Support Vector Machine models (AUC 0.874; 95% CI 0.769-0.959) outperformed the CHA2DS2-VASc score (AUC 0.643) in predicting incident ischaemic stroke in HFrEF patients without atrial fibrillation.
Observational (n=2,213)
Do machine learning models improve the prediction of incident ischaemic stroke compared to the CHA2DS2-VASc score in patients with HFrEF without AF?
Machine learning models, particularly SVM and XGBoost, significantly outperform the CHA2DS2-VASc score in predicting incident ischaemic stroke in patients with HFrEF without atrial fibrillation.
Effect estimate: AUC 0.874 (95% CI 0.769-0.959)
Abstract Background The prediction of ischaemic stroke in patients with heart failure with reduced ejection fraction (HFrEF) but without atrial fibrillation (AF) remains challenging. Our aim was to evaluate the performance of machine learning (ML) in identifying the development of ischaemic stroke in this population. Methods We performed a post‐hoc analysis of the WARCEF trial, only including patients without a history of AF. We evaluated the performance of 9 ML models for identifying incident stroke using metrics including area under the curve (AUC) and decision curve analysis. The importance of each feature used in the model was ranked by SAPley Additive exPlanations (SHAP) values. Results We included 2213 patients with HFrEF but without AF (mean age 58 ± 11 years; 80% male). Of these, 74 (3.3%) had an ischaemic stroke in sinus rhythm during a mean follow‐up of 3.3 ± 1.8 years. Out of the 29 patient‐demographics variables, 12 were selected for the ML training. Almost all ML models demonstrated high AUC values, outperforming the CHA 2 DS 2 ‐VASc score (AUC: 0.643, 95% confidence interval CI: 0.512–0.767). The Support Vector Machine (SVM) and XGBoost models achieved the highest AUCs, with 0.874 (95% CI: 0.769–0.959) and 0.873 (95% CI: 0.783–0.953), respectively. The SVM and LightGBM consistently provided significant net clinical benefits. Key features consistently identified across these models were creatinine clearance (CrCl), blood urea nitrogen (BUN) and warfarin use. Conclusions Machine‐learning models can be useful in identifying incident ischaemic strokes in patients with HFrEF but without AF. CrCl, BUN and warfarin use were the key features.
Ishiguchi et al. (Mon,) conducted a observational in Heart failure with reduced ejection fraction (HFrEF) without atrial fibrillation (n=2,213). Machine learning models (Support Vector Machine and XGBoost) vs. CHA2DS2-VASc score was evaluated on Incident ischaemic stroke (AUC 0.874, 95% CI 0.769-0.959). Support Vector Machine models (AUC 0.874; 95% CI 0.769-0.959) outperformed the CHA2DS2-VASc score (AUC 0.643) in predicting incident ischaemic stroke in HFrEF patients without atrial fibrillation.