Ishiguchi Hironori, Chen Yang, Huang Bi, Gue Ying, Correa Elon, Homma Shunichi, Thompson John L P, Qian Min, Lip Gregory Y H, Abdul-Rahim Azmil H
Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool, UK.
Division of Cardiology, Department of Medicine and Clinical Science, Yamaguchi University Graduate School of Medicine, Ube, Japan.
Eur J Clin Invest. 2025 Mar;55(3):e14360. doi: 10.1111/eci.14360. Epub 2024 Nov 18.
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.
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.
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 CHADS-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.
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.
对于射血分数降低的心力衰竭（HFrEF）且无房颤（AF）的患者，缺血性卒中的预测仍然具有挑战性。我们的目的是评估机器学习（ML）在识别该人群缺血性卒中发生情况方面的性能。
我们对WARCEF试验进行了事后分析，仅纳入无房颤病史的患者。我们使用包括曲线下面积（AUC）和决策曲线分析等指标，评估了9种ML模型识别新发卒中的性能。模型中使用的每个特征的重要性通过SHAP值进行排名。
我们纳入了2213例HFrEF但无AF的患者（平均年龄58±11岁；80%为男性）。在平均3.3±1.8年的随访期间，其中74例（3.3%）在窦性心律时发生了缺血性卒中。在29个患者人口统计学变量中，选择了12个用于ML训练。几乎所有ML模型都显示出较高的AUC值，优于CHADS-VASc评分（AUC：0.643，95%置信区间[CI]：0.512-0.767）。支持向量机（SVM）和XGBoost模型的AUC最高，分别为0.874（95%CI：0.769-0.959）和0.873（95%CI：0.783-0.953）。SVM和LightGBM始终提供显著的净临床益处。这些模型中一致确定的关键特征是肌酐清除率（CrCl）、血尿素氮（BUN）和华法林的使用。
机器学习模型可用于识别HFrEF但无AF患者的新发缺血性卒中。CrCl、BUN和华法林的使用是关键特征。
