more sensors claim 1 , the one or more sensors comprising at least one EDA sensor.5. The method of claim 1 , wherein the data indicative of the arousal event comprises electrocardiography (ECG) data captured using the one or more sensors claim 1 , the one or more sensors comprising at least one ECG sensor.6. The method of claim 1 , further comprising transforming the data indicative of the arousal event.7. The method of ...

Apparatus for automatically determining sleep disorder using deep running and operation method of the apparatus

Provided is an automatic determination apparatus using a deep learning, the automatic determination apparatus including a signal data processor configured to collect signal data detected through polysomnography, to extract feature data by analyzing a feature of the collected signal data, and to transform the extracted feature data to time series data; and a sleep stage classification model processor configured to input the processed signal data to a pre-generated sleep stage classification model, and to classify a sleep stage corresponding to the signal data. The sleep stage classification model processor is configured to classify the sleep stage based on at least one of an American Academy of Sleep Medicine (AASM) standard and a Rechtschaffen and Kales (R&K) standard using an epoch unit of time series data as the processed signal data.

REMOVING FAR-FIELD FROM INTRACARDIAC SIGNALS

In one embodiment, a method includes receiving first intracardiac signals including first far-field components captured by at least one first sensing electrode of a first catheter, the at least one sensing electrode being in contact with tissue of a cardiac chamber of a first living subject, and at least one far-field signal captured from at least one far-field electrode inserted into the cardiac chamber and not in contact with the tissue of the cardiac chamber, training a neural network to remove far-field components from intracardiac signals responsively to the first intracardiac signals and the at least one far-field signal, receiving second intracardiac signals captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject, and applying the trained neural network to the second intracardiac signals to remove respective second far-field components from the second intracardiac signals. 1. A method for analyzing signals , comprising:receiving: first intracardiac signals comprising first far-field components captured by at least one first sensing electrode of a first catheter, the at least one sensing electrode being in contact with tissue of a cardiac chamber of a first living subject; and at least one far-field signal captured from at least one far-field electrode inserted into the cardiac chamber and not in contact with the tissue of the cardiac chamber;training an artificial neural network to remove far-field components from intracardiac signals responsively to the received first intracardiac signals and the at least one far-field signal;receiving second intracardiac signals captured by at least one second sensing electrode of a second catheter inserted into a cardiac chamber of a second living subject; andapplying the trained artificial neural network to the second intracardiac signals to remove respective second far-field components from the second intracardiac signals.2. The method according to ...

METHODS, SYSTEMS AND MEDIA FOR DETRENDING BIOELECTRIC SIGNALS

Methods, systems, and media are disclosed for detrending a bioelectric signal. In some embodiments, the disclosed system can include a processor configured to receive the bioelectric signal, identify at least one breakpoint section corresponds to a rapid change of amplitude of the bioelectric signal, smooth an amplitude of the bioelectric signal after the at least one breakpoint section; and reconstruct the bioelectric signal based on the smoothed amplitude of the bioelectric signal and a reset of the breakpoint section to remove extrinsic components caused by a non-biological factor from the bioelectric signal. 1. A system for detrending a bioelectric signal , comprising: receive the bioelectric signal;', 'identify at least one breakpoint section corresponds to a rapid change of amplitude of the bioelectric signal;', 'smooth an amplitude of the bioelectric signal after the at least one breakpoint section; and', 'reconstruct the bioelectric signal based on the smoothed amplitude of the bioelectric signal and a reset of the breakpoint section to remove extrinsic components caused by a non-biological factor from the bioelectric signal., 'a processor configured to2. The system of claim 1 , further comprising:an electrode configured to collect the bioelectric signal, wherein the bioelectric signal comprises a cardiac electrophysiology signal.3. The system of claim 1 , wherein the processor is further configured to:determine a slew threshold indicating a minimum amplitude change for identifying an energy injection event caused by the non-biological factor;determine if the rapid change of amplitude of the bioelectric signal is larger than the slew threshold and a time point of the rapid change; andidentify the at least one breakpoint section based on the determined time point and a parametric temporal radius around the determined time point.4. The system of claim 3 , wherein the processor is further configured to:adjust at least one of the slew threshold, the parametric ...

Method for measuring social relationship using heart rhythm pattern (hrp)

A social intimacy determining method includes detecting electrocardiogram (ECG) data from at least two subjects; detecting heart rhythm pattern (HRP) data from ECG signals of the two subjects; and determining a relationship (intimacy) between the two subjects by comparing the FIRP data of the two subjects.

RECORDING DEVICE, RECORDING METHOD, AND PROGRAM

A recording device includes: an acquisition unit () configured to acquire vital signs through a multi-electrode catheter (X) having a plurality of electrodes; a recording unit () configured to record a bipolar potential of a main channel which is defined by combining the plurality of electrodes, using the vital signs; an addition unit () configured to add a mark to each waveform plotted based on a potential of the bipolar potential, at a predetermined position on a time axis; and an adjusting unit () configured to adjust a position of the mark added to each waveform. The adjusting unit () is configured to adjust the position of the mark added to the bipolar potential of the main channel, based on bipolar potentials of reference channels including electrodes included in the main channel. 1. A recording device comprising:an acquisition unit configured to acquire vital signs through a sensor device having a plurality of electrodes;a recording unit configured to record a bipolar potential of a main channel which is defined by combining the plurality of electrodes, using the vital signs;an addition unit configured to add a mark to each waveform plotted based on variation of the bipolar potential over time, at a predetermined position on a time axis; andan adjusting unit configured to adjust a position of the mark added to each waveform,wherein the adjusting unit is configured to adjust the position of the mark added to the bipolar potential of the main channel, based on bipolar potentials of reference channels including electrodes included in the main channel.2. The recording device according to claim 1 , whereinbased on waveforms of the bipolar potentials of the reference channels included in a predetermined reference range, the adjusting unit is configured to adjust the position of the mark added to the bipolar potential of the main channel included in the predetermined reference range.3. The recording device according to claim 2 , whereinthe number of the reference ...

Systems and methods for calculating patient information

Provided herein are systems and methods for calculating patient information. The method includes determining a transfer matrix, recording electric potentials via a first set of recording electrodes located at a first set of recording locations to create a first set of recorded signals, and calculating patient information for a set of target locations by applying the transfer matrix to the first set of recorded signals. The transfer matrix is a characterization of electrical properties of tissue between the first set of recording locations and the set of target locations.

Method and apparatus for enhancement of chest compressions during cpr

An apparatus for assisting a rescuer in performing chest compressions during CPR on a victim, the apparatus comprising a pad or other structure configured to be applied to the chest near or at the location at which the rescuer applies force to produce the chest compressions, at least one sensor connected to the pad, the sensor being configured to sense movement of the chest or force applied to the chest, processing circuitry for processing the output of the sensor to determine whether the rescuer is substantially releasing the chest following chest compressions, and at least one prompting element connected to the processing circuitry for providing the rescuer with information as to whether the chest is being substantially released following chest compressions.

FETAL HEART RATE VARIABILITY MONITORING DEVICE

Provided is a fetal heart rate variability monitoring device capable of easily determining a fetal condition. A fetal heart rate variability monitoring device includes a processing unit and a display unit that acquire a fetal heart rate and display a fetal heart rate diagram showing the fetal heart rate over time, an LTV and STV conversion processing unit that calculates STV and LTV from the fetal heart rate, and an event input unit that can designate a predetermined period on the fetal heart rate diagram. The processing unit and the display unit have a function of issuing notification of the STV and LTV in the predetermined period calculated by the LTV and STV conversion processing unit when the predetermined period is designated by the event input unit. 1. A fetal heart rate variability monitoring device comprising:display that acquires a fetal heart rate and displaying a fetal heart rate diagram showing the fetal heart rate over time;calculator that calculates variability information which is information about fetal heart rate variability from the fetal heart rate;a designated period input unit capable of designating a predetermined period on the fetal heart rate diagram; andnotifier that issues notification of the variability information in the predetermined period calculated by the calculator when the predetermined period is designated by the designated period input unit.2. The fetal heart rate variability monitoring device according to claim 1 ,wherein the calculator calculates at least one of values of STV and LTV at a time interval set in advance, andthe display displays the value, which is successively calculated, in a graph.3. The fetal heart rate variability monitoring device according to claim 1 ,wherein the notifier causes the display to display information indicating the predetermined period designated by the designated period input unit in correspondence with the fetal heart rate diagram.4. The fetal heart rate variability monitoring device according ...

Waveform Signal Processing Method and Apparatus

A method includes obtaining a filtered waveform signal, marking the waveform signal as K signal line segments based on monotonicity, extracting line segment data of each signal line segment, and determining a line segment matching template of the waveform signal based on the line segment data of each signal line segment, where the line segment matching template includes M consecutive signal line segments, and M is an integer less than K. The method further includes matching each of the K signal line segments with the M signal line segments included in the line segment matching template, and determining a target wave group of the waveform signal based on a matching result of each signal line segment. The method further includes determining periodic signal data of the waveform signal based on line segment data of the target wave group.

Apparatus and method for estimating biometric information

An apparatus for estimating biometric information is provided. According to one exemplary embodiment, the apparatus may include a sensor comprising an electrocardiogram (ECG) sensor configured to measure an ECG signal of a user and a pulse wave sensor configured to measure two or more pulse wave signals at two or more measurement sites of the user; and a processor configured to obtain biometric information based on the ECG signal and the two or more pulse wave signals measured by the sensor.

