A Closer Look at Mortality Risk Prediction from Electrocardiograms
Several recent studies combine large private ECG databases with AI to predict patient mortality. These studies typically use a few, highly variable, modeling approaches. While benchmarking these approaches has historically been limited by a lack of public ECG datasets, this changed with the 2023 release of MIMIC-IV, containing 795,546 ECGs from a U.S. hospital system, and the 2020 release of Code-15, containing 345,779 ECGs collected during routine care in Brazil. We benchmark over 500 AI-ECG survival models predicting all-cause mortality on Code-15 and MIMIC-IV with 2 neural architectures, 4 Deep-Survival-Analysis approaches, and classifiers predicting mortality at 4 time horizons. We extend the highest-performing approach to a dataset from Boston Children's Hospital (BCH, 225,379 ECGs). Models train with and without demographics (age/sex) and evaluate across datasets. The best performing Deep-Survival-Analysis models trained with ECG and demographics yield good median Concordance Indices (Code-15: 0.82, MIMIC-IV: 0.78, BCH: 0.76) and AUPRC scores (median 1-yr/5-yr, Code-15: 0.07/0.15; MIMIC-IV: 0.45/0.55; BCH: 0.04/0.13) considering the percentage of ECGs linked to mortality (1-yr/5-yr, Code-15: 1.2%/3.4%; MIMIC-IV: 14.8%/24.5%; BCH: 0.9%/4.8%). Contrasting with Deep-Survival-Analysis models, classifier-based AI-ECG models exhibit significant, site-dependent sensitivity to the choice of time horizon (median Pearson's R, Code-15: 0.69, p<1E-5; MIMIC-IV: -0.80 p<1E-5). Demographic-only models perform surprisingly well on Code-15. Concordance drops 0.03-0.24 on external validation. We recommend Deep-Survival-Analysis over Classifier-Cox approaches and the inclusion of demographic covariates in ECG survival modeling. Comparisons to demographic-only and baseline models is crucial. External evaluations support fine-tuning models on site-specific data.
Code (1)
Tasks
BenchmarkingPredictionSurvival AnalysisSimilar Papers 제목 키워드 기반
Electrocardiographic Deep Learning for Predicting Post-Procedural Mortality
Background. Pre-operative risk assessments used in clinical practice are limited in their ability to identify risk for post-operative mortality. We hypothesize that electrocardiograms contain hidden risk markers that can…
Deep LearningEarly prediction of the risk of ICU mortality with Deep Federated Learning
Intensive Care Units usually carry patients with a serious risk of mortality. Recent research has shown the ability of Machine Learning to indicate the patients' mortality risk and point physicians toward individuals wit…
Federated LearningICU MortalityMortality PredictionLarge Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction
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 predic…
Language ModelingLanguage ModellingLarge Language ModelAge Prediction From 12-lead Electrocardiograms Using Deep Learning: A Comparison of Four Models on a Contemporary, Freely Available Dataset
The 12-lead electrocardiogram (ECG) is routine in clinical use and deep learning approaches have been shown to have the identify features not immediately apparent to human interpreters including age and sex. ECG predicte…
Harmonized Interpretable ECG Waveform Features for Robust Cross-Dataset Clinical Prediction
Electrocardiograms (ECGs) are widely used for cardiovascular risk prediction, yet models often fail to transfer across hospitals because of protocol, population, and measurement differences. We benchmark cross-dataset ge…