Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks

Abstract

Atrial fibrillation (AF) is a type of cardiac arrhythmia affecting millions of people every year. This disease increases the likelihood of strokes, heart failure, and even death. While dedicated medical-grade electrocardiogram (ECG) devices can enable gold-standard analysis, these devices are expensive and require clinical settings. Recent advances in the capabilities of general-purpose smartphones and wearable technology equipped with photoplethysmography (PPG) sensors increase diagnostic accessibility for most populations. This work aims to develop a single model that can generalize AF classification across the modalities of ECG and PPG with a unified knowledge representation. This is enabled by approximating the transformation of signals obtained from low-cost wearable PPG sensors in terms of Pulse Rate Variability (PRV) to temporal Heart Rate Variability (HRV) features extracted from medical-grade ECG. This paper proposes a one-dimensional deep convolutional neural network that uses HRV-derived features for classifying 30-s heart rhythms as normal sinus rhythm or atrial fibrillation from both ECG and PPG-based sensors. The model is trained with three MIT-BIH ECG databases and is assessed on a dataset of unseen PPG signals acquired from wrist-worn wearable devices through transfer learning. The model achieved the aggregate binary classification performance measures of accuracy: 95.50%, sensitivity: 94.50%, and specificity: 96.00% across a five-fold cross-validation strategy on the ECG datasets. It also achieved 95.10% accuracy, 94.60% sensitivity, 95.20% specificity on an unseen PPG dataset. The results show considerable promise towards seamless adaptation of gold-standard ECG trained models for non-ambulatory AF detection with consumer wearable devices through HRV-based knowledge transfer.

Automatic Atrial Fibrillation Arrhythmia Detection Using Univariate and Multivariate Data

“…However, assessment of different AF classes remains limited, pioneered by field studies [29,50] separating AF into chronic (ChAF) and paroxysmal (ParAF). Throughout reviewed studies, the research efforts put on device-oriented and field data progress deserve special credit [25,47,49,72] regardless of the not yet remarkable performances achieved, as only the fully ambulatory approaches (online processing) that achieve success would enable future development of pacemaker-like medical devices capable of reverting AF attacks to normal rhythms. While the low computational demands of the RR-based univariate methods offer a bright future in the domain of wearables with limited but increasing computational capabilities, the interconnected IoT Cloud and services that are emerging in remote health markets may be calling for a research look at a wide range of multivariate pretrained models with renewed interest.…”

“…Addressing the problem of Paroxysmal AF detection in 5-min HRV segments, performance achieved values of 80.4% and 89% sensitivity and specificity, respectively, in a system trained by the Paroxysmal Atrial Fibrillation Prediction Challenge data that is tested with a combination of NSRDB and AFDB HRV sequences including Paroxysmal AF cases from the latter. In the work of Ramesh et al [72], important progress is shown in moving ECG-based AF detection methods to photoplethysmography-equipped remote health tracking devices. Although still falling short in performance with respect to benchmark tests on databases, partly due to class imbalance for the device acquired data, this work successfully paves the way for future transfer knowledge directions.…”

Machine learning in the detection and management of atrial fibrillation

“…Concerning diagnosis from a one-lead ECG recording, Hannun et al showed a superior accuracy of a DNN compared with board-certified cardiologists [ 28 ], which furthermore extended to other arrhythmias such as regular supraventricular tachycardia and atrioventricular block. Unifying applications across different diagnostic modalities, Ramesh et al recently reported the development of a DNN able to detect AF with a high diagnostic accuracy in both ECG and photoplethysmographic recordings [ 29 ]. Importantly, neural networks can also aid the screening for AF even when it is absent at the time of presentation.…”

Clinical significance, challenges and limitations in using artificial intelligence for electrocardiography-based diagnosis

“…While there is still limited supporting evidence for systematic screening for AF, as well as associated cost implications [26], targeted screening, systemic opportunistic screening or smartphone algorithms, may be a more cost-effective option when using AI-enhanced ECG systems. With an increasing consumer adoption of wearable healthcare technologies [27,28], the incorporation of AIenhanced algorithms for AF screening [29][30][31][32] would be expected to AF-related morbidities in the long-term [33,34].…”