Method and system for screening and monitoring of cardiac diseases

Patent metadata

Field	Value
Publication number	US-2021000356-A1
Application number	US-202016946718-A
Country	US
Kind code	A1
Filing date	Jul 1, 2020
Priority date	Jul 2, 2019
Publication date	Jan 7, 2021
Grant date	—

Abstract

Embodiments herein provide a system and method for screening and monitoring of cardiac diseases by analyzing acquired physiological signals. Unlike state of art approaches that consider only synchronized ECG and PPG signals for cardiac health analysis and do not consider PCG which is a critical signal for CAD analysis, the system synchronously captures physiological signals such as photo plethysmograph (PPG), phonocardiogram (PCG) and electrocardiogram (ECG) from subject(s) and builds an analytical model in the cloud for analyzing heart conditions from the captured physiological signals. The system and method provides a fusion based approach of combining the captured physiological signals such as PPG, PCG and ECG along with other details such as subject clinical information, demography information and so on. The analytical model is pretrained using ECG. PPG and PCG along with metadata associated with the subject such as demography and clinical information.

First claim

What is claimed is:

1 . A processor implemented method for screening and monitoring cardiac diseases by analyzing acquired physiological signals, the method comprising:
displaying a User Interface (UI), by one or more hardware processors of a heart sense device, for enabling entering of metadata comprising demography and clinical information associated with a subject among a plurality of subjects screened and monitored via an authenticated access to the heart sense device, wherein a plurality of probes of the heart sense device are non-invasively attached to the subject; synchronously acquiring, by the one or more hardware processors via the plurality of probes, a plurality of physiological signals comprising an ECG, a PPG, and a PCG of the subject, wherein synchronously acquiring the plurality of physiological signals comprises: a) acquiring each of the plurality of physiological signals as a plurality of segments of data; b) converting the plurality of segments of data corresponding to the physiological signals into a plurality of digital segments using an Analog to Digital Converter (ADC); c) associating each of the plurality of digital segments with time stamps; d) pre-processing each of the plurality of digital segments with the time stamps to discard noisy segments and identify a plurality of clean segments; e) identifying a set of synchronous segments from the plurality of clean segments, based on mapping time stamps, wherein each of the set of synchronous segments corresponds to each of the plurality of physiological signals, and wherein the set of synchronous segments are captured over a configurable predetermined time interval; and f) displaying the set of synchronous segments on the UI; and transmitting, by the one or more hardware processors, the set of synchronous segments and the metadata of the subject to a cloud server via an application on a mobile device, wherein the application on the mobile device communicates with the heart sense device over a short range communication interface and enables editing of metadata and preliminary analysis on the set of synchronous segments via an authenticated access mechanism.

2 . The method of claim 1 , wherein the method comprises analyzing using an analytical model in the cloud server, the set of synchronous segments and the metadata of each of the plurality of subjects and predicting a cardiac disease among a plurality of cardiac diseases, wherein the analytical model is a pretrained Machine Learning (ML) model.

3 . The method of claim 2 , wherein the method comprises displaying the predicted cardiac disease on the mobile device.

4 . The method of claim 1 , wherein the heart sense device is a portable battery operated device.