APPARATUS AND METHOD FOR EXTRACTING FEATURE OF BIO-SIGNAL, AND APPARATUS FOR DETECTING BIO-INFORMATION

An apparatus configured to extract a feature from a bio-signal is disclosed. The apparatus includes a bio-signal acquirer configured to acquire the bio-signal, and a processor configured to analyze concavity and convexity of a waveform of the bio-signal in intervals of the bio-signal, and extract the feature from the bio-signal based on the analyzed concavity and the analyzed convexity. 1. (canceled)2. (canceled)3. An apparatus for detecting bio-information of a user , the apparatus comprising:a sensor configured to irradiate the user with light, detect the light scattered or reflected by the user, and measure a photoplethysmography (PPG) signal; and derive a secondary differential signal of the PPG signal;', 'calculate a difference between a local maximum value and a local minimum value in an interval of the secondary differential signal as a convex to concave difference (CCD) value;', 'extract a characteristic point from the PPG signal based on the CCD value;', 'extract a feature from the PPG signal based on the characteristic point; and', 'detect the bio-information of the user based on the feature,, 'a processor configured towherein the characteristic point comprises at least one of time information of the local minimum value, and amplitude information of the PPG signal corresponding to the time information.4. The apparatus according to claim 3 , wherein the processor is further configured to:segment the interval of the secondary differential signal into sub-intervals.5. The apparatus according to claim 4 , wherein the processor is further configured to:segment a portion of the secondary differential signal from a local maximum point of the secondary differential signal to a subsequent local minimum point as one of the sub-intervals.6. The apparatus according to claim 4 , wherein the processor is further configured to:merge the sub-intervals based on a difference between a local minimum value and a subsequent local maximum value in the interval of the secondary ...

Lung function monitoring from heart signals

A breathing monitor has ECG, PPG, or bioimpedance sensors feeding a neural network to provide inspiratory and expiratory phases of breathing and tidal volume (TV), filters for the inspiratory and expiratory phases of breathing and TV; and apparatus configured to provide measurements of breathing rate (RR), and fractional inspiratory time (FIT). In embodiments, the device uses the RR, FIT, and TV to estimate spirometric parameters such as lung obstruction severity, forced expiratory volume in one second (FEV1), forced expiratory volume (FEV), forced vital capacity (FVC), FEV1/FEV ratio, and FEV1/FVC ratio. A method of determining a classification of lung obstruction from heart signals includes feeding heart signals into a neural network to determine TV and inspiratory and expiratory classes used to determine FIT and RR; and using FIT, RR, and TV to determine lung obstruction classification of mild, moderate, severe, or very severe obstructive symptoms.

INTELLIGENT PORTABLE MEDICAL INSTRUMENT

An intelligent portable medical instrument has an information processing unit and a data storage unit which are connected to a measurement and human body data collection unit. The measurement and human body data collection unit measures electrical, chemical, and acoustic data and sends the data to the information processing unit. The information processing unit compares the measured human physiological index data with the standard ranges of values and makes a preliminary health diagnosis opinion. The preliminary health diagnosis opinion and the measured data are transmitted to an in vitro unit which preferably uploads the information to a cloud server. The in vivo portion of the intelligent portable medical instrument is provided by a single integrated circuit. 1. An intelligent portable medical instrument , comprising:at least one information processing unit, a measurement and body data collection unit, and a data storage unit, wherein said at least one information processing unit and said measurement and body data collection unit, and said data storage unit are operatively connected for collecting, processing and storing living body data and are integrated into one or more semiconductor integrated circuit chips which are disposed within a living body;said measurement and body data collection unit which are configured to collect physiological indicator data and send the collected physiological indicator data to said at least one information processing unit which stores the collected physiological indicator data in said data storage unit;said data storage unit configured to store both the collected physiological indicator data and standard ranges of preset physiological indicators; andwherein said at least one information processing unit compares the collected physiological indicator data with the standard ranges of preset physiological indicators, and determines a preliminary health diagnosis opinion according to an analysis of the comparison and sends the ...

ELECTROCARDIOGRAM WAVEFORM ANALYSIS APPARATUS

An electrocardiogram waveform analysis apparatus includes: a waveform input section to which an electrocardiogram waveform is input; an application range setting section configured to set an application range of a filter in the input electrocardiogram waveform; a filtering section configured to apply a filtering process to the application range of the filter; a beat detector configured to detect beats from the electrocardiogram waveform that has undergone the filtering process; and an output section configured to perform an outputting process based on the detected beats. 1. An electrocardiogram waveform analysis apparatus comprising:a waveform input section to which an electrocardiogram waveform is input;an application range setting section configured to set an application range of a filter in the input electrocardiogram waveform;a filtering section configured to apply a filtering process to the application range of the filter;a beat detector configured to detect beats from the electrocardiogram waveform that has undergone the filtering process; andan output section configured to perform an outputting process based on the detected beats.212. The electrocardiogram waveform analysis apparatus according to claim 1 , wherein the electrocardiogram waveform that is input to the waveform input section is an electrocardiogram waveform that extends over a predetermined time period and is measured by a patient monitor claim 1 , a defibrillator claim 1 , a -lead electrocardiograph claim 1 , or a Holter electrocardiograph.3. The electrocardiogram waveform analysis apparatus according to claim 1 , whereinthe application range setting section is configured to set a specific amplitude as a reference, the specific amplitude being in the predetermined time period of the electrocardiogram waveform, the specific amplitude satisfying a predetermined standard, andthe application range setting section is configured to set, as the application range, one or more waveforms having an ...

Gpu-based parallel electrocardiogram signal analysis method, computer readable storage medium and device

The present disclosure provides a GPU-based parallel electrocardiogram signal analysis method, comprising: performing a filtering process of electrocardiogram signals through a long interval artifact removal and a short interval artifact removal; performing a QRS detection of the filtering-processed electrocardiogram signals through an R-wave position extraction, a QRS complex start and end positions extraction and a QRS complex width extraction; performing an abnormal waveform classification of the QRS-detected electrocardiogram signals through template creation; wherein at least one of the long interval artifact removal, the short interval artifact removal, the R-wave position extraction, the QRS complex width extraction and the creation template is performed by a multiple threads at a GPU device side in parallel, any thread being read through its unique index number to process corresponding data. By executing one or more steps of the electrocardiogram signal analysis at GPU in parallel, the present disclosure increases the analysis speed of the electrocardiogram signals.

GENERATING ELECTROCARDIOGRAMS FROM MULTIPLE REFERENCES

A method is provided. The method is implemented by an interpretation engine executed by processors coupled to a memory. The method includes receiving a bipolar intracardiac reference signal from reference electrodes of a catheter and executing a preprocessing of the bipolar intracardiac reference signal. The method further includes interpreting the bipolar intracardiac reference signal according to a threshold for contact by a reference electrode of the electrodes. 1. A method comprising:receiving, by an interpretation engine executed by one or more processors coupled to a memory, a bipolar intracardiac reference signal from a plurality of reference electrodes of a catheter;executing, by the interpretation engine, a preprocessing of the bipolar intracardiac reference signal; andinterpreting, by the interpretation engine, the bipolar intracardiac reference signal according to a threshold for contact by a reference electrode of the plurality of electrodes.2. The method of claim 1 , wherein the preprocessing comprises a power noise removal filter claim 1 , high pass filter claim 1 , or median filtering.3. The method of claim 1 , wherein the method comprises determining the threshold for the contact.4. The method of claim 1 , wherein the threshold for the contact comprises dynamic threshold.5. The method of claim 1 , wherein points associated with the reference electrode are not collected when the threshold is crossed.6. The method of claim 1 , wherein the method comprises switching from the reference electrode to a second reference electrode of the plurality of the electrodes when the threshold is crossed.7. The method of claim 1 , wherein the catheter is in communication with the interpretation engine and provides the bipolar intracardiac reference signal.8. The method of claim 1 , wherein the method comprises determining which of two reference electrodes of the plurality of the electrodes caused the threshold to be crossed and utilizing a remaining other one of two ...

SIGNAL AND CORRECTION PROCESSING FOR ANATOMICAL STRUCTURE MAPPING DATA

A method is provided. The method is implemented by a mapping engine. The method includes receiving biometric data of at least a portion of an anatomical structure from at least a catheter and analyzing the biometric data based on an automatic tagging operation, a time weighted local activation time assignment operation, or a discrimination operation. The method also includes determining scar tissue of the portion of the anatomical structure based on the analyzing of the biometric data. 1. A method comprising:receiving, by a mapping engine executed by one or more processors, biometric data of at least a portion of an anatomical structure from at least a catheter;analyzing, by the mapping engine, the biometric data based on at least one of an automatic tagging operation, a time weighted local activation time assignment operation, and a discrimination operation; anddetermining scar tissue of the portion of the anatomical structure based on the analyzing of the biometric data.2. The method of claim 1 , wherein the automatic tagging operation comprises:determining, by the mapping engine, electrical measurements of the biometric data that have an indication associated therewith to generate a sub-data set of measurements; andassigning, by the mapping engine, a scar probability to each measurement of the sub-data set.3. The method of claim 2 , wherein the method further comprises determining a time window and which of the electrical measurements within the time widow have the indication to generate the sub-data set.4. The method of claim 2 , wherein the indication comprises a tissue proximity indicator feature of the mapping engine that identifies contact by the catheter with the portion of the anatomical structure.5. The method of claim 1 , wherein the scar probability is assigned based on voltage of the corresponding electrical measurement.6. The method of claim 1 , wherein the scar probability scar probability is assigned using fuzzy logic.7. The method of claim 1 , ...

