Kowadlo Gideon, Mittelberg Yoel, Ghomlaghi Milad, Stiglitz Daniel K, Kishore Kartik, Guha Ranjan, Nazareth Justin, Weinberg Laurence
Atidia Health, Melbourne, Australia.
Department of Anaesthesiology and Perioperative Medicine, Alfred Health, Melbourne, Australia.
BMC Med Inform Decis Mak. 2024 Mar 11;24(1):70. doi: 10.1186/s12911-024-02463-w.
Pre-operative risk assessment can help clinicians prepare patients for surgery, reducing the risk of perioperative complications, length of hospital stay, readmission and mortality. Further, it can facilitate collaborative decision-making and operational planning.
To develop effective pre-operative risk assessment algorithms (referred to as Patient Optimizer or POP) using Machine Learning (ML) that predict the development of post-operative complications and provide pilot data to inform the design of a larger prospective study.
After institutional ethics approval, we developed a base model that encapsulates the standard manual approach of combining patient-risk and procedure-risk. In an automated process, additional variables were included and tested with 10-fold cross-validation, and the best performing features were selected. The models were evaluated and confidence intervals calculated using bootstrapping. Clinical expertise was used to restrict the cardinality of categorical variables (e.g. pathology results) by including the most clinically relevant values. The models were created with logistic regression (LR) and extreme gradient-boosted trees using XGBoost (Chen and Guestrin, 2016). We evaluated performance using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Data was obtained from a metropolitan university teaching hospital from January 2015 to July 2020. Data collection was restricted to adult patients undergoing elective surgery.
A total of 11,475 adult admissions were included. The performance of XGBoost and LR was very similar across endpoints and metrics. For predicting the risk of any post-operative complication, kidney failure and length-of-stay (LOS), POP with XGBoost achieved an AUROC (95%CI) of 0.755 (0.744, 0.767), 0.869 (0.846, 0.891) and 0.841 (0.833, 0.847) respectively and AUPRC of 0.651 (0.632, 0.669), 0.336 (0.282, 0.390) and 0.741 (0.729, 0.753) respectively. For 30-day readmission and in-patient mortality, POP with XGBoost achieved an AUROC (95%CI) of 0.610 (0.587, 0.635) and 0.866 (0.777, 0.943) respectively and AUPRC of 0.116 (0.104, 0.132) and 0.031 (0.015, 0.072) respectively.
The POP algorithms effectively predicted any post-operative complication, kidney failure and LOS in the sample population. A larger study is justified to improve the algorithm to better predict complications and length of hospital stay. A larger dataset may also improve the prediction of additional specific complications, readmission and mortality.
术前风险评估有助于临床医生让患者为手术做好准备，降低围手术期并发症、住院时间、再入院率和死亡率的风险。此外，它还可以促进共同决策和手术规划。
使用机器学习（ML）开发有效的术前风险评估算法（称为患者优化器或POP），以预测术后并发症的发生，并提供试点数据，为更大规模的前瞻性研究设计提供参考。
经机构伦理批准后，我们开发了一个基础模型，该模型概括了结合患者风险和手术风险的标准手动方法。在一个自动化过程中，纳入了其他变量，并进行10折交叉验证测试，选择表现最佳的特征。使用自抽样法对模型进行评估并计算置信区间。利用临床专业知识，通过纳入最具临床相关性的值来限制分类变量（如病理结果）的基数。使用逻辑回归（LR）和基于XGBoost的极端梯度提升树创建模型（Chen和Guestrin，2016年）。我们使用受试者操作特征曲线下面积（AUROC）和精确召回率曲线下面积（AUPRC）评估性能。数据取自2015年1月至2020年7月一家大都市大学教学医院。数据收集仅限于接受择期手术的成年患者。
共纳入11475例成人住院病例。XGBoost和LR在各个终点和指标上的表现非常相似。对于预测任何术后并发症、肾衰竭和住院时间（LOS）的风险，基于XGBoost的POP的AUROC（95%CI）分别为0.755（0.744，0.767）、0.869（0.846，0.891）和0.841（0.833，0.847），AUPRC分别为0.651（0.632，0.669）、0.336（0.282，0.390）和0.741（0.729，0.753）。对于30天再入院率和住院死亡率，基于XGBoost的POP的AUROC（95%CI）分别为0.610（0.587，0.635）和0.866（0.777，0.943），AUPRC分别为0.116（0.104，0.132）和0.031（0.015，0.072）。
POP算法有效地预测了样本人群中的任何术后并发症、肾衰竭和住院时间。有必要进行更大规模的研究来改进算法，以更好地预测并发症和住院时间。更大的数据集也可能改善对其他特定并发症、再入院率和死亡率的预测。
