Modeling Day-Long ECG Signals to Predict Heart Failure Risk with Explainable AI

TL;DR

This study demonstrates that deep learning applied to 24-hour ECG data can effectively predict five-year heart failure risk, offering explainability and capturing circadian and arrhythmic patterns.

Contribution

Introduces DeepHHF, a novel deep learning model that predicts heart failure risk from 24-hour ECG data with explainability, outperforming shorter segment models and clinical scores.

Findings

DeepHHF achieved an AUC of 0.80 in risk prediction.

High-risk individuals had a two-fold increase in hospitalization or death.

Explainability revealed focus on arrhythmias and circadian patterns.

Abstract

Heart failure (HF) affects 11.8% of adults aged 65 and older, reducing quality of life and longevity. Preventing HF can reduce morbidity and mortality. We hypothesized that artificial intelligence (AI) applied to 24-hour single-lead electrocardiogram (ECG) data could predict the risk of HF within five years. To research this, the Technion-Leumit Holter ECG (TLHE) dataset, including 69,663 recordings from 47,729 patients, collected over 20 years was used. Our deep learning model, DeepHHF, trained on 24-hour ECG recordings, achieved an area under the receiver operating characteristic curve of 0.80 that outperformed a model using 30-second segments and a clinical score. High-risk individuals identified by DeepHHF had a two-fold chance of hospitalization or death incidents. Explainability analysis showed DeepHHF focused on arrhythmias and heart abnormalities, with key attention between 8 AM and 3 PM. This study highlights the feasibility of deep learning to model 24-hour continuous ECG data, capturing paroxysmal events and circadian variations essential for reliable risk prediction. Artificial intelligence applied to single-lead Holter ECG is non-invasive, inexpensive, and widely accessible, making it a promising tool for HF risk prediction.