Heartbeat Categorization

An automatic method for categorizing heartbeats using two or more selected ECG signals, the method comprising, when a heartbeat has been detected, the steps of: (a) determining a signal velocity for each selected signal at a categorization fiducial time t C within the detected heartbeat; (b) forming a vector F(t C ) having as its components the velocities of each of the selected signals at time t C ; (c) determining the angle between the vector F(t C ) and a previously-stored template vector; (d) comparing the angle with a threshold angle; and (e) if the angle is less than the threshold angle, categorizing the heartbeat as similar to a heartbeat which corresponds to the template vector.

Biological information analysis device, system, and program

A biological information analysis device includes: an indicator extraction unit configured to extract, from time-series data regarding blood pressure waveforms consecutively measured by a sensor that is configured to be worn on a body part of a user and to be capable of non-invasively measuring a blood pressure waveform for each heartbeat, and from time-series data regarding breathing measured by a respiration sensor during a period of time corresponding to the time-series data regarding blood pressure waveforms, an indicator indicating the relationship between the user's breathing and changes in blood pressure; and a processing unit configured to perform processing that is based on the indicator thus extracted.

System and method for improved cardiac rhythm classification from the time between heart beat intervals using non-linear dynamics

A system for classifying cardiac rhythms is disclosed. The system includes one or more processors, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors. The program instructions include first program instructions to obtain data representative of a time series of the times between heartbeats. The program instructions further comprise second program instructions to segment the time series into a plurality of segments. The program instructions further comprise third program instructions to calculate a plurality of parameters corresponding to each of the 30-second segments. The program instructions further comprise fourth program instructions to analyze the obtained data and the calculated parameters using a plurality of multivariable algorithms for rhythm classification. The program instructions further comprise fifth program instructions to synthesize the results of the plurality of multivariable algorithms to formulate a single rhythm classification.

Patient Signal Analysis Based on Vector Analysis

Disclosed herein is a framework for facilitating patient signal analysis based on vector analysis. In accordance with one aspect, a set of vectors is generated from a patient signal data waveform. The vectors may be directed from a common center to points of interest on the patient signal data waveform. The framework may further extract one or more vector parameters from the set of vectors, and determine one or more vector ratios based on the vector parameters to monitor changes in the patient signal data waveform.

Automated detection of cardiopulmonary resuscitation chest compressions

A system for assisting a rescuer in providing cardiopulmonary resuscitation (CPR) chest compressions includes a motion sensor configured to generate motion sensor signals indicative of chest motion and a defibrillator. The defibrillator includes a processor and a display screen configured to provide CPR feedback and defibrillation information. The processor is configured to receive the motion sensor signals, analyze the motion sensor signals for features characteristic of a chest compression delivery type to distinguish between chest compression delivery types comprising manual compression, non-automated ACD, and automated ACD, and selectively provide the CPR feedback at the display screen based on an identification of the chest compression delivery type such that the CPR feedback includes a plurality of CPR parameters for the manual compression delivery type and remove at least portions of the CPR parameters from the display screen for the non-automated ACD and the automated ACD compression delivery types.

Implantable cardiac device with dyspnea measurement

Cardiac monitoring and/or stimulation methods and systems employing dyspnea measurement. An implantable cardiac device may sense transthoracic impedance and determine a patient activity level. An index indicative of pulmonary function is implantably computed to detect an episode of dyspnea based on a change, trend, and/or value exceeding a threshold at a determined patient activity level. Trending one or more pulmonary function index values may be done to determine a patient's pulmonary function index profile, which may be used to adapt a cardiac therapy. A physician may be automatically alerted in response to a pulmonary function index value and/or a trend of the patient's pulmonary index being beyond a threshold. Computed pulmonary function index values and their associated patient's activity levels may be stored periodically in a memory and/or transmitted to a patient-external device.

Adaptive waveform appraisal in an implantable cardiac system

Methods and implantable devices for cardiac signal analysis. The methods and devices make use of waveform appraisal techniques to distinguish event detections into categories for suspect events and waveform appraisal passing events. When adjustments are made to the data entering analysis for waveform appraisal, the waveform appraisal thresholds applied are modified as well. For example, when the data analysis window for waveform appraisal changes in length, a waveform appraisal threshold is modified. Other changes, including changes in sensing characteristics with which waveform appraisal operates may also result in changes to the waveform appraisal threshold including changes in gain, sensing vector, activation of other devices, implantee posture and other examples which are explained.

TWELVE-LEAD ELECTROCARDIOGRAM USING A THREE-ELECTRODE DEVICE

An apparatus includes an electrocardiograph device having first, second, and third, electrode assemblies with first, second, and third electrodes adapted to measure first, second, and third electrical signals of an individual, respectively. The apparatus further includes a processing device to: determine a Lead I from the first electrical signal and the second electrical signal; determine a Lead II from the second electrical signal and the third electrical signal; generate a Lead III using (Lead III=Lead II−Lead I); determine, using a machine learning model trained using measured twelve-lead ECG data, Leads aVR, aVL, aVF, V V V V V and V based on Lead I, Lead II, and Lead III; and provide Leads Lead I, Lead II, Lead III, aVR, aVL, aVF, V V V V V and V for display on a client device. 1. An apparatus , comprising:an electrocardiograph device having first, second, and third, electrode assemblies with first, second, and third electrodes adapted to measure first, second, and third electrical signals of an individual, respectively; and determine a Lead I from the first electrical signal and the second electrical signal;', 'determine a Lead II from the second electrical signal and the third electrical signal;', 'generate a Lead III using (Lead III=Lead II−Lead I);', {'b': 1', '2', '3', '4', '5', '6, 'determine, using a machine learning model trained using measured twelve-lead ECG data, Leads aVR, aVL, aVF, V, V, V, V, V, and V based on Lead I, Lead II, and Lead III; and'}, {'b': 1', '2', '3', '4', '5', '6, 'provide Leads Lead I, Lead II, Lead III, aVR, aVL, aVF, V, V, V, V, V, and V for display on a client device.'}], 'a processing device to2. The apparatus of claim 1 , wherein the Lead II is determined sequentially with Lead I.3. The apparatus of claim 2 , wherein the processing device is further to time align Lead I and Lead II.41. The apparatus of claim 1 , wherein the Lead II is determined contemporaneously with Lead .5. The apparatus of claim 1 , the processing device ...

Sensible Wired Earphones

Sensible wired earphones are electrically connected with information equipment and contain: at least one body, a controller, and a telecommunication connector. Each of the at least one body includes a sensing unit, a micro-control unit, a casing, and a speaker. The sensing unit is configured to acquire user's photoplethysmography (PPG) signals, the micro-control unit is electrically connected with said each body, the sensing unit, and the telecommunication connector which is electrically coupled with the information equipment. The micro-control unit is configured to process and analyze the user's PPG signals, and the user's PPG signals are processed and analyzed by the information equipment. The controller includes a controlling interface electrically connected with the micro-control unit, the controller is electrically in connection with the telecommunication connector via a first electric wire, and said each body is electrically connected with the micro-control unit via a second electric wire.

Systems and methods for medical imaging

A method may include obtaining scan data that is captured by scanning a heart of a subject with the imaging device. The method may include obtaining electrocardiogram (ECG) data during the scans of the heart of the subject. The method may include determining first scan data from the scan data. The method may include reconstructing the cardiac image based on the first scan data. The method may also include performing one or more iterations. Each of the one or more iterations may include determining whether there is a pulsatile artifact in the reconstructed cardiac image, determining a second time period of at least one cardiac cycle based on the pulsatile artifact, and reconstructing the cardiac image based on the scan data and the second time period.

Non-Invasive Monitoring of Physiological Conditions

This document provides methods and materials related to the non-invasive measurement of analytes in blood.

Biological information analyzing device, system, and program

A biological information analyzing device includes: an indicator extraction unit that extracts, from blood pressure waveform data measured continuously by a sensor that is worn on a user's body and can non-invasively measure a blood pressure waveform for each of heartbeats, an indicator expressing a load placed on the user's heart by an activity, and a processing unit that outputs the indicator extracted by the indicator extraction unit. The indicator extraction unit finds the indicator on the basis of a difference between a blood pressure waveform in a resting section corresponding to when the user is in a resting state and a blood pressure waveform in an active section corresponding to when the user is engaged in the activity.

Biological information analysis device, system, and program

A biological information analysis device includes: an indicator extraction unit configured to extract, from data regarding blood pressure waveforms consecutively measured by a sensor configured to be worn on a body part of a sleeping user and to be capable of non-invasively measuring a blood pressure waveform for each heartbeat, an indicator that is related to the functionality of respiratory organs of the user, based on characteristics of the blood pressure waveforms; and a processing unit configured to perform processing that is based on the indicator thus extracted.

System and Method for Characterizing Arrhythmias

A system and method of discovering the origin of a wave front in a human heart by measuring the difference in time of the activation of electrodes due to the propagation of the wave front through the heart. The location of the origin can then be mathematically modelled using the knowledge of the distance between the electrodes and the difference in time of activation.

Anti-tachycardia pacing for low power implantable medical devices

Methods and devices are provided for managing anti-tachycardia pacing therapy delivered by an implantable medical device (IMD). The methods and devices detect events from cardiac signals sensed at electrodes of the IMD. The cardiac signals represent a ventricular tachycardia (VT) episode that includes at least a select number of VT events having a corresponding VT cycle length. The methods and devices analyze the VT cycle length to define an anti-tachycardia pacing (ATP) therapy that includes a first coupling interval and deliver a first ATP pulse that is spaced the first coupling interval after a reference refractory VT event sensed at the electrodes. The methods and devices deliver a second ATP pulse following the first ATP pulse by a non-stimulation segment that is at least one and three-quarters (1.75) times a projected VT cycle length.

