Development and validation of a machine learning-based nomogram model for predicting frailty after cardiac surgery
Author:
Affiliation:
Department of Cardiovascular Surgery, the First Affiliated Hospital of Nanjing Medical University, Nanjing 210029 , China
Fund Project:
摘要
|
图/表
|
访问统计
|
参考文献
|
相似文献
|
引证文献
|
资源附件
|
文章评论
摘要:
目的：构建并验证一种用于预测心脏术后衰弱风险的个体化预测模型。方法：纳入2023年1—12月在南京医科大学第一附属医院接受心脏手术的患者，在术后1个月采用衰弱筛查量表对患者进行衰弱评估。根据评估结果将患者分为衰弱组及非衰弱组。采用最小绝对收缩和选择算子（least absolute shrinkage and selection operator，LASSO）、随机森林（random forest，RF）以及极限梯度提升（extreme gradient boosting，XGBoost）3种机器学习算法筛选共同预测因子，随后使用Logistic回归构建列线图模型。采用受试者工作特征（receiver operating characteristic，ROC）曲线及其曲线下面积（area under the curve，AUC）评估模型的区分度、校准曲线评估模型的一致性、决策曲线分析（decision curve analysis，DCA）评估该模型的临床价值，并在内部验证集以及时间分层验证集中予以验证。结果：共纳入301例患者，其中235例按7∶3比例分为训练集（n=165）、内部验证集（n=70），其余66例患者作为时间分层验证。依据机器学习结果，纳入4个共同预测因子：年龄、术前左心室射血分数（left ventricular ejection fraction，LVEF）、术前白蛋白水平和术前左心室舒张末期内径（left ventricular diastolic dimension，LVDd）。以此构建列线图，在训练集（AUC=0.846，95%CI：0.763~0.928）、内部验证集（AUC=0.821，95%CI：0.701~0.940）和时间分层验证集（AUC=0.846，95%CI：0.740~0.951）中均表现出优异的区分能力。校准曲线显示预测风险与观察风险之间具有高度一致性。DCA进一步证明了其良好的临床实用性。结论：基于患者年龄、术前白蛋白水平、LVEF以及LVDd构建的心脏术后衰弱预测列线图模型具有良好的预测效能与临床适用性，有助于早期识别高危患者。
Abstract:
Objective：To develop and externally validate a patient - level prediction model for postoperative frailty in adults undergoing cardiac surgery. Methods：Our study included patients who underwent cardiac surgery at the First Affiliated Hospital of Nanjing Medical University between January and December 2023. Frailty was assessed one month postoperatively using the FRAIL scale，and patients were categorized into frailty and non-frailty groups. Three machine learning algorithms，least absolute shrinkage and selection operator（LASSO），random forest（RF），and extreme gradient boosting（XGBoost），were employed to identify common predictors. A nomogram prediction model was subsequently constructed using Logistic regression. The model’s discriminative ability was evaluated using the receiver operating characteristic（ROC）curve and the area under the curve（AUC）. Calibration curves assessed consistency，and decision curve analysis（DCA）evaluated clinical utility. The model was validated internally and externally.Results：A total of 301 patients were included. Among them，235 patients were divided into a training set（n=165）and an internal validation set（n=70）at a ratio of 7∶3，while the remaining 66 patients served as temporal validation. Based on the machine learning results，four common predictors were identified：age，preoperative left ventricular ejection fraction（LVEF），preoperative albumin level，and preoperative left ventricular end - diastolic dimension（LVDd）. These were used to construct the nomogram. The modeldemonstrated excellent discriminative ability in the training set（AUC=0.846，95% CI：0.763-0.928），internal validation set（AUC=0.821，95%CI：0.701-0.940），and temporal validation set（AUC=0.846，95%CI：0.740-0.951）. The calibration curve indicated high consistency between predicted and observed risks. Decision curve analysis further confirmed its good clinical practicality. Conclusion：The nomogram prediction model for post-cardiac surgery frailty，based on patient age，preoperative albumin level，LVEF，and LVDd，exhibits good predictive performance and clinical applicability，facilitating the early identification of high-risk patients.