5 . A system for screening and monitoring cardiac diseases by analyzing acquired physiological signals, the system comprising:
a heart sensing device, a mobile device, and a cloud server, wherein: the heart sensing device comprises a memory storing instructions; one or more Input/Output (I/O) interfaces; and one or more hardware processors coupled to the memory via the one or more I/O interfaces, wherein the one or more hardware processors are configured by the instructions to:
display a User Interface (UI) for enabling entering of metadata comprising demography and clinical information associated with a subject among a plurality of subjects screened and monitored via an authenticated access to the heart sense device, wherein a plurality of probes of the heart sense device are non-invasively attached to the subject;
synchronously acquire via the plurality of probes, a plurality of physiological signals comprising an ECG, a PPG, and a PCG of the subject, wherein synchronously acquiring the plurality of physiological signals comprises:
a) acquiring each of the plurality of physiological signals as a plurality of segments of data;
b) converting the plurality of segments of data corresponding to the physiological signals into a plurality of digital segments using an Analog to Digital Converter (ADC);
c) associating each of the plurality of digital segments with time stamps;
d) pre-processing each of the plurality of digital segments associated with the time stamps to discard noisy segments and identify a plurality of clean segments;
e) identifying a set of synchronous segments from the plurality of clean segments based on mapping time stamps, wherein each of the set of synchronous segments corresponds to each of the plurality of physiological signals, and wherein the set of synchronous segments are captured over a configurable predetermined time interval; and
f) displaying the set of synchronous segments on the UI; and
transmit the set of synchronous segments and the metadata of the subject to a cloud server via an application on a mobile device, wherein the application on the mobile device communicates with the heart sense device over a short range communication interface and enables editing of metadata and preliminary analysis on the set of synchronous segments via an authenticated access mechanism.

6 . The system of claim 5 , wherein the cloud server is configured to analyze, using an analytical model, the set of synchronous segments and the metadata of each of the plurality of subjects and predicting a cardiac disease among a plurality of cardiac diseases, wherein the analytical model is a pretrained Machine Learning (ML) model.

7 . The system of claim 6 , wherein the cloud server is configured to communicate the predicted cardiac disease to the mobile device, and wherein the mobile device is configured to display the predicted cardiac disease on the mobile device.

8 . The system of claim 5 , wherein the heart sensing device is a portable battery operated device.

9 . One or more non-transitory machine-readable information storage mediums comprising one or more instructions, which when executed by one or more hardware processors causes a method for screening and monitoring cardiac diseases by analyzing acquired physiological signals, the method comprising:
displaying a User Interface (UI) for enabling entering of metadata comprising demography and clinical information associated with a subject among a plurality of subjects screened and monitored via an authenticated access to the heart sense device, wherein a plurality of probes of the heart sense device are non-invasively attached to the subject; synchronously acquiring via the plurality of probes, a plurality of physiological signals comprising an ECG, a PPG, and a PCG of the subject, wherein synchronously acquiring the plurality of physiological signals comprises: a) acquiring each of the plurality of physiological signals as a plurality of segments of data; b) converting the plurality of segments of data corresponding to the physiological signals into a plurality of digital segments using an Analog to Digital Converter (ADC); c) associating each of the plurality of digital segments with time stamps; d) pre-processing each of the plurality of digital segments with the time stamps to discard noisy segments and identify a plurality of clean segments; e) identifying a set of synchronous segments from the plurality of clean segments, based on mapping time stamps, wherein each of the set of synchronous segments corresponds to each of the plurality of physiological signals, and wherein the set of synchronous segments are captured over a configurable predetermined time interval; and f) displaying the set of synchronous segments on the UI; and transmitting the set of synchronous segments and the metadata of the subject to a cloud server via an application on a mobile device, wherein the application on the mobile device communicates with the heart sense device over a sh

Assignees

• Tata Consultancy Services Ltd

Inventors

• Kimbahune Sanjay Madhukar
• Shinde Sujit Raghunath
• Pal Arpan
• Khandelwal Sundeep
• Bhattacharjee Tanuka
• Mukhopadhayay Shalini
• Banerjee Rohan
• Ghose Avik
• Chakravarty Tapas

Classifications

• A61B2505/07

  Home care · CPC title

• A61B5/7221

  Determining signal validity, reliability or quality (preventing, reducing or removing noise induced by motion artefacts A61B5/7207; noise originating from a therapeutic or surgical apparatus A61B5/7217) · CPC title

• A61B5/02416 Primary

  using photoplethysmograph signals, e.g. generated by infrared radiation (A61B5/14552 takes precedence) · CPC title

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• A61B5/7275

  Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor · CPC title