Computational localization of fibrillation sources

A system for computational localization of fibrillation sources is provided. In some implementations, the system performs operations comprising generating a representation of electrical activation of a patient's heart and comparing, based on correlation, the generated representation against one or more stored representations of hearts to identify at least one matched representation of a heart. The operations can further comprise generating, based on the at least one matched representation, a computational model for the patient's heart, wherein the computational model includes an illustration of one or more fibrillation sources in the patient's heart. Additionally, the operations can comprise displaying, via a user interface, at least a portion of the computational model. Related systems, methods, and articles of manufacture are also described.

Wearable device for the detection of cardiac signals, a system comprising said device and a relative method of operation

Described is a detection device (1) for detecting cardiac electrical signals, wearable by a patient, comprising a right lower electrode (11) and a left lower electrode (12), for detecting cardiac electrical potentials, positioned in alignment with each other on a first horizontal axis (x′), spaced apart from each other by a first distance (d1); a right upper electrode (13) and a left upper electrode (14), for detecting cardiac electrical potentials, positioned above said lower electrodes (11, 12), and being aligned with each other on a second horizontal axis (x″), parallel to said first horizontal axis (x′), and spaced from each other by a second distance (d2), greater than or equal to said first distance (d1); and a logic control unit (U), electrically connected to said electrodes (11, 12, 13, 14), wherein said logic control unit (U) is configured to receive a first bipolar lead (DI′), detected between said left upper electrode (14) and said right upper electrode (13); a second bipolar lead (DII′), detected between said left lower electrode (12) and said right upper electrode (13); a third bipolar lead (DIII′), detected between said left lower electrode (12) and said left upper electrode (14); a first unipolar lead (V1′), detected between said right lower electrode (11) and a first average potential, and a second unipolar lead (V2′), detected between said left lower electrode (12) and said first average potential, wherein said first average potential is equal to the average of detected signals, with respect to a reference potential, on said right upper electrode (13), on said left upper electrode (14) and on said left lower electrode (12). The invention also relates to a system comprising said device and a relative method of operation.

Wearable monitor

The present disclosure relates to a wearable monitor device and methods and systems for using such a device. In certain embodiments, the wearable monitor records cardiac data from a mammal and extracts particular features of interest. These features are then transmitted and used to provide health-related information about the mammal.

Pace pulse detector for a medical device

In situations in which an implantable medical device (e.g., a subcutaneous ICD) is co-implanted with a leadless pacing device (LPD), it may be important that the subcutaneous ICD knows when the LPD is delivering pacing, such as anti-tachycardia pacing (ATP). Techniques are described herein for detecting, with the ICD and based on the sensed electrical signal, pacing pulses and adjusting operation to account for the detected pulses, e.g., blanking the sensed electrical signal or modifying a tachyarrhythmia detection algorithm. In one example, the ICD includes a first pace pulse detector configured to obtain a sensed electrical signal and analyze the sensed electrical signal to detect a first type of pulses having a first set of characteristics and a second pace pulse detector configured to obtain the sensed electrical signal and analyze the sensed electrical signal to detect a second type of pulses having a second set of characteristics.

ECG MEASUREMENT SYSTEM AND ECG TRANSMITTER

An electrocardiographic transmitter executes statistical processes for an electrocardiographic signal to calculate an average value HRav of a heart rate HR in a predetermined period of time. In a case where the average value HRav of the heart rate HR is abnormal, the electrocardiographic transmitter continuously transmits electrocardiogram data based on the electrocardiographic signal to a terminal. The terminal receives and transfers the electrocardiogram data as it is to a host device. The host device stores therein and supplies the transferred electrocardiogram data for a diagnosis by medical worker. Thus, the state of a subject's heart can be monitored over the long term. 1. An electrocardiographic measurement system comprising:an attachable electrocardiographic transmitter that includes an electrocardiographic signal detection circuit configured to detect an electrocardiographic signal and a wireless communication circuit configured to wireless transmit the electrocardiographic signal, the transmitter capable of being attached to the body of a subject; anda terminal configured to receive the electrocardiographic signal that is wireless transmitted from the electrocardiographic transmitter;wherein the electrocardiographic transmitter executes a statistical process for the electrocardiographic signal to compute an amount of statistics and then transmits the amount of statistics to the terminal, andthe terminal determines whether or not the received amount of statistics is out of a predetermined range, andthe electrocardiographic transmitter transmits electrocardiogram data based on the electrocardiographic signal to the terminal in one case where the terminal determines that the amount of statistics is out of the predetermined range, and, on the other hand, does not transmit the electrocardiogram data to the terminal in the other case where the terminal determines that the amount of statistics is within the predetermined range.2. An electrocardiographic ...

SIMULTANEOUS MONITORING OF ECG & BIOIMPEDANCE VIA SHARED ELECTRODES

A system for acquiring electrocardiograph (ECG) and bioimpedance (BI) data is disclosed. The system (an ECG/BI measurement system) can use as few as one or two pairs of electrodes, permitting wearable devices employing the ECG/BI measurement system to be made into smaller, more comfortable, and more inconspicuous formats, as well as decreasing potential failure points in the measurement of electrical signals conducted between the system and the user. The system can measure both ECG and BI data using at least one shared pair of electrodes. In some cases, ECG and BI data are separately extracted from a measured signal across a shared pair of electrodes, while another pair of electrodes is being driven with a supply current. In other cases, internal switching can automatically switch a pair of electrodes between ECG-measuring circuitry and BI-measuring circuitry, such as based on a clock signal or other trigger. 1. A system , comprising:a first pair of electrodes electrically couplable to skin of a user;a second pair of electrodes electrically couplable to the skin of the user, wherein the first pair of electrodes and the second pair of electrodes are arranged in a linear array; anda control system coupled to the first pair of electrodes and the second pair of electrodes, the control system configured to perform operations including:providing an injection current via the first pair of electrodes;acquiring a sensed signal via the second pair of electrodes; anddetermining electrocardiogram (ECG) measurements and bioimpedance (BI) measurements from the sensed signal.2. The system of claim 1 , wherein the second pair of electrodes are positioned within a space defined between each electrode of the first pair of electrodes.3. The system of claim 1 , wherein the control system is housed within an electronics module of a wearable device claim 1 , and wherein the first pair of electrodes and the second pair of electrodes are each electrically coupled to the skin of the user ...

Method for building a heart rhythm classification model

A method for building a heart rhythm classification model that is used to classify a heart rhythm of a person is provided. 12-lead ECG datasets are used to train a neural network model that includes multiple bidirectional LSTM layers. The bidirectional LSTM layers enable the neural network model to analyze the 12-lead ECG datasets in different aspects, so as to enhance classification accuracy.

Computer-implemented method of handling electrocardiogram data

This specification describes a method of visually displaying electrocardiogram data in a compressed manner on the display screen wherein rhythmic information is visible and a method of categorizing zones of the electrocardiogram data.

Machine-Based Risk Prediction for Peri-Procedural Myocardial Infarction or Complication from Medical Data

Machine-based risk prediction or assistance is provided for peri-procedural complication, such as peri-procedural myocardial infarction (PMI). A machine-learned model is used to predict risk of PMI and/or recommend courses of action to avoid PMI in PCI. Various combinations of types or modes of information are used in the prediction, such as both imaging and non-imaging data. The prediction may be made prior to, during, and/or after PCI using the machine-learned model to more quickly reduce the chance of PMI. The workflows for prior, during, and/or post PCI incorporate the risk prediction and/or risk-based recommendations to reduce PMI for patients. 1. A method for machine-based risk prediction for peri-procedural myocardial infarction , the method comprising:imaging, by a medical diagnostic imaging system, a patient, the imaging providing first image data representing an internal cardiac region of the patient, the first image data being from a first mode of data acquisition;acquiring second data for the patient, the second data being for a second mode of data acquisition different than the first mode;determining, by a processor, a risk of the peri-procedural myocardial infarction by input of first data responsive to the first image data and the second data to a machine-learned model; anddisplaying information based on the risk.2. The method of wherein imaging comprises computed tomography imaging claim 1 , magnetic resonance imaging claim 1 , x-ray angiography claim 1 , or intravascular imaging claim 1 , and wherein the first data comprises anatomical claim 1 , heart disease claim 1 , and/or cardiac function measurement claim 1 , the first data based claim 1 , at least in part claim 1 , from detection in the first image data.3. The method of wherein acquiring the second data comprises acquiring blood test measurements claim 1 , ECG measurements claim 1 , genetic data claim 1 , demographic data claim 1 , clinical data claim 1 , or percutaneous coronary intervention ...

Smart wristband for multiparameter physiological monitoring

An ergonomically designed smart wristband for clinical-grade multiparameter monitoring is disclosed. The smart wristband incorporates multiple sensors including custom-designed reflective arterial pulse sensors, a thermopile sensor, and electrocardiogram (ECG) electrodes. When the smart wristband is worn on the wrist, the biosensors contact the skin. The smart wristband may tether wirelessly to a mobile or any other computing device to continuously acquire and stream information like arterial pulse waveform and temperature data. Algorithms running on the computing device or onboard microprocessor analyze the acquired data to report parameters like blood pressure, body temperature, respiration, and blood oxygen. The device can also operate in a fully-standalone mode to accomplish continuous multiparameter physiological monitoring, analysis, and reporting. Whenever the user touches an electrode on the device with a finger of the other hand, an ECG signal is additionally acquired for monitoring parameters such as heart rate and heart rate variability.

