Yu Jiayu, Peng Xiran, Zhou Ruihao, Zhu Tao, Hao Xuechao
Department of Anesthesiology, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China.
Research Unit for Perioperative Stress Assessment and Clinical Decision, Chinese Academy of Medical Sciences West China Hospital, Sichuan University, Chengdu, China.
Int J Surg. 2025 Feb 1;111(2):1939-1949. doi: 10.1097/JS9.0000000000002203.
Major adverse cardiovascular events (MACEs) within 30 days following noncardiac surgery are prognostically relevant. Accurate prediction of risk and modifiable risk factors for postoperative MACEs is critical for surgical planning and patient outcomes. We aimed to develop and validate an accurate and easy-to-use machine learning model for predicting postoperative MACEs in geriatric patients undergoing noncardiac surgery.
The cohort study was conducted at an academic medical center between June 2019 and February 2023. The outcome was postoperative MACEs within 30 days after surgery. Significant predictors were selected using permutation-shuffling. Ten machine learning models were established and compared with the Revised Cardiac Risk Index (RCRI). The SHapley Additive exPlanations algorithm was used to interpret the models.
Of the 18,395 patients included, 354 (1.92%) experienced postoperative MACEs. Eighteen predictors were included in model development. The AutoGluon model outperformed other models and the RCRI with an AUROC of 0.884 (95% CI: 0.878-0.890), an accuracy of 0.976 (95% CI: 0.973-0.978), and a Brier score of 0.023 (95% CI: 0.020-0.026). In interpretability analyses, the hemoglobin level was the most important predictor. We identified the relationships between predictors and postoperative MACEs and interaction effects between some predictors. The AutoGluon model has been deployed as a web-based tool for further external validation ( https://huggingface.co/spaces/MDC2J/Predicting_postoperative_MACEs ).
In this prospective study, the AutoGluon model could accurately predict MACEs after noncardiac surgery in geriatric patients, outperforming existing models and the RCRI. Subsequent interpretability analysis can provide insight into how our model works and help personalize surgical strategies.
非心脏手术后30天内发生的主要不良心血管事件（MACE）具有预后相关性。准确预测术后MACE的风险和可改变的风险因素对于手术规划和患者预后至关重要。我们旨在开发并验证一种准确且易于使用的机器学习模型，用于预测接受非心脏手术的老年患者术后发生的MACE。
队列研究于2019年6月至2023年2月在一家学术医疗中心进行。结局指标为术后30天内发生的MACE。使用排列重排法选择显著预测因素。建立了10种机器学习模型，并与修订心脏风险指数（RCRI）进行比较。使用SHapley加性解释算法对模型进行解释。
纳入的18395例患者中，354例（1.92%）发生了术后MACE。模型开发纳入了18个预测因素。AutoGluon模型的表现优于其他模型和RCRI，其曲线下面积（AUROC）为0.884（95%CI：0.878 - 0.890），准确率为0.976（95%CI：0.973 - 0.978），布里尔评分（Brier score）为0.023（95%CI：0.020 - 0.026）。在可解释性分析中，血红蛋白水平是最重要的预测因素。我们确定了预测因素与术后MACE之间的关系以及一些预测因素之间的交互作用。AutoGluon模型已作为基于网络的工具进行部署，用于进一步的外部验证（https://huggingface.co/spaces/MDC2J/Predicting_postoperative_MACEs）。
在这项前瞻性研究中，AutoGluon模型能够准确预测老年患者非心脏手术后的MACE，表现优于现有模型和RCRI。后续的可解释性分析可以深入了解我们的模型如何工作，并有助于个性化手术策略。
