Hu Yue, Ma Fanghui, Hu Mengjie, Shi Binbing, Pan Defeng, Ren Jingjing
Department of General Practice, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Department of General Practice, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu 221004, China.
Int J Med Inform. 2025 Feb;194:105703. doi: 10.1016/j.ijmedinf.2024.105703. Epub 2024 Nov 14.
Heart failure with preserved ejection fraction (HFpEF) is associated with elevated rates of readmission and mortality. Accurate prediction of readmission risk is essential for optimizing healthcare resources and enhancing patient outcomes.
We conducted a retrospective cohort study utilizing HFpEF patient data from two institutions: the First Affiliated Hospital Zhejiang University School of Medicine for model development and internal validation, and the Affiliated Hospital of Xuzhou Medical University for external validation. A machine learning (ML) model was developed and validated using 53 variables to predict the risk of readmission within one year. The model's performance was assessed using several metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F1 score, model training time, model prediction time and brier score. SHAP (SHapley Additive exPlanations) analysis was employed to enhance model interpretability, and a dynamic nomogram was constructed to visualize the predictive model.
Among the 766 HFpEF patients included in the study, 203 (26.5%) were readmitted within one year. The LightGBM model exhibited the highest predictive performance, with an AUC of 0.88 (95% confidence interval (CI):0.84-0.91), an accuracy of 0.79, a sensitivity of 0.81, and a specificity of 0.78. Key predictors included the E/e' ratio, NYHA classification, LVEF, age, BNP levels, MLR, history of atrial fibrillation (AF), use of ACEI/ARB/ARNI, and history of myocardial infarction (MI). External validation also demonstrated strong predictive performance, with an AUC of 0.87 (95%CI:0.83-0.91).
The LightGBM model exhibited robust performance in predicting one-year readmission risk among HFpEF patients, providing a valuable tool for clinicians to identify high-risk individuals and implement timely interventions.
射血分数保留的心力衰竭（HFpEF）与再入院率和死亡率升高相关。准确预测再入院风险对于优化医疗资源和改善患者预后至关重要。
我们进行了一项回顾性队列研究，利用来自两个机构的HFpEF患者数据：浙江大学医学院附属第一医院用于模型开发和内部验证，徐州医科大学附属医院用于外部验证。使用53个变量开发并验证了一个机器学习（ML）模型，以预测一年内再入院的风险。使用包括受试者操作特征曲线下面积（AUC）、准确性、敏感性、特异性、F1分数、模型训练时间、模型预测时间和布里尔分数等多个指标评估模型的性能。采用SHAP（Shapley值相加解释）分析来增强模型的可解释性，并构建动态列线图以可视化预测模型。
在纳入研究的766例HFpEF患者中，203例（26.5%）在一年内再次入院。LightGBM模型表现出最高的预测性能，AUC为0.88（95%置信区间（CI）：0.84 - 0.91），准确性为0.79，敏感性为0.81，特异性为0.78。关键预测因素包括E/e'比值、纽约心脏协会（NYHA）分级、左心室射血分数（LVEF）、年龄、脑钠肽（BNP）水平、心肌质量比（MLR）、心房颤动（AF）病史、使用血管紧张素转换酶抑制剂/血管紧张素Ⅱ受体拮抗剂/血管紧张素受体脑啡肽酶抑制剂（ACEI/ARB/ARNI）以及心肌梗死（MI）病史。外部验证也显示出强大的预测性能，AUC为0.87（95%CI：0.83 - 0.91）。
LightGBM模型在预测HFpEF患者一年再入院风险方面表现出强大的性能，为临床医生识别高危个体并及时实施干预提供了一个有价值的工具。