METHOD, APPARATUS, SYSTEM AND COMPUTER PROGRAM FOR PROCESSING AN ALMOST-PERIODIC INPUT SIGNAL

Examples relate to a method, an apparatus and a computer program for processing an almost-periodic input signal comprising a plurality of signal portions of varying duration, and to a system comprising such an apparatus and a visual output device. The plurality of signal portions are characterized by a common signal shape. The method comprises assigning the plurality of signal portions to a plurality of sets of signal portions. Each set of signal portions comprises two or more signal portions. The method comprises adjusting a duration of at least a subset of the signal portions such that the signal portions of a set have the same duration. The method comprises superimposing the two or more signal portions of a set within a combined output signal. 1. A method for processing an almost-periodic input signal comprising a plurality of signal portions of varying duration , the plurality of signal portions being characterized by a common signal shape , the method comprising:assigning the plurality of signal portions to a plurality of sets of signal portions, each set of signal portions comprising two or more signal portions;adjusting a duration of at least a subset of the signal portions such that the signal portions of a set have the same duration; andsuperimposing the two or more signal portions of a set within a combined output signal.2. The method according to claim 1 , wherein the signal portions of a set occur sequentially within the input signal.3. The method according to claim 1 , wherein the adjusted duration of the signal portions is the same for the plurality of signal portions.4. The method according to claim 1 , wherein the sets of signal portions comprise at least a first set and a second set claim 1 , the signal portions of the first set having an adjusted duration being different from an adjusted duration of the signal portions of the second set.5. The method according to claim 1 , wherein the adjusted duration of the signal portions of a set is based on an ...

Wearable monitor with arrhythmia burden evaluation

The present disclosure relates to a wearable monitor device and methods and systems for using such a device. In certain embodiments, the wearable monitor records cardiac data from a mammal and extracts particular features of interest. These features are then transmitted and used to provide health-related information about the mammal.

Systems and methods of identity analysis of electrocardiograms

Disclosed systems include an electrocardiogram sensor configured to sense electrocardiograms of a subject and a processing device operatively coupled to the electrocardiogram sensor. The processing device receives an electrocardiogram from the electrocardiogram sensor. The electrocardiogram is input into a machine learning model, the machine learning model to generate an output based on the received electrocardiogram. The processing device determines based on the electrocardiogram, that the output does not match an expected range of outputs for the target subject and generates an alert indicating a possible change in a status of the subject in response to the output not matching the expected range of outputs for the target subject.

Method and device for detecting respiration anomaly from low frequency component of electrical cardiac activity signals

A medical device and method are provided and include a sensing circuitry configured to obtain cardiac activity (CA) signals indicative of cardiac activity over one or more beats. The medical device includes a filter configured to separate, from the CA signals, a respiratory component that varies based on at least one of respiration rate or respiration depth. The medical device includes memory that is configured to store program instructions. The medical device includes a processor that, when executing the program instructions, is configured to analyze the respiratory component to identify a respiration characteristic of interest (COI). The respiration COI is based on at least one of variations in an amplitude of the respiratory component or an interval within the respiratory component and identifies a respiration anomaly based on the respiration COI.

Physiological monitoring system for a neonate and a neonatal blanket powering a wireless physiological sensor

A neonatal blanket includes a substrate material configured to cover a neonate and at least one antenna on the substrate material, where the antenna is configured to transmit RF energy to power the at least one wireless physiological sensor on the neonate. The blanket further includes a power connection configured to connect to a power source to power the wireless physiological sensor via the antennae.

Patient Signal Analysis Based on Vector Analysis

Disclosed herein is a framework for facilitating patient signal analysis based on vector analysis. In accordance with one aspect, a set of vectors is generated from a patient signal data waveform. The vectors may be directed from a common center to points of interest on the patient signal data waveform. The framework may further extract one or more vector parameters from the set of vectors, and determine one or more vector ratios based on the vector parameters to monitor changes in the patient signal data waveform.

System and method to detect stable arrhythmia heartbeat and to calculate and detect cardiac mapping annotations

A system and method for detecting a mapping annotation for an electrophysiological (EP) mapping system. The system includes a processor comprising a machine learning algorithm configured to receive a first heartbeat at an identified cardiac spatial location including a first set of attributes information corresponding to the first heartbeat; receive a second heartbeat at the identified cardiac spatial location including a second set of attributes information corresponding to the second heartbeat; compare the first set of attributes information with the second set of attributes information; and determine which of the first heartbeat and the second heartbeat has optimal characteristics based on the compared attribute information.

Method and apparatus for enhancement of chest compressions during cpr

An apparatus for assisting a rescuer in performing chest compressions during CPR on a victim, the apparatus comprising a pad or other structure configured to be applied to the chest near or at the location at which the rescuer applies force to produce the chest compressions, at least one sensor connected to the pad, the sensor being configured to sense movement of the chest or force applied to the chest, processing circuitry for processing the output of the sensor to determine whether the rescuer is substantially releasing the chest following chest compressions, and at least one prompting element connected to the processing circuitry for providing the rescuer with information as to whether the chest is being substantially released following chest compressions.

Medical system for remote monitoring, analysis and prognosis of the patient's condition by first-lead electrocardiogram series and computer-assisted method for monitoring, analysis and prognosis of the patient's condition

Medical system for remote monitoring, analysis and prognosis of patient's condition by series of at least first-lead electrocardiograms (ECGs), comprises: unit for gathering for each patient a series of ECGs; unit for extracting from the gathered database an ECG subset of a target group of patients, in accordance with at least one of identifiers according to examination purpose; unit for clustering the extracted ECG subset based on the feature of similarity of their forms; unit for determining an ECG form similarity measure in the space of ECG form features associates each ECG with a discretized ECG (DECG), which is a point having coordinates in at least one space of ECG form features; unit for generating STANDARDS for each cluster; unit for assessing variation in patient's condition over time by temporal variation in distances between each newly received DECGs in patient's DECG series and assigned at least one STANDARD.

Monitor and display screen switching method therefor

Monitors and display screen switching methods therefor are disclosed. An exemplary monitor includes a host and a first display communicatively connected to the host. An exemplary display screen switching method for the monitor includes detecting that a second display is connected, the second display being provided independently of the monitor. The display screen switching method further includes detecting that a display screen switching instruction is received and reading a corresponding display file according to configuration parameters of the second display, the display file comprising one or more physiological parameters to be displayed, an interface layout and interface elements. The display screen switching method also includes acquiring data of the one or more physiological parameters according to the display file and generating frame data, the frame data being used for representing pixel values of pixels on a display interface. The display screen switching method additionally includes outputting the frame data to the second display to display data of the one or more physiological parameters.

Detecting abnormalities in ecg signals

A method of detecting abnormalities in ECG signals by providing an ECG signal to a neural network, performing a first series of convolution operations to a first subset of layers and in a final layer, and determining a plurality of preliminary classification estimates, each preliminary classification estimate corresponding with a time segment of the ECG signal. Furthermore, determining input data for a second subset of layers of the neural network by concatenating the preliminary classification with the output of a layer of the first subset of layers that precedes the final layer of the first subset of layers. Within the second subset of layers of the neural network, performing a second series of convolution operations. In a final layer of the second subset, determining plurality of final classification estimates, each final classification estimate corresponding with a time segment of the ECG signal.

EKG based heart rate monitor

A heart rate monitor for calculating heart rate based upon EKG signals. The monitor preferably utilizes 3 electrodes to pick up EKG signals and a differential amplifier to cancel common mode signals in the output of the electrode. An analog bandpass filter comprised of a low pass and high pass filter in series each with different rolloffs filters out low and high frequency components. The signals are digitized and digital filtering to remove power line hum and remnants of low and high frequency noise is performed. Then the EKG signals are digitally enhanced by differentiating and squaring the results of the differentiator then being averaged in a moving average computation so as to generate enhanced digital data. The enhanced digital data is then processed to learn the EKG characteristics, and a heart rate arbitrator processes the incoming signals to select out actual EKG complexes from EMG noise and other noise. The EKG isolation process is done using rules of reason and the learned characteristics of the EKG signal.

MULTI SENSOR AND METHOD

A method including the steps of receiving a first signal sensed from a patient, receiving a first physiological signal sensed from the patient, and processing the first signal based at least on the first physiological signal to obtain a second signal that is a measurement of the patient's Heart Rhythm.

生物体信息分析装置、系统以及程序

本发明的生物体信息分析装置具有：指标提取部，从通过佩戴在睡眠中的用户的身体上并能够非侵入性地测量每一次心跳的血压波形的传感器连续地测量出的血压波形的数据，基于血压波形的特征，提取与所述用户的呼吸系统的功能相关的指标；以及处理部，进行基于提取出的所述指标的处理。

Anaesthesia and consciousness depth monotoring system

본 발명은 엔트로피 또는 생물체 피검자로부터의 연속 또는 유발 신호들을 모니터링하는 다른 복잡도 분석 등의 비선형 동적(NLD) 분석을 포함하는 방법 및 시스템으로 이루어지며, 여기서 이러한 시스템은 a) 생물체 피검자에 주어진 환자 자극의 결과로서 생물체의 신호 유발과, 신호 순서 또는 규칙성에서의 일시적 변화들을 잡아낼 수 있는 비선형 분석 방법의 결합; b) 유발 또는 연속 중추 신경 또는 말초 생리적 메커니즘들의 임의의 결합; c) 마취 및 의식 심도(A&CD), 진정 또는 수면/각성 상태의 환자의 레벨을 나타내는 측정치를 발생시키는 수단을 포함하는 처리 단계들로 이루어진다. 또한, 본 발명은 a) 중추 신경계(CNS), b) 말초 조절 또는 신경계(PNS), c) 자율 조절 또는 신경계(ANS), d) 각성들, 및 e) 인공물들의 임의의 결합을 포함하는 여러 가지 신호 기원들 사이에 구별을 향상시키기 위한 NLC 분석 수단을 포함하는 방법 및 시스템으로 이루어진다. The present invention consists of a method and system comprising non-linear dynamic (NLD) analysis, such as entropy or other complexity analysis to monitor continuous or induced signals from an organism subject, wherein the system comprises: a) A combination of signaling of the organism as a result and nonlinear analytical methods capable of capturing transient changes in signal sequence or regularity; b) any combination of induced or continuous central nervous or peripheral physiological mechanisms; c) anesthesia and consciousness depth (A & CD), means for generating a measure indicative of the level of the patient in a sedative or sleep / arousal state. The present invention also provides a method of treating a disorder or condition selected from the group consisting of a) central nervous system (CNS), b) peripheral or nervous system (PNS), c) autonomic regulation or nervous system (ANS) And methods of NLC analysis to improve discrimination between the different signal sources.

