Design and Implementation of an Ultra-Low-Power ECG Patch and Smart Cloud-Based Platform

<p>This paper reports a new device for electrocardiogram (ECG) signal monitoring and software for signal analysis and artificial intelligence (AI) assisted diagnosis. </p> <p>The hardware mitigates the signal loss common in previous products by enhancing the ergonomy, flexibility, and battery life. The power efficiency is optimized by design using switching converters, ultra-low-power components, and efficient signal processing. It enables 14-day of uninterrupted ECG monitoring and connectivity with a smartphone and microSD card storage.</p><p>The software is implemented in Android app and web-based platforms via Internet of Things (IoT). This component provides cloud-based and local storage and uses AI for arrhythmia detection. The arrhythmia detection algorithm shows 98.7% accuracy using Artificial Neural Network and K-Nearest Neighbors methods, and 98.1% using Decision Tree method on test data set.</p>

Commercially-available heart rate monitor repurposed into a 9-gram standalone device for automatic arrhythmia detection with snapshot electrocardiographic capability: a pilot validation.

Background: The usefulness of opportunistic arrhythmia screening strategies, using an electrocardiogram (ECG) or other methods for random snapshot assessments is limited by the unexpected and occasional nature of arrhythmias, leading to a high rate of missed-diagnosis. We have previously validated a cardiac monitoring system for AF detection pairing simple consumer-grade Bluetooth low-energy (BLE) heart rate (HR) sensors with a smartphone application (RITMIA, Heart Sentinel srl, Italy). In the current study we test a significant upgrade to the abovementioned system, thanks to the technical capability of new HR sensors to run algorithms on the sensor itself and to acquire (and store on-board) single-lead ECG strips, if asked to do so. Methods and Results We have reprogrammed a HR monitor intended for sports use (Movensense HR+) to run our proprietary RITMIA algorithm code in real-time, based on RR analysis, so that if any type of arrhythmia is detected it triggers a brief retrospective recording of a single-lead ECG, providing tracings of the specific arrhythmia for later consultation. We report the initial data on the behavior, feasibility and high diagnostic accuracy of this ultra-low weight customized device for standalone automatic arrhythmia detection and ECG recording, when several types of arrhythmias were simulated, under different baseline conditions. Conclusions This customized device was capable to detect all types of simulated arrhythmias and correctly triggered an visually interpretable ECG tracing. Future human studies are needed to address real-life accuracy of this device.

Design and Implementation of an Ultra-Low-Power ECG Patch and Smart Cloud-Based Platform

<p>This paper reports a new device for electrocardiogram (ECG) signal monitoring and software for signal analysis and artificial intelligence (AI) assisted diagnosis. </p> <p>The hardware mitigates the signal loss common in previous products by enhancing the ergonomy, flexibility, and battery life. The power efficiency is optimized by design using switching converters, ultra-low-power components, and efficient signal processing. It enables 14-day of uninterrupted ECG monitoring and connectivity with a smartphone and microSD card storage.</p><p>The software is implemented in Android app and web-based platforms via Internet of Things (IoT). This component provides cloud-based and local storage and uses AI for arrhythmia detection. The arrhythmia detection algorithm shows 98.7% accuracy using Artificial Neural Network and K-Nearest Neighbors methods, and 98.1% using Decision Tree method on test data set.</p>

MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection

In this work, a memristive spike-based computing in memory (CIM) system with adaptive neuron (MSPAN) is proposed to realize energy-efficient remote arrhythmia detection with high accuracy in edge devices by software and hardware co-design. A multi-layer deep integrative spiking neural network (DiSNN) is first designed with an accuracy of 93.6% in 4-class ECG classification tasks. Then a memristor-based CIM architecture and the corresponding mapping method are proposed to deploy the DiSNN. By evaluation, the overall system achieves an accuracy of over 92.25% on the MIT-BIH dataset while the area is 3.438 mm2 and the power consumption is 0.178 μJ per heartbeat at a clock frequency of 500 MHz. These results reveal that the proposed MSPAN system is promising for arrhythmia detection in edge devices.

Remote Arrhythmia Detection for Eldercare in Malaysia

Cardiovascular disease continues to be one of the most prevalent medical conditions in modern society, especially among elderly citizens. As the leading cause of deaths worldwide, further improvements to the early detection and prevention of these cardiovascular diseases is of the utmost importance for reducing the death toll. In particular, the remote and continuous monitoring of vital signs such as electrocardiograms are critical for improving the detection rates and speed of abnormalities while improving accessibility for elderly individuals. In this paper, we consider the design and deployment characteristics of a remote patient monitoring system for arrhythmia detection in elderly individuals. Thus, we developed a scalable system architecture to support remote streaming of ECG signals at near real-time. Additionally, a two-phase classification scheme is proposed to improve the performance of existing ECG classification algorithms. A prototype of the system was deployed at the Sarawak General Hospital, remotely collecting data from 27 unique patients. Evaluations indicate that the two-phase classification scheme improves algorithm performance when applied to the MIT-BIH Arrhythmia Database and the remotely collected single-lead ECG recordings.

Design and Implementation of an Ultra-Low-Power ECG Patch and Smart Cloud-Based Platform

<p>This paper reports a new device for electrocardiogram (ECG) signal monitoring and software for signal analysis and artificial intelligence (AI) assisted diagnosis. </p> <p>The hardware mitigates the signal loss common in previous products by enhancing the ergonomy, flexibility, and battery life. The power efficiency is optimized by design using switching converters, ultra-low-power components, and efficient signal processing. It enables 14-day of uninterrupted ECG monitoring and connectivity with a smartphone and microSD card storage.</p><p>The software is implemented in Android app and web-based platforms via Internet of Things (IoT). This component provides cloud-based and local storage and uses AI for arrhythmia detection. The arrhythmia detection algorithm shows 98.7% accuracy using Artificial Neural Network and K-Nearest Neighbors methods, and 98.1% using Decision Tree method on test data set.</p>

Real‐Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks

Background Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results This study involves a total of 953 independent life‐threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid‐ convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5‐fold cross‐validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.