Ahmed Badr

Abstract:

This work presents XBeats, a novel platform for real-time electrocardiogram monitoring and analysis that uses edge computing and machine learning for early anomaly detection. The platform encompasses a data acquisition ECG patch with 12 leads to collect heart signals, perform on-chip processing, and transmit the data to healthcare providers in real-time for further analysis. The ECG patch provides a dynamically configurable selection of the active ECG leads that could be transmitted to the backend monitoring system. The selection ranges from a single ECG lead to a complete 12-lead ECG testing configuration. XBeats implements a lightweight binary classifier for early anomaly detection to reduce the time to action should abnormal heart conditions occur. This initial detection phase is performed on the edge (i.e., the device paired with the patch) and alerts can be configured to notify designated healthcare providers. Further deep analysis can be performed on the full fidelity 12-lead data sent to the backend. A fully functional prototype of the XBeats has been implemented to demonstrate the feasibly and usability of the proposed system. Performance evaluation shows that XBeats can achieve up to 95.30% detection accuracy for abnormal conditions, while maintaining a high data acquisition rate of up to 441 samples per second. Moreover, the analytical results of the energy consumption profile show that the ECG patch provides up to 37 h of continuous 12-lead ECG streaming.

Abstract:

Abstract:

In response to the rapid digital revolution and the COVID-19 pandemic, the healthcare landscape has significantly shifted from physical to virtual care and telemedicine. As a result, healthcare providers and patients have shown increased interest and adoption for up-to-date technologies to monitor ongoing health conditions, including cardiovascular diseases. Driven by the importance of an efficient remote cardiovascular monitor for virtual care, we present a platform that enables remote ECG testing and provides ubiquitous data access to patients and their healthcare providers. A patent-pending 12-lead data acquisition ECG patch is attached to the patient's body to simultaneously collect heart signals, perform binary classification, and transmit the data to healthcare providers for further analysis at a high rate of up to 480 samples per second. As a preliminary classification phase, the presented platform introduces a machine learning technique to classify ECG signals near the ECG patch. The classification function is optimized for power-constrained devices using machine learning techniques. Moreover, the preliminary results of the energy consumption profile show that the ECG patch provides up to 37 hours of continuous 12-lead ECG streaming.

Abstract:

The Internet of Things (IoT) is a conceptual paradigm that connects billions of Internet-enabled devices to exchange data among themselves and their surroundings to enable smart interactions and connect the physical infrastructure to digital systems. IoT represents a revolutionary paradigm that started to affect our lives in many positive ways. The term Internet of Things was first coined in 1999 by Kevien Ashton (Ashton, 2009) and was initially designed to support RFID technology. However, nowadays IoT has reached far beyond its designers’ vision and become much popular for the new applications it opens up in many vital domains like healthcare, intelligent transportation, public safety, home automation, smart city, asset monitoring, industrial automation and much more. The evolution of IoT presented the long-awaited promise of ubiquitous data access in which people wanted to have access to real-time data on the go anywhere and anytime.

Abstract:

ECG monitoring systems have a significant role in detecting cardiovascular diseases and reducing the rate of sudden cardiac deaths. One of the critical factors to support real-time ECG tracking is to guarantee monitoring system availability. Hence, this work targets battery life expansion for a 12 Lead ECG patch. ECG patch operational hours are extended by reducing Bluetooth Low Energy (BLE) communication airtime, hence reducing the overall transmission power and extending the battery life. Huffman, delta, and base-delta compression techniques are implemented on a Texas Instruments CC2650 Microcontroller Unit using different sampling rates and cardiac conditions such as normal, ventricular tachycardia, and ventricular fibrillation state. The performance of each encoding algorithm is evaluated in terms of compression ratio, the execution time, and power consumption of the ECG patch. Our findings show that the base-delta encoding technique outperforms other techniques and achieves 70% data compression on normal ECG data, 41% on ventricular fibrillation, and 44% on ventricular tachycardia. The execution time of base-delta encoding takes less than 25 ms execution time and saves up to 36 % of the power consumption on the MCU environment.

Abstract:

The electrocardiogram (ECG) test is developed to monitor the functionality of the cardiovascular system. Nowadays, numerous attentions have been given to the accurate and early detection of heartbeat anomalies in real-time to prevent complications and take necessary measures. This paper proposes a robust real-time binary classification for ECG signals to detect possible anomalies. We implement an initial detection phase right where ECG data is collected through lightweight deep learning analysis. We evaluate the system on two widely used datasets, PTB and MIT-BIH datasets from PhysioNet. Our experiments suggest using artificial neural network (ANN) algorithms for their superior performance over other machine learning algorithms with an accuracy up to 99.3%. Furthermore, we implemented our system on a Raspberry Pi B+ representing an ECG patch to collect and process ECG signals and detect any abnormalities using the proposed ANN model. To create a scalable system, we stream the data in real-time using Apache Kafka and MQTT to keep records of patients’ ECG data and use it for further analysis to identify causes and support medical diagnosis. The system notifies healthcare providers when abnormalities are detected.

Abstract:

Enabled by the fast development of Internet of Things (IoT) technologies in recent years, the healthcare domain has witnessed significant advancements in wearable devices that seamlessly collect vital medical information. With the availability of IoT devices serving the healthcare domain, extraordinary amounts of sensory data are generated in real-time, requiring immediate diagnoses and attention in critical medical conditions. The provision of remote patient monitoring (RPM) and analytics infrastructure proved to be fundamental components of the healthcare domain during the Coronavirus pandemic. Traditional healthcare services are digitized and offered virtually, where patients are monitored and managed remotely without the need to go to hospitals. This paper presents a comprehensive RPM framework for real-time telehealth operations with scalable data monitoring, real-time analytics and decision-making, fine-grained data access and robust notification mechanisms in emergencies and critical health conditions. We focus on the overall framework architecture, enabling technologies integration, various system-level integrations and deployment options. Furthermore, we provide a use case application for patients with chronic heart conditions for real-time electrocardiogram (ECG) monitoring. We are releasing the framework as open-source software to the active research community.

Abstract:

Continuous real-time electrocardiogram (ECG) monitoring can detect arrhythmia and provide early warning for heart attacks. Effective power management signals and controlling the mode of operation to reduce the need for full fidelity ECG signal. This work studies the impact of the base-delta compression technique for different cardiac conditions on power consummation. It also aims to evaluate operational strategies and their effect on the battery life when the ECG patch can switch between different operating modes (e.g., varying the number of leads according to the cardiac conditions). We use a binary classifier to inform the decision of switching between different operational strategies. Both scenarios are evaluated in terms of execution time, Bluetooth Low Energy (BLE) communication airtime, power consumption, and energy-saving ratios on a Texas Instruments CC2650 Micro-controller Unit (MCU). We compare the performance of the base-delta compression and changing the mode of operation scenarios on various cardiac abnormalities. Performance evaluation shows that operational strategies outperforms data compression in power saving for normal ECG readings by a double fold. In contrast, operational strategies incurs an additional overhead of 1011 ms during an abnormal status. However, base-delta satisfies the embedded platform constraints on execution time and airtime with 25 ms and 20 ms, respectively in the MCU environment.