Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG Signal

TL;DR

This paper introduces a contrastive self-supervised learning framework for patient similarity search using physiological signals, validated on atrial fibrillation detection from PPG data, demonstrating improved accuracy over baseline methods.

Contribution

It presents a novel contrastive learning approach with neighbor selection algorithms for patient similarity, specifically applied to AF detection from smartwatch PPG signals.

Findings

Effective patient similarity measurement demonstrated

Outperforms baseline methods in AF detection accuracy

Validated on a dataset of over 170 individuals

Abstract

In this paper, we propose a novel contrastive learning based deep learning framework for patient similarity search using physiological signals. We use a contrastive learning based approach to learn similar embeddings of patients with similar physiological signal data. We also introduce a number of neighbor selection algorithms to determine the patients with the highest similarity on the generated embeddings. To validate the effectiveness of our framework for measuring patient similarity, we select the detection of Atrial Fibrillation (AF) through photoplethysmography (PPG) signals obtained from smartwatch devices as our case study. We present extensive experimentation of our framework on a dataset of over 170 individuals and compare the performance of our framework with other baseline methods on this dataset.