Towards the Prediction of Atrial Fibrillation Based on Interpretable ECG Features

Alexander Hammer, Hagen Malberg, Martin Schmidt
TU Dresden


Atrial fibrillation (AF) is our society's most common cardiac arrhythmic disease, leading to increased morbidity and mortality. Since early detection of AF episodes allows timely interventions, predicting AF episodes during sinus rhythm based on electrocardiograms (ECGs) is highly important. It is known, that changes in selected ECG morphology features are a predictor for the onset of AF, but no systematic investigation of different ECG features' temporal changes has been performed so far.

We split the sinus rhythm episodes 60 minutes before AF from the MIT-BIH AF database into segments of 5 minutes with 50% overlap (n = 644) and calculated 155 features per segment, including signal quality indices, (variability) features, beat characteristics, and beat-to-beat changes. Logistic regression analyses between the segments preceding AF and others revealed the most significant effects for segments ending 5 minutes before AF onset. PQ interval slope (p < 0.01), PQ interval correlation (p < 0.05), and median RR time (p < 0.05) were indicated the most relevant among the 21 features, showing significant effects. Other segments showed significant effects but less frequently. Using a decision tree ensemble, trained with all features, we achieved an accuracy of 0.87 when distinguishing 8 segment clusters.

Our results confirm expected changes in ECG features (e.g., PQ interval) before AF episodes, indicating impaired atrial excitation, and show that the combination of interpretable features is sufficient to discriminate at different points in time before AF onset. For advanced analyses, extensive databases should be included.