Application of federated learning techniques for arrhythmia classification using 12-lead ECG signals

TL;DR

This paper demonstrates that federated learning can effectively train AI models for arrhythmia classification from 12-lead ECG signals across multiple sources, preserving privacy and achieving performance comparable to centralized methods.

Contribution

It introduces a federated learning approach for ECG-based arrhythmia detection that maintains data privacy and performs well on heterogeneous, distributed datasets.

Findings

Models achieved comparable accuracy to centralized training.

Federated approach reduced training complexity and time.

Effective on both IID and non-IID data distributions.

Abstract

Artificial Intelligence-based (AI) analysis of large, curated medical datasets is promising for providing early detection, faster diagnosis, and more effective treatment using low-power Electrocardiography (ECG) monitoring devices information. However, accessing sensitive medical data from diverse sources is highly restricted since improper use, unsafe storage, or data leakage could violate a person's privacy. This work uses a Federated Learning (FL) privacy-preserving methodology to train AI models over heterogeneous sets of high-definition ECG from 12-lead sensor arrays collected from six heterogeneous sources. We evaluated the capacity of the resulting models to achieve equivalent performance compared to state-of-the-art models trained in a Centralized Learning (CL) fashion. Moreover, we assessed the performance of our solution over Independent and Identical distributed (IID) and non-IID federated data. Our methodology involves machine learning techniques based on Deep Neural Networks and Long-Short-Term Memory models. It has a robust data preprocessing pipeline with feature engineering, selection, and data balancing techniques. Our AI models demonstrated comparable performance to models trained using CL, IID, and non-IID approaches. They showcased advantages in reduced complexity and faster training time, making them well-suited for cloud-edge architectures.