开发与评估机器学习模型预测肾衰竭患者非心脏手术后主要心脏事件与死亡风险
研究开发并评估简化机器学习模型,预测加拿大阿尔伯塔省和曼尼托巴省肾衰竭患者非心脏手术后30天内主要心脏事件与死亡。曼尼托巴省数据分为训练集70%、验证集15%和测试集15%,阿尔伯塔省数据用于外部验证。最终XGBoost和随机森林模型在测试集中AUC-ROC分别为0.861和0.863,外部验证性能相似且校准良好。
要点
- 简化XGBoost模型(8个特征)测试集AUC-ROC为0.861,AUC-PR为0.304。
- 简化随机森林模型(19个特征)测试集AUC-ROC为0.863,AUC-PR为0.332。
- 模型在阿尔伯塔省外部验证中性能相似且校准良好。
核心结论
- 机器学习模型准确且比现有基于回归的工具更简约。
- 未来工作应在其他人群中测试这些模型并与基于回归的模型比较,同时评估这些工具用于指导风险导向围手术期护理的价值。
研究设计与样本
- 曼尼托巴省数据分为训练集70%、验证集15%和测试集15%,训练集用于超参数调优和模型训练,验证集用于特征选择和评估模型性能,测试集用于最终模型性能。
- 外部评估在阿尔伯塔省队列中进行。
- 纳入曼尼托巴省成人(≥18岁)肾衰竭患者(eGFR < 15 mL/min/1.73 m2或维持性透析)接受非心脏手术(2007-2019),评估数据为阿尔伯塔省成人(2005-2019)。
- 共4175名参与者(12082次手术),观察到569个结局(5%)。
主要发现
- 简化XGBoost模型(8个特征)在测试队列中AUC-ROC为0.861,AUC-PR为0.304。
- 简化随机森林模型(19个特征)在测试队列中估计AUC-ROC为0.863,AUC-PR为0.332。
- 在阿尔伯塔省的外部验证显示相似性能且校准良好。
临床怎么用
- 这些模型可能让临床医生告知患者其个体化风险,这可能支持共享围手术期决策。
局限性
- 缺乏加拿大以外的外部验证。
- 未来工作应在其他人群中测试这些模型并与基于回归的模型比较,同时评估这些工具用于指导风险导向围手术期护理的价值。
- 需要更多研究了解它们在其他地理位置和卫生保健系统中的表现。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
RATIONALE & OBJECTIVE: People with kidney failure undergoing noncardiac surgery face an elevated risk of cardiovascular events and mortality. Existing risk prediction tools for perioperative events are either inaccurate in this population or include many variables that may complicate implementation. We developed and evaluated the performance of simplified machine-learning models for major cardiac events and mortality within 30 days after noncardiac surgery in patients with kidney failure in Alberta and Manitoba, Canada. STUDY DESIGN: Data from Manitoba was split into training (70%), validation (15%), and testing (15%) sets. The training set was used for hyperparameter tuning and model training, the validation set for feature selection and evaluating model performance, and the testing set for final model performance. External evaluation was performed in a cohort from Alberta. SETTING & PARTICIPANTS: We included Manitoban adults (≥18 years) with kidney failure (eGFR < 15 mL/min/1.73 m2 or on maintenance dialysis) undergoing noncardiac surgery (2007-2019), with evaluation data on adults from Alberta (2005-2019). PREDICTORS: Variables included sex, age, surgery type and setting, kidney failure type, chronic conditions, and preoperative laboratory values (albumin and hemoglobin). OUTCOME: Composite of acute myocardial infarction, cardiac arrest, ventricular arrhythmia, and all-cause mortality within 30 days of surgery. ANALYTICAL APPROACH: Model performance was evaluated using area under the receiver operating characteristic curve (AUC-ROC), area under the precision-recall curve (AUC-PR), and calibration. The final XGBoost and random forest models were externally validated using Alberta data. RESULTS: Among 4,175 participants (12,082 surgeries), 569 outcomes (5%) were observed. The parsimonious XGBoost model (8 features) showed an AUC-ROC of 0.861 and AUC-PR of 0.304, and the parsimonious random forest model (19 features) estimated an AUC-ROC of 0.863 and AUC-PR of 0.332 in the testing cohort. External validation in Alberta showed similar performance with good calibration. LIMITATIONS: Lack of external validation outside Canada. CONCLUSIONS: Our machine learning models were accurate and had improved parsimony over existing regression-based tools. Future work should test these models in other populations and compare them with regression-based models, in addition to assessing the value of these tools for informing risk-guided perioperative care. PLAIN-LANGUAGE SUMMARY: People with kidney failure face high risks of cardiovascular problems and death after noncardiac surgery, but the current tools to predict these risks do not work well. This study developed new machine learning-based risk prediction models to help identify which patients are at higher risk after having noncardiac surgery. The models used a small number of easily available variables such as type of surgery, surgery setting, and laboratory results. We tested the models by using data from 2 Canadian provinces and found them to be accurate and reliable. These models may allow clinicians to inform patients of their individualized risk, which may support shared perioperative decision making. More research is needed to see how they perform in other geographic locations and health care systems.
引用
- Pabla GS, Harrison TG, Ferguson T, et al. Development and Evaluation of Machine Learning Models to Predict the Risk of Major Cardiac Events and Death for People With Kidney Failure Having Non-Cardiac Surgery. Am J Kidney Dis. 2025. PMID: 40967556. doi:10.1053/j.ajkd.2025.07.006
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。