心电数据的分类方法及分类系统

本发明实施例提供一种心电数据的分类方法及分类系统，涉及医疗信息技术领域，可以提高处理心电数据的准确度和泛化能力。一种心电数据的处理方法，包括：将心电数据分割成多个心搏数据；对多个心搏数据进行卷积和池化，得到第一特征向量；获取第二特征向量，所述第二特征向量包括多个所述心搏数据的频域特征数据和时域特征数据；对所述第一特征向量和所述第二特征向量融合，生成融合特征向量；根据所述融合特征向量，得到所述心电数据的分类信息。

移动心脏健康监视

公开了用于移动心脏健康监视的技术。在一些实施例中，一种用于移动心脏健康监视的系统，包括包含处理器的移动设备，所述处理器被配置成从光学传感器接收第一数据集；从电学传感器接收第二数据集；并且使用来自光学传感器的第一数据集和来自电学传感器的第二数据集来执行多个心脏健康测量。

用于可植入心脏刺激系统的患者筛选工具

提供用于通过分析使用外部或皮肤电极捕获的心脏信号以确定患者是否非常适合于接受可植入心脏刺激设备的工具和设备。一些说明性的工具包括用于与打印的ECG带视觉比较的形状。还公开了电子地执行至少一些对于患者的分析功能的自动设备。在实例中，打印的ECG带与形状视觉比较以便确保患者非常适合接受具有特定的植入位置和/或心脏信号分析方法实施方案的心脏刺激设备。

무선 생리학적 모니터링 기기 및 시스템

본원의 개시내용은 심장 모니터링 시스템 및 그러한 시스템을 사용하는 방법에 관한 것이다. 바람직한 실시 예들은 착용 가능한 기기를 통해 심장 정보를 탐지 및 기록하고, 그 후에는 상기 기록된 심장 정보로부터 데이터 특징들을 추출한다. 그리고 나서, 상기 추출된 데이터 특징들은 분석되어 임상 진단에 사용될 수 있다.

生物体信息分析装置、生物体信息分析系统、程序以及生物体信息分析方法

生物体信息分析装置具有：指标提取部，使用通过佩戴在用户的身体上并能够非侵入性地测量每一次心跳的血压波形的传感器连续测量的血压波形的数据，提取与血压波形的特征相关的指标；以及处理部，进行基于提取出的所述指标的处理。

Apparatus and method for regenerating missing electrocardiogram signal

결측 심전도 신호 재생성 장치 및 방법이 개시되며, 본원의 일 실시예에 따른 결측 심전도 신호 재생성 방법은, (a) 복수의 심전도 신호 각각에 대하여, 상기 복수의 심전도 신호 중 어느 하나의 신호의 결측시 상기 어느 하나의 신호를 재생성하기 위한 복원 신호 조합을 상기 복수의 심전도 신호 중 상기 어느 하나의 신호를 제외한 나머지 심전도 신호로부터 선정하는 단계, (b) 상기 복원 신호 조합에 기초하여 상기 복수의 심전도 신호 각각을 재생성하는 인공지능 모델을 학습시키는 단계, (c) 대상자의 신체로부터 측정된 상기 복수의 심전도 신호를 획득하고, 상기 복수의 심전도 신호 중 결측 신호를 식별하는 단계 및 (d) 상기 인공지능 모델을 통해 상기 결측 신호에 대하여 선정된 상기 복원 신호 조합에 기초하여 상기 결측 신호를 재생성하는 단계를 포함할 수 있다.

Method and system for constructing emotion recognition model based on machine learning and physiological signals

本发明涉及一种基于机器学习和生理信号的情绪识别模型构建方法及系统。该方法包括：获取样本人群的多种生理数据，并构建第一样本数据集，而后提取各生理信号特征，预处理后得到第二样本数据集，并按预设比例分为训练集和验证集；选取分类机器学习模型为每种生理信号构造一级模型，将训练集作为输入进行训练，得到若干情绪识别模型；对每个情绪识别模型进行准确性分析，并计算不同模型之间的相关性，以及样本数据的稳定性，由此得到该情绪识别模型的融合权重；基于融合权重，结合所有情绪识别模型，构建综合预测模型。本发明有效提升了模型精度和泛化能力，能通过生理信号快速预测待测者的情绪状态，避免待测者主观因素对情绪判别的影响。

Method and apparatus for determining arrhythmia, and recording media recorded program realizing the same

부정맥 판단 방법 및 장치, 그리고 이를 구현하기 위한 프로그램이 기록된 기록매체가 제공된다. 본 발명의 일 실시예에 따른 부정맥 판단 방법은, 응용 프로그램의 어플리케이션 모델 및 운영체제 모델을 통합하여 실행 시나리오 모델을 생성하는 단계; 상기 실행 시나리오 모델에서 태스크 실행 순서 및 문장 블록을 도출하는 단계; 상기 응용 프로그램의 실행에 따른 문맥 전환 위치를 주석첨가(annotate)하는 단계; 상기 태스크 실행 순서 및 문장 블록과, 상기 문맥 전환 위치를 기초로 상기 응용 프로그램의 실행 가능한 경로를 검증하는 단계; 및 상기 응용 프로그램의 실행 가능성을 확인하여 보고하는 단계를 포함한다.

Control system and user interface for an ablation system

Electrosurgical generators having improved functionality and user interface. In an example, the user may modify therapy output parameters without interrupting therapy delivery within a therapy regimen. In an example, the display shows both therapy amplitudes and encountered impedances for a plurality of therapy pulses in different portions of a display. In an example, the electrosurgical generator is operable in a triggered mode using a cardiac signal trigger and provides the operator with an estimate of remaining time that is calculated in light of a calculated cardiac rate.

Biont information analytical equipment, system and program

生物体信息分析装置具有：指标提取部，根据通过佩戴在用户的身体上并能够非侵入性地测量每一次心跳的血压波形的传感器连续测量的血压波形的时间序列数据和在与所述血压波形的时间序列数据相对应的期间通过呼吸传感器测量的呼吸的时间序列数据，提取表示所述用户的呼吸和血压变动的关系的指标；以及处理部，用于进行基于提取出的所述指标的处理。

device and method for providing digital therapeutics information

본 발명은 디지털 컨텐츠 기반 치료 정보 제공 장치 및 방법에 관한 것이다. 본 발명의 일 양상인 디지털 컨텐츠 기반 치료 정보 제공 방법은, 사용자에 대한 뇌 자극을 수행하여, 상기 사용자의 fNIRS(functional near-infrared spectroscopy) 데이터를 획득하는 제 1 단계; 상기 획득된 fNIRS 데이터를 이용하여 상기 사용자의 뇌의 복수의 영역 중 활성화된 제 1 뇌 활성화 영역을 추출하는 제 2 단계; 상기 제 1 뇌 활성화 영역을 기초로, 상기 사용자의 제 1 뇌 상태를 판단하는 제 3 단계; XR(Extended Reality) 환경에서, 상기 판단된 제 1 뇌 상태에 대응하여 결정된 컨텐츠를 상기 사용자에 제공하는 제 4 단계; 상기 컨텐츠에 대응하여 상기 사용자가 미션을 수행하는 제 5 단계; 상기 미션을 수행한 사용자의 fNIRS 데이터를 기준으로, 상기 복수의 영역 중 활성화된 제 2 뇌 활성화 영역을 추출하는 제 6 단계; 상기 제 2 뇌 활성화 영역을 기초로, 상기 사용자의 제 2 뇌 상태를 판단하는 제 7 단계; 및 상기 제 1 뇌 상태 정보 및 상기 제 2 뇌 상태 정보를 이용하여 상기 사용자의 뇌 상태 개선과 관련된 정보를 결정하는 제 8 단계;를 포함할 수 있다. The present invention relates to an apparatus and method for providing treatment information based on digital content. According to an aspect of the present invention, a method for providing treatment information based on digital content includes: a first step of performing brain stimulation for a user to obtain functional near-infrared spectroscopy (fNIRS) data of the user; a second step of extracting an activated first brain activation region from among a plurality of regions of the user's brain using the acquired fNIRS data; a third step of determining a first brain state of the user based on the first brain activation region; a fourth step of providing content determined in response to the determined first brain state to the user in an extended reality (XR) environment; a fifth step of performing a mission by the user in response to the content; a sixth step of extracting an activated second brain activation region from among the plurality of regions based on the fNIRS data of the user who has performed the mission; a seventh step of determining a second brain state of the user based on the second brain activation region; and an eighth step of determining information related to improvement of the user's brain state by using the first brain state information and the second brain state information.

Method for predicting chronic disease based on ecg signal

According to one embodiment of the present invention, disclosed is a method for predicting a chronic disease based on an ECG signal performed by a computing device. The method may comprise: a step of generating gradient information and section information by waveform of the ECG signal from ECG data; a step of generating integrated data by lead based on at least one piece among the ECG data, gradient information, or section information by waveform; and a step of generating N-dimensional input data based on the integrated data by lead.

Apparatus and method for generating photoplethysmography wave data from electrocardiogram data

본 발명의 실시예는 광용적맥파 데이터 생성 장치 및 방법에 관한 것으로서, ECG 데이터로부터 실제 PPG 데이터와 유사한 PPG 데이터를 생성하는 생성 모듈 및 생성된 PPG 데이터와 실제 PPG 데이터를 구분하는 판별 모듈을 경쟁적으로 학습시켜, ECG 데이터로부터 실제와 유사한 PPG 데이터를 획득하는 광용적맥파 데이터 생성 장치 및 방법에 관한 것이다. An embodiment of the present invention relates to an apparatus and method for generating PPG data, and a generating module for generating PPG data similar to actual PPG data from ECG data and a discrimination module for discriminating the generated PPG data from actual PPG data are competitively provided. The present invention relates to an apparatus and method for generating PPG data similar to reality by learning the PPG data from ECG data.

Medical data providing method and recording medium storing the Medical data providing method

본 개시의 실시예들에 따르면, 의료 데이터 제공 장치가, 심전도 신호를 수신하는 단계; 상기 의료 데이터 제공 장치가, 상기 심전도 신호를 복수의 세그먼트들로 분할하는 단계; 복수의 세그먼트들 중에서, 제1 세그먼트를 분석하여, 제1 세그먼트의 피크 값의 크기(magnitude)를 기 설정된 임계값(threshold)과 비교하여 정상 구간인지 여부를 판단하는 단계; 상기 의료 데이터 제공 장치가, 상기 제1 세그먼트가 정상 구간인 경우, 상기 제1 세그먼트를 정상 구간으로 분류하고, 상기 의료 데이터 제공 장치가, 상기 제1 세그먼트가 정상 구간이 아닌 경우, 상기 제1 세그먼트의 형태학적 패턴을 추출하고, 상기 형태학적 패턴을 이용하여 상기 제1 세그먼트를 정상 구간이 아닌 것으로 분류하는 단계; 상기 의료 데이터 제공 장치가, 복수의 세그먼트들에 대해서, 정상 구간의 세그먼트들을 분석하는 단계;를 포함하는, 의료 데이터 제공 방법을 개시한다. According to embodiments of the present disclosure, the medical data providing apparatus may include receiving an electrocardiogram signal; Dividing, by the medical data providing device, the electrocardiogram signal into a plurality of segments; analyzing a first segment among a plurality of segments and comparing a magnitude of a peak value of the first segment with a preset threshold to determine whether the segment is a normal segment; If the first segment is a normal section, the medical data providing device classifies the first segment as a normal section, and if the first segment is not a normal section, the medical data providing device classifies the first segment as a normal section. extracting a morphological pattern of and classifying the first segment as a non-normal section using the morphological pattern; Disclosed is a medical data providing method including analyzing, by the medical data providing apparatus, segments of a normal section for a plurality of segments.

Artificial intelligence based device and method for providing brain information

【課題】使用者が活動する状態で、脳に関する信号を収集し、脳状態を判断してフィードバックすることができる人工知能に基づく脳情報提供方法を提供する。【解決手段】脳信号測定部１０の脳信号取得部が、使用者の脳に近赤外線を照射し、大脳皮質を透過した光を検出する第１のステップと、脳信号測定部の脳信号処理部が、検出された光を基に、脳血流内のヘモグロビン酸素化程度を判断する第２のステップと、脳信号分析部が、判断されたヘモグロビン酸素化程度を基に、脳の複数の領域のうち、活性化された少なくとも１つの脳活性化領域を抽出する第３のステップと、診断部５０が一定期間の間、連続して抽出された少なくとも１つの脳活性化領域を基に、脳状態を判断する第４のステップとを含み、第１のステップの脳信号取得部の信号収集動作は、使用者が動く状態で行われる。【選択図】図１

Biological signal monitoring apparatus

피험자의 정신적 건강 상태들 및 생리적 건강 상태들을 동시에 판정하는 방법으로서: 적어도 하나의 생체 신호들을 모니터링하는 단계 - 여기서, 상기 생체 신호들은, 의식 상태를 나타내는, 지속적인 EEG 생체 신호들 또는 청각 자극들에 의해 생성되는 유발 EEG 생체 신호들; 상기 의식 상태를 나타내는, 산소 포화도(SA02) 및 반사형 혈량 측정 파형 신호들, 호흡 전파 시간 및 맥박 전파 시간, ECG, 혈류 변화들 및 혈압 변화들, 맥파 동맥 파형 변화들 또는 맥파 동맥 긴장 변화들, 심박수 및 심박수 변동성 중 적어도 하나를 포함하는 또다른 생체 신호들; 근전도(EMG) 생체 신호들; 및 심전도(ECG) 생체 신호들을 포함함 -; 상기 피험자의 활력 징후들을 측정하는 단계; 상기 측정된 생체 신호들의 특성에 근거하여, 수면 상태, 정신 상태, 또는 지각 상태 중에서 상기 피험자의 상기 의식 상태를 판정하는 단계; 상기 판정된 의식 상태 그리고 상기 측정된 활력 징후들과 상기 활력징후들의 알려진 정상 범위와의 비교 결과에 근거하여, 상기 피험자의 상기 정신적 건강 상태들 또는 생리적 건강 상태들을 판정하는 단계; 및 상기 피험자의 상기 정신적 건강 상태들 또는 생리적 건강 상태들 그리고 상기 측정된 활력 징후들에 근거하여, 상기 피험자의 생리적 또는 정신적 건강 위험 예측을 판정하는 단계를 포함한다.

Biont information analytical equipment, system and program

本发明的生物体信息分析装置具有：指标提取部，根据由佩戴在用户的身体上并能够非侵入性地测量每一次心跳的血压波形的传感器连续地测量出的血压波形的数据，提取表示心脏状态的指标，以及处理部，输出由所述指标提取部所提取出的所述指标；所述指标提取部根据所测量出的血压波形数来提取每一次心跳的心脏负荷指标，并基于与多次心跳的所述心脏负荷指标的分布相关的特征，来求出用于表示心脏状态的指标。

Wearable monitor with arrhythmia burden evaluation

The present disclosure relates to a wearable monitor device and methods and systems for using such a device. In certain embodiments, the wearable monitor records cardiac data from a mammal and extracts particular features of interest. These features are then transmitted and used to provide health-related information about the mammal.

Wearable monitor

The present disclosure relates to a wearable monitor device and methods and systems for using such a device. In certain embodiments, the wearable monitor records cardiac data from a mammal and extracts particular features of interest. These features are then transmitted and used to provide health-related information about the mammal.

Simultaneous monitoring of ecg & bioimpedance via shared electrodes

A system for acquiring electrocardiograph (ECG) and bioimpedance (BI) data is disclosed. The system (an ECG/BI measurement system) can use as few as one or two pairs of electrodes, permitting wearable devices employing the ECG/BI measurement system to be made into smaller, more comfortable, and more inconspicuous formats, as well as decreasing potential failure points in the measurement of electrical signals conducted between the system and the user. The system can measure both ECG and BI data using at least one shared pair of electrodes. In some cases, ECG and BI data are separately extracted from a measured signal across a shared pair of electrodes, while another pair of electrodes is being driven with a supply current. In other cases, internal switching can automatically switch a pair of electrodes between ECG-measuring circuitry and BI-measuring circuitry, such as based on a clock signal or other trigger.

Apparatus and method for monitoring or analyzing consciousness state of subject

본 발명은 생물학적 대상자의 통증, 진정, 마취, 의식, 주의, 인지 기능, 인지 인식 또는 인지 기억 유지의 수준을 결정하기 위해, 상기 생물학적 대상자의 생리적 데이터를 획득하기 위한 장치에 관한 것이다. 상기 장치는: 상기 생물학적 대상자의 적어도 하나의 반응 신호를 유발하기 위한 자극을 생성하기 위한 수단; 및 상기 자극을 생성하기 위한 수단으로부터 얻어진 유발 반응 신호로부터 적어도 2개의 파라미터들을 도출하기 위한 수단을 포함한다. 여기서, 상기 유발 반응 신호로부터의 상기 파라미터들은 상기 생물학적 대상자의 생리적 또는 심리적 메커니즘들 중 적어도 하나를 나타낸다. The present invention relates to a device for acquiring physiological data of a biological subject for determining the level of pain, sedation, anesthesia, consciousness, attention, cognitive function, cognitive cognition or cognitive memory maintenance of said biological subject. The apparatus comprises: means for generating a stimulus to elicit at least one response signal in the biological subject; and means for deriving at least two parameters from a evoked response signal obtained from the means for generating the stimulus. Here, the parameters from the evoked response signal represent at least one of physiological or psychological mechanisms of the biological subject.

