Leveraging Self-Supervised Learning Methods for Remote Screening of Subjects with Paroxysmal Atrial Fibrillation
Adrian Atienza, Gouthamaan Manimaran, Sadasivan Puthusserypady, Helena Dominguez, Peter K. Jacobsen, Jakob E. Bardram
TL;DR
The paper addresses the bottleneck of large labeled clinical datasets by applying Self-Supervised Learning (SSL) to screen Paroxysmal Atrial Fibrillation (P-AF) from remote, single-lead ECG signals recorded in normal sinus rhythm. It compares a range of SSL approaches (both contrastive and non-contrastive) against supervised baselines using a very small evaluation cohort (50 subjects) and pre-training on the Sleep Heart Health Study (SHHS) data. The results show SSL consistently outperforms supervised methods, enabling feasible preliminary analyses in data-limited settings and guiding where labeled data collection should be focused. The work demonstrates the potential for SSL-enabled, remote ECG screening to scale population monitoring and informs strategies for data collection in healthcare AI research.
Abstract
The integration of Artificial Intelligence (AI) into clinical research has great potential to reveal patterns that are difficult for humans to detect, creating impactful connections between inputs and clinical outcomes. However, these methods often require large amounts of labeled data, which can be difficult to obtain in healthcare due to strict privacy laws and the need for experts to annotate data. This requirement creates a bottleneck when investigating unexplored clinical questions. This study explores the application of Self-Supervised Learning (SSL) as a way to obtain preliminary results from clinical studies with limited sized cohorts. To assess our approach, we focus on an underexplored clinical task: screening subjects for Paroxysmal Atrial Fibrillation (P-AF) using remote monitoring, single-lead ECG signals captured during normal sinus rhythm. We evaluate state-of-the-art SSL methods alongside supervised learning approaches, where SSL outperforms supervised learning in this task of interest. More importantly, it prevents misleading conclusions that may arise from poor performance in the latter paradigm when dealing with limited cohort settings.