Atrial Fibrillation Detection Using Machine Learning

2026-02-20

AI Summary

This study addresses the critical need for early, non-invasive detection of atrial fibrillation (AF) to mitigate the risk of ischemic stroke by proposing a machine learning framework that integrates multimodal photoplethysmography (PPG) and electrocardiogram (ECG) signals. The approach extracts 22 time-domain, frequency-domain, and heart rate variability features, which are then processed using an ensemble of bagged decision trees, cubic kernel support vector machines (SVM), and subspace k-nearest neighbors (KNN) classifiers. Optimized through an ensemble strategy and 10-fold cross-validation, the method demonstrates exceptional performance in non-invasive AF detection: the subspace KNN classifier achieves a test accuracy of 98.7%, while all top-performing models exhibit both sensitivity and specificity exceeding 95%, substantially enhancing diagnostic reliability and clinical applicability.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Atrial fibrillation (AF) is a common cardiac arrhythmia and a major risk factor for ischemic stroke. Early detection of AF using non-invasive signals can enable timely intervention. In this work, we present a comprehensive machine learning framework for AF detection from simultaneous photoplethysmogram (PPG) and electrocardiogram (ECG) signals. We partitioned continuous recordings from 35 subjects into 525 segments (15 segments of 10,000 samples each at 125Hz per subject). After data cleaning to remove segments with missing samples, 481 segments remained (263 AF, 218 normal). We extracted 22 features per segment, including time-domain statistics (mean, standard deviation, skewness, etc.), bandpower, and heart-rate variability metrics from both PPG and ECG signals. Three classifiers -- ensemble of bagged decision trees, cubic-kernel support vector machine (SVM), and subspace k-nearest neighbors (KNN) -- were trained and evaluated using 10-fold cross-validation and hold-out testing. The subspace KNN achieved the highest test accuracy (98.7\%), slightly outperforming bagged trees (97.9\%) and cubic SVM (97.1\%). Sensitivity (AF detection) and specificity (normal rhythm detection) were all above 95\% for the top-performing models. The results indicate that ensemble-based machine learning models using combined PPG and ECG features can effectively detect atrial fibrillation. A comparative analysis of model performance along with strengths and limitations of the proposed framework is presented.

Problem

• Atrial Fibrillation
• Early Detection
• PPG
• ECG
• Non-invasive Signals

Innovation

• photoplethysmogram (PPG)
• electrocardiogram (ECG)
• subspace k-nearest neighbors
• atrial fibrillation detection
• ensemble machine learning