Key result
CLAIRE explainable AI framework outperforms conventional ML with ~0.98 AUROC for MACE prediction.
Why the study?
AI models predicting cardiovascular risk from ECGs often lack interpretability, limiting clinical adoption due to inability to explain prediction drivers.
Does the CLAIRE explainable AI framework improve prediction and interpretation of mortality and MACE using standard 12-lead ECGs compared to conventional machine learning models?
Observational (n=60,000)
No
Does the CLAIRE explainable AI framework improve prediction and interpretation of mortality and MACE using standard 12-lead ECGs compared to conventional machine learning models?
An LLM-based AI framework provides highly accurate prediction of cardiovascular events from routine 12-lead ECGs while generating physiologically plausible reasoning, addressing the lack of interpretability that hinders clinical adoption of standard AI.
Artificial intelligence (AI) algorithms can detect subtle patterns in electrocardiograms (ECGs) to predict cardiovascular risk. Though accurate, these models are often unable to explain the factors driving their predictions, limiting interpretability and clinical adoption. We developed CLAIRE, an explainable AI framework leveraging an open-source chain-of-thought large language model (DeepSeek-R1-0528-Qwen3-8B) and structured ECG parameters to forecast mortality and major adverse cardiovascular events (MACE). Using 60,000 adult ECGs, the framework consisted of two stages: CLAIRE-α, trained on 636 unique ECG features, age, and gender to predict outcomes, and CLAIRE-β, which identified the most informative features and generated physiologically plausible explanatory pathways linking ECG abnormalities to clinical endpoints. Feature-reduced CLAIRE-α variants were subsequently trained using top-ranked features from CLAIRE-β. Models using all 636 features achieved the highest performance for MACE (accuracy/AUROC 0.97/0.98) and mortality (accuracy/AUROC 0.86/0.86) prediction. Feature-reduced variants retained good to excellent discrimination while lowering computational burden. Model-generated explanations highlighted relationships consistent with plausible cardiovascular physiology, as assessed by board-certified physicians. CLAIRE combined predictive accuracy with interpretability by identifying physiologically meaningful ECG features and providing hypothesis-generating explanations for its risk predictions. This study represents a step toward transparency and addresses a key limitation of contemporary ECG-based AI models.
No takes yet. Share an insight, caveat, or question.
Peng et al. (2026) conducted an observational in Cardiovascular risk prediction (n=60,000). CLAIRE explainable AI framework vs. Standard machine learning models (XGBoost, Multilayer Perceptron, Transformer) was evaluated on MACE prediction (AUROC) (AUROC 0.98, 95% CI 0.97-0.99). The CLAIRE explainable AI framework utilizing 636 structured ECG features achieved an AUROC of 0.98 for MACE prediction, outperforming conventional machine learning baselines while generating physiologically plausible explanations.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: