Key result
Random Forest achieves ~94% ECG classification accuracy, outperforming other machine learning models.
Why the study?
Accurate and timely detection of AF is crucial for avoiding serious cardiovascular complications such as stroke and heart failure, motivating the development of an automated machine learning-based ECG classification system.
Do machine learning and ensemble classifiers using spectral and temporal ECG features accurately classify atrial fibrillation, normal rhythm, and noisy rhythm in short single-lead ECG recordings?
Do machine learning and ensemble classifiers using spectral and temporal ECG features accurately classify atrial fibrillation, normal rhythm, and noisy rhythm in short single-lead ECG recordings?
Tree-based (Random Forest) and soft voting ensemble classifiers combined with spectral-temporal ECG feature extraction and SMOTE class balancing provide high accuracy (>93%) in distinguishing atrial fibrillation from normal and noisy ECG rhythms.
Accurate and timely detection of atrial fibrillation (AF) is a crucial issue in avoiding the risk of serious cardiovascular complications such as stroke and heart failure. This study proposed a machine learning-based system used for automated electrocardiogram (ECG) signal classification using features derived from spectral and temporal analyses. The study used a dataset obtained from the PhysioNet 2017 challenge database with 5000 samples labeled as normal rhythm (N), AF, and noisy rhythm (NR). Five primary features: average spectral energy, variation in spectral power, root mean square fluctuation, overall signal energy, and power variance were extracted, expressing both amplitude and frequency-domain characteristics of cardiac dynamics. 10-fold stratified cross-validation approach was used to evaluate the performance of the model using multiple classifiers, which are: quadratic discriminant analysis (QDA), support vector machine (SVM), random forest (RF), K-nearest neighbors (KNN), and multi-layer perceptron (MLP). Additionally, to improve model stability and accuracy, a soft voting-based ensemble model was developed. Although RF achieved the highest accuracy (94.15%), the ensemble model (93.21%) outperformed QDA and SVM. The ensemble approach achieved sensitivities ranging from 0.89 to 0.96 and specificities between 0.95 and 0.97 across all rhythm categories, demonstrating strong generalization.
No takes yet. Share an insight, caveat, or question.
Fathel et al. (2026) studied Atrial fibrillation (ECG signal classification) (n=5,000). Machine learning classifiers (Random Forest, Soft Voting Ensemble, KNN, MLP, SVM, QDA) using spectral and temporal ECG features vs. Comparison across six classification models (QDA, SVM, RF, KNN, MLP, Ensemble) was evaluated on Overall classification accuracy for ECG rhythm categories (normal, atrial fibrillation, noisy rhythm). Random Forest achieved the highest ECG classification accuracy at 94.15% (AUC 1.000), while the soft voting ensemble model achieved 93.21% accuracy (AUC 0.997), outperforming QDA (64.30%).
Synapse has enriched 5 related papers. Consider them for comparative context: