Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Chen, Li, Lei, Beetz, Marcel, Banerjee, Abhirup, Gupta, Ramneek, Grau, Vicente
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909651999653888
author Chen, Chen
Li, Lei
Beetz, Marcel
Banerjee, Abhirup
Gupta, Ramneek
Grau, Vicente
author_facet Chen, Chen
Li, Lei
Beetz, Marcel
Banerjee, Abhirup
Gupta, Ramneek
Grau, Vicente
contents 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 twelve 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_10581
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction
Chen, Chen
Li, Lei
Beetz, Marcel
Banerjee, Abhirup
Gupta, Ramneek
Grau, Vicente
Quantitative Methods
Artificial Intelligence
Computation and Language
Machine Learning
Signal Processing
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 twelve 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.
title Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction
topic Quantitative Methods
Artificial Intelligence
Computation and Language
Machine Learning
Signal Processing
url https://arxiv.org/abs/2403.10581