Lv Huasheng, Sun Fengyu, Zhang Yuchen, Zhou Xinrong
State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Xinjiang Medical University, Urumqi, Xinjiang, People's Republic of China.
The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, People's Republic of China.
Int J Gen Med. 2025 Jun 8;18:2957-2972. doi: 10.2147/IJGM.S523029. eCollection 2025.
To develop and validate a machine learning (ML) model for predicting long-term depression risk in ACS patients following percutaneous coronary intervention (PCI).
This retrospective cohort study included 1951 ACS patients who underwent PCI in 2023. Feature selection was conducted using the Boruta algorithm, and restricted cubic spline (RCS) analysis was applied to assess non-linear associations. Six ML models were trained and tested using a 70:30 train-validation split. Model performance was evaluated using Area under the curve(AUC), sensitivity, specificity, F1-score, calibration curves, and decision curve analysis. SHapley Additive exPlanations (SHAP) were used to interpret feature contributions.
Among the 1951 patients, 382 (19.6%) developed long-term depression. After feature selection via the Boruta algorithm, ten key predictors were identified, including NYHA classification, diabetes, thyroid-stimulating hormone (TSH), and left ventricular ejection fraction (LVEF). The LGBM and XGBoost models achieved the highest discrimination, with AUCs of 0.849 (training) and 0.652 (validation) for LGBM, and 0.814 (training) and 0.699 (validation) for XGBoost. Calibration curves showed good alignment between predicted and observed outcomes. SHAP analysis confirmed NYHA classification, TSH, and diabetes as the most influential features. Decision curve analysis demonstrated the clinical benefit of both models across a range of thresholds.
The models demonstrated potential for early risk stratification of post-PCI depression and may inform targeted clinical interventions.
开发并验证一种机器学习（ML）模型，用于预测经皮冠状动脉介入治疗（PCI）后急性冠状动脉综合征（ACS）患者的长期抑郁风险。
这项回顾性队列研究纳入了2023年接受PCI的1951例ACS患者。使用Boruta算法进行特征选择，并应用受限立方样条（RCS）分析来评估非线性关联。使用70:30的训练-验证分割对六个ML模型进行训练和测试。使用曲线下面积（AUC）、灵敏度、特异性、F1分数、校准曲线和决策曲线分析来评估模型性能。使用SHapley加法解释（SHAP）来解释特征贡献。
在1951例患者中，382例（19.6%）出现长期抑郁。通过Boruta算法进行特征选择后，确定了十个关键预测因素，包括纽约心脏协会（NYHA）分级、糖尿病、促甲状腺激素（TSH）和左心室射血分数（LVEF）。LightGBM（LGBM）和XGBoost模型具有最高的辨别力，LGBM的训练AUC为0.849，验证AUC为0.652；XGBoost的训练AUC为0.814，验证AUC为0.699。校准曲线显示预测结果与观察结果之间具有良好的一致性。SHAP分析证实NYHA分级、TSH和糖尿病是最具影响力的特征。决策曲线分析表明，这两个模型在一系列阈值范围内均具有临床益处。
这些模型显示了对PCI后抑郁进行早期风险分层的潜力，并可为有针对性的临床干预提供参考。
