Large language model-informed ECG dual attention network for heart failure risk prediction

Journal article

Heart failure (HF) poses a significant public health challenge, with a rising global mortality rate. Early detection and prevention of HF could significantly reduce its impact. We introduce a novel methodology for predicting HF risk using 12-lead electrocardiograms (ECGs). We present a novel, lightweight dual attention ECG network designed to capture complex ECG features essential for early HF risk prediction, despite the notable imbalance between low and high-risk groups. This network incorporates a cross-lead attention module and 12 lead-specific temporal attention modules, focusing on cross-lead interactions and each lead's local dynamics. To further alleviate model overfitting, we leverage a large language model (LLM) with a public ECG-Report dataset for pretraining on an ECG-Report alignment task. The network is then fine-tuned for HF risk prediction using two specific cohorts from the UK Biobank study, focusing on patients with hypertension (UKB-HYP) and those who have had a myocardial infarction (UKB-MI). The results reveal that LLM-informed pre-training substantially enhances HF risk prediction in these cohorts. The dual attention design not only improves interpretability but also predictive accuracy, outperforming existing competitive methods with C-index scores of 0.6349 for UKB-HYP and 0.5805 for UKB-MI. This demonstrates our method's potential in advancing HF risk assessment with clinical complex ECG data.

Authors: Chen, C; Li, L; Beetz, M; Banerjee, A; Gupta, R

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Journal: IEEE Transactions on Big Data
• Volume: 11
• Issue: 3
• Pages: 948-960
• Place of publication: United States
• Publication date: 2025-01-30
• Acceptance date: 2024-06-20
• DOI: 10.1109/tbdata.2025.3536922
• EISSN: 2332-7790
• Pmid: 40524840
• Language: English
• Keywords: large language model; risk prediction; interpretable artificial intelligence; heart failure; multi-modal learning; electrocardiogram; hafnium; lead; electrocardiography; predictive models; feature extraction; biological system modeling; data models; training; representation learning; large language models