NeuroECG: ECGFounder-Based Deep ECG Representation for EEG-Free Neurological Prognostication After Cardiac Arrest

2026-07-13

AI Summary

This study addresses the underexplored predictive value of low-cost electrocardiography (ECG) for neurological prognostication after cardiac arrest, which conventionally relies on expensive electroencephalography (EEG). Leveraging the ECGFounder pre-trained model, this work pioneers an EEG-free prognostic framework by substituting deep ECG representations for EEG signals. Specifically tailored for single-lead monitoring ECG, the proposed approach incorporates progressive unfreezing fine-tuning, quantile pooling for feature aggregation, principal component analysis-based dimensionality reduction, and clinical covariate fusion. Evaluated on the I-CARE database, the fused model achieves an AUROC of 0.8077 and an AUPRC of 0.8970, significantly outperforming ECG-only baselines. These results demonstrate the feasibility of utilizing cost-effective ECG to enable high-accuracy neurological prognostication in post-cardiac arrest care.

Abstract

Neurological prognostication after cardiac arrest commonly relies on electroencephalography (EEG). However, EEG demands high clinical resources. Bedside electrocardiography (ECG) is standard and low-cost. Yet, its value for predicting neurological outcomes remains underexplored. In this study, we propose NeuroECG, an ECGFounder-based deep representation framework for EEG-free auxiliary prognostication. NeuroECG adapts a pretrained ECG foundation model via task-specific fine-tuning. We implement a gradual unfreezing strategy on single-channel bedside monitoring ECG. Multiple ECG segments per patient are encoded into segment-level deep features. These embeddings are aggregated via quantile pooling ($q = 0.24$) and compressed using principal component analysis (PCA). Experiments on 412 ECG-available patients from the multicenter I-CARE database show that the adapted ECGFounder backbone achieves the best performance among ECG-only backbone baselines, with a test AUROC of 0.7333. We further combine the learned deep ECG representation with static clinical covariates. The proposed NeuroECG model achieves a test AUROC of 0.8077 and an AUPRC of 0.8970. These results support deep bedside ECG representations as a useful source of auxiliary prognostic information. Their integration with static clinical covariates improves prediction in an EEG-free setting. The source code is available at https://github.com/goddream66/NeuroECG_

Problem

• Cardiac Arrest
• Neurological Prognostication
• Electrocardiography (ECG)
• EEG-Free

Innovation

• ECG foundation model
• Gradual unfreezing
• Quantile pooling
• Deep ECG representation
• EEG-free prognostication