Optimization of Atrial Fibrillation Detection Using Multiple Machine Learning Approaches Based on a Large-Scale Data Set of 12-Lead Electrocardiograms (Preprint)

Abstract

Atrial fibrillation (AF) represents a hazardous cardiac arrhythmia that significantly elevates the risk of stroke and heart failure. Despite its severity, its diagnosis largely relies on the proficiency of healthcare professionals. At present, the real-time identification of paroxysmal AF is hindered by the lack of automated techniques. Consequently, a highly effective machine learning algorithm specifically designed for AF detection could offer substantial clinical benefits. The aim of this study is therefore to develop a clinical valuable machine learning algorithm that can accurately detect AF.

The aim of this study is to develop a clinical valuable machine learning algorithm that can accurately detect AF.

We utilized 12-lead ECG recordings sourced from the 2020 PhysioNet Challenge data sets. The Welch method was employed to extract power spectral features of the 12-lead electrocardiograms (ECGs) within a frequency range of 0.083 to 24.92 Hz. Subsequently, various machine learning techniques were evaluated and optimized to classify sinus rhythm and AF based on these power spectral features.

The LightGBM was found to be the most effective in classifying AF and SR, achieving an average F1 score of 0.988 across all ECG leads. Among the frequency subbands, the 0.083 to 4.92 Hz range yielded the highest F1 score. In lead comparisons, aVR had the highest performance (F1 = 0.993), with minimal differences observed between leads.

In conclusion, this study successfully employed machine learning methodologies, particularly the LightGBM model, to differentiate SR and AF based on power spectral features derived from 12-lead ECGs. The performance marked by an average F1 score of 0.988 and minimal interlead variation underscores the potential of machine learning algorithms to bolster real-time atrial fibrillation detection. This advancement could significantly improve patient care in intensive care units as well as facilitate remote monitoring through wearable devices, ultimately enhancing clinical outcomes.