Method for providing worker safty analysis service in construction site and server and system for performing the same

본 발명은, 안전도 분석 서비스 제공 서버에 관한 것으로서, 상기 서버는, 저장부, 통신부, 상기 저장부, 상기 통신부와 동작 가능하게 연결된 프로세서를 포함하되, 상기 프로세서는, 건설 현장에 배치된 복수의 작업자 각각의 담당 공종에 따른 안전 사고 유형을 매칭하고, 상기 복수의 작업자 각각에 대한 생체 데이터 및 상태 데이터를 획득하고, 작업자의 생체 데이터와 상태 데이터를 입력으로 하여 안전 사고 유형 별 작업자의 안전도를 예측하도록 학습된 안전도 분석 모델에 상기 복수의 작업자 각각의 생체 데이터와 상기 상태 데이터를 입력하여 안전 사고 유형 별로 상기 복수의 작업자 각각의 안전도를 출력하고, 상기 복수의 작업자 중 안전도가 기준 값 이상인 작업자에게 알람을 제공하도록 구성된다. 본 발명에 따르면, 건설 현장에서 발생한 사고와 작업자의 생체 변화, 얼굴 표정 변화, 행동 변화를 매칭시켜 학습하고, 그에 따른 안전도 분석 모델을 구축함으로써, 현재 건설 현장 작업 진행도에 따른 안전 사고의 유형 별로 작업자의 안전도를 예측 및 예방할 수 있다. The present invention relates to a safety analysis service providing server, wherein the server includes a storage unit, a communication unit, a storage unit, and a processor operatively connected to the communication unit, wherein the processor includes a plurality of Match the safety accident type according to the type of work in charge of each worker, obtain biometric data and status data for each of the plurality of workers, and predict the safety level of workers by safety accident type by inputting the worker's biometric data and status data as input By inputting the biometric data and the state data of each of the plurality of workers to the safety analysis model learned to do so, the safety level of each of the plurality of workers is output for each type of safety accident, and the safety level of the plurality of workers is greater than or equal to the reference value. configured to provide an alarm. According to the present invention, the type of safety accident according to the current construction site work progress by matching the accident occurring at the construction site and the worker's biometric change, facial expression change, and behavior change, and building a safety analysis model accordingly. Each worker's safety level can be predicted and prevented.

Face supporting mask and head mounted display apparatus comprising the same

본 발명의 실시예에 따른 안면 지지 마스크는 헤드 마운트 디스플레이 장치에 탈부착 가능한 마스크 본체; 및 마스크 본체에 설치되고, 사용자의 착용 시 사용자의 피부에 접촉되어 생체신호를 감지하는 생체신호 감지부;를 포함 한다. 본 발명의 실시예에 따르면, 마스크 본체에 사용자의 피부에 접촉되어 하나 이상의 생체신호를 측정 가능한 생체신호 감지부를 설치함으로써, 가상현실 영상을 확인 중인 사용자의 다양한 신체적 변화를 측정 가능하고, 이를 활용하여 다양한 체험요소를 포함하는 콘텐츠를 개발 가능하여 제품의 확장성을 증대시키고, 사용자의 체험 만족도를 향상시킬 수 있다. A face support mask according to an embodiment of the present invention includes a mask body detachable to a head mounted display device; And a biosignal detection unit installed on the mask body and contacting the user's skin when the user wears it to sense a biosignal. According to an embodiment of the present invention, by installing a bio-signal detector capable of measuring one or more bio-signals in contact with the user's skin on the mask body, it is possible to measure various physical changes of a user who is checking a virtual reality image. Contents including various experience elements can be developed, thereby increasing product scalability and enhancing user experience satisfaction.

Biological information analysis device, system, program, and biological information analysis method

生物体信息分析装置具有：指标提取部，将通过佩戴在用户的身体上并能够非侵入性地测量每一次心跳的血压波形的传感器连续测量的血压波形的时间序列数据转换为频谱，并提取基于所述频谱中的规定的频率分量的强度的指标；以及处理部，进行基于提取出的所述指标的处理。

Improving the analysis of physiological electrograms

РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2017 107 224 A (51) МПК A61B 5/04 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ЗАЯВКА НА ИЗОБРЕТЕНИЕ (21)(22) Заявка: 2017107224, 29.07.2015 (71) Заявитель(и): ФЕН ИП ЛИМИТЕД (GB) Приоритет(ы): (30) Конвенционный приоритет: (72) Автор(ы): СУМАРЕС Ричард С. (GB) 13.08.2014 GB 1414330.9 26 (85) Дата начала рассмотрения заявки PCT на национальной фазе: 13.03.2017 GB 2015/052190 (29.07.2015) (87) Публикация заявки PCT: WO 2016/024081 (18.02.2016) A Адрес для переписки: 191036, Санкт-Петербург, а/я 24, "НЕВИНПАТ" R U (57) Формула изобретения 1. Способ анализа электрограммы для различения физиологического сигнала и шума, включающий получение модели шума из первой части электрограммы, в которой предполагают отсутствие физиологического сигнала; преобразование второй части электрограммы, в которой предполагают наличие физиологического сигнала, в указанную модель шума, и при этом физиологический сигнал идентифицируют путем идентификации частей второй части электрограммы, которые не соответствуют модели шума. 2. Способ по п. 1, отличающийся тем, что модель шума получают из нескольких частей электрограммы, в которых предполагают отсутствие физиологического сигнала. 3. Способ по п. 1 или 2, отличающийся тем, что модель шума получают путем взаимной корреляции первой части электрограммы, в которой предполагают отсутствие физиологического сигнала, с несколькими шаблонами, которые представляют признаки предполагаемого физиологического сигнала, с получением ряда коррелированных шаблонами сигналов. 3. Способ по п. 2, отличающийся тем, что включает получение матрицы ковариации из коррелированных шаблонами сигналов для каждой части электрограммы, в которой предполагают отсутствие физиологического сигнала. 4. Способ по п. 3, отличающийся тем, что включает получение средней матрицы Стр.: 1 A 2 0 1 7 1 0 7 2 2 4 (54) Усовершенствование анализа физиологических электрограмм 2 0 1 7 1 0 7 2 2 4 (86) Заявка PCT: R U (43) Дата ...

Vital sign data statistical system and monitor

一种监护仪及生命体征数据统计系统，具有生命体征数据的统计功能。该监护仪(100)包括信号采集模块(120)、数据处理模块(110)和显示模块(130)。数据处理模块(110)对信号采集模块(120)采集的生命体征信号进行处理，生成生理参数。当接收到请求显示生命体征数据统计结果的请求信息时，数据处理模块(110)对预设时间范围内的生命体征数据根据设定的类别和各类别的统计项进行分类统计，并通过显示模块(130)进行显示。本监护仪既能辅助医生快速了解了患者较长时间的总体情况，又节约了医生的时间和精力。

User interfaces for health applications

The present disclosure generally relates to user interfaces for health applications. In some embodiments, exemplary user interfaces for managing health and safety features on an electronic device are described. In some embodiments, exemplary user interfaces for managing the setup of a health feature on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described. In some embodiments, exemplary user interfaces for managing a biometric measurement taken using an electronic device are described. In some embodiments, exemplary user interfaces for providing results for captured health information on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described.

User interfaces for health applications

The present disclosure generally relates to user interfaces for health applications. In some embodiments, exemplary user interfaces for managing health and safety features on an electronic device are described. In some embodiments, exemplary user interfaces for managing the setup of a health feature on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described. In some embodiments, exemplary user interfaces for managing a biometric measurement taken using an electronic device are described. In some embodiments, exemplary user interfaces for providing results for captured health information on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described.

User interfaces for health applications

The present disclosure generally relates to user interfaces for health applications. In some embodiments, exemplary user interfaces for managing health and safety features on an electronic device are described. In some embodiments, exemplary user interfaces for managing the setup of a health feature on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described. In some embodiments, exemplary user interfaces for managing a biometric measurement taken using an electronic device are described. In some embodiments, exemplary user interfaces for providing results for captured health information on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described.

Artificial intelligence-based bio-signal remote monitoring system

The present invention relates to an artificial intelligence-based bio-signal remote monitoring system, which enables real-time monitoring of received multiple bio-signals, requests reading to deep learning artificial intelligence through a heart disease analysis server and a prognosis analysis server to analyze the heart disease or prognosis, sends an alarm message to a monitor system of a hospital and mobile terminals of medical staff and patients when a preset alarm threshold is exceeded, and remotely sets the type or measurement period of the bio-signal of multiple bio-signal measuring devices manually or automatically depending on the severity or prognosis of the patient.

Method and apparatus for predicting user state

본 발명의 실시예에 따른 사용자 상태를 예측하기 위한 방법 및 그 장치가 제공된다. 본 발명의 실시예에 따른 사용자 상태 예측 방법은, 복수의 사용자들에 대한 제1 생체 데이터를 획득하는 단계; 상기 획득된 제1 생체 데이터 및 고정된 학습 파라미터를 기초로 예측 모델을 파인 튜닝(Fine Tuning)하는 단계; 및 적어도 하나의 사용자에 대한 사용자 상태를 예측하기 위한 제2 생체 데이터를 입력으로, 상기 파인 튜닝된 예측 모델을 이용하여 예측된 사용자 상태를 출력하는 단계를 포함하고, 상기 고정된 학습 파라미터는, 상기 예측 모델과 상이하며, 상기 복수의 사용자들에 대한 제1 생체 데이터를 입력으로 상기 복수의 사용자들에 대한 사용자 상태를 예측하도록 학습된 제1 모델에 기반하여 추출된다. A method and an apparatus for predicting a user state according to an embodiment of the present invention are provided. A user state prediction method according to an embodiment of the present invention includes: acquiring first biometric data for a plurality of users; Fine tuning a predictive model based on the obtained first biometric data and a fixed learning parameter; and outputting a user state predicted by using the fine-tuned prediction model by inputting second biometric data for predicting a user state for at least one user, wherein the fixed learning parameter includes: It is different from the prediction model, and is extracted based on the first model learned to predict the user state of the plurality of users by inputting the first biometric data for the plurality of users.