重症成人肌酐清除率预测机器学习模型的开发与验证
研究利用EPaNIC多中心随机对照试验数据库中2825例患者数据,用梯度提升机(GBM)算法开发三种预测次日肌酐清除率(CrCl)的模型:Core模型(人口学、入院诊断、每日实验室结果)、Core+BGA模型(增加血气分析)、Core+BGA+Monitoring模型(增加高分辨率监测数据),并在鲁汶大学医院M@tric数据库9576例患者中外部验证。外部验证队列中,以预测日当日CrCl代替次日值的参考方法MAE为20.6(95%CI 20.3-20.9)ml/min、RMSE为40.1(95%CI 37.9-42.3)ml/min;RMSE最小的Core+BGA+Monitoring模型MAE为18.1(95%CI 17.9-18.3)ml/min、RMSE为28.9(95%CI 28-29.7)ml/min。三种模型预测误差均小于参考方法。作者认为这些模型可能有助于亲水性药物剂量调整或患者风险分层。
要点
- 在9576例外部验证队列中,Core+BGA+Monitoring模型预测次日CrCl的MAE为18.1(95%CI 17.9-18.3)ml/min、RMSE为28.9(95%CI 28-29.7)ml/min。
- 以当日CrCl代替次日值的参考方法在外部验证队列中MAE为20.6(95%CI 20.3-20.9)ml/min、RMSE为40.1(95%CI 37.9-42.3)ml/min。
- 三种开发模型(Core、Core+BGA、Core+BGA+Monitoring)的预测误差均小于参考方法。
- 模型开发基于EPaNIC多中心随机对照试验数据库的2825例患者,外部验证基于鲁汶大学医院M@tric数据库的9576例患者。
- 作者认为这些基于ICU常规收集数据的模型可能有助于亲水性药物剂量调整或患者风险分层。
适用人群与场景
- 开发队列:EPaNIC多中心随机对照试验数据库中的2825例重症成人患者。
- 外部验证队列:鲁汶大学医院M@tric数据库中的9576例重症成人患者。
研究设计与关键结果
- 研究类型:预测模型开发与外部验证研究;开发队列2825例(EPaNIC多中心随机对照试验数据库),外部验证队列9576例(鲁汶大学医院M@tric数据库)。
- 干预/方法:采用梯度提升机(GBM)机器学习算法开发三种预测次日CrCl的模型:Core模型基于人口学、入院诊断和每日实验室结果;Core+BGA模型增加血气分析结果;Core+BGA+Monitoring模型增加高分辨率监测数据;以平均绝对误差(MAE)和均方根误差(RMSE)对照实际CrCl评价模型性能。
- 主要终点结果:外部验证队列中,以预测日当日CrCl代替次日值的参考方法MAE为20.6(95%CI 20.3-20.9)ml/min、RMSE为40.1(95%CI 37.9-42.3)ml/min;RMSE最小的Core+BGA+Monitoring模型MAE为18.1(95%CI 17.9-18.3)ml/min、RMSE为28.9(95%CI 28-29.7)ml/min。
- 关键次要终点:三种开发模型的预测误差均小于参考方法。
证据类型、等级与局限
- 证据类型:预测模型开发与外部验证研究(基于EPaNIC多中心随机对照试验数据库开发,在鲁汶大学医院M@tric数据库外部验证)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,基于ICU常规收集临床数据的预测模型能够较准确预测次日CrCl,可能有助于亲水性药物剂量调整或患者风险分层。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: In critically ill patients, measured creatinine clearance (CrCl) is the most reliable method to evaluate glomerular filtration rate in routine clinical practice and may vary subsequently on a day-to-day basis. We developed and externally validated models to predict CrCl one day ahead and compared them with a reference reflecting current clinical practice.
METHODS: A gradient boosting method (GBM) machine-learning algorithm was used to develop the models on data from 2825 patients from the EPaNIC multicenter randomized controlled trial database. We externally validated the models on 9576 patients from the University Hospitals Leuven, included in the M@tric database. Three models were developed: a "Core" model based on demographic, admission diagnosis, and daily laboratory results; a "Core + BGA" model adding blood gas analysis results; and a "Core + BGA + Monitoring" model also including high-resolution monitoring data. Model performance was evaluated against the actual CrCl by mean absolute error (MAE) and root-mean-square error (RMSE).
RESULTS: All three developed models showed smaller prediction errors than the reference. Assuming the same CrCl of the day of prediction showed 20.6 (95% CI 20.3-20.9) ml/min MAE and 40.1 (95% CI 37.9-42.3) ml/min RMSE in the external validation cohort, while the developed model having the smallest RMSE (the Core + BGA + Monitoring model) had 18.1 (95% CI 17.9-18.3) ml/min MAE and 28.9 (95% CI 28-29.7) ml/min RMSE.
CONCLUSIONS: Prediction models based on routinely collected clinical data in the ICU were able to accurately predict next-day CrCl. These models could be useful for hydrophilic drug dosage adjustment or stratification of patients at risk.
TRIAL REGISTRATION: Not applicable.
参考来源
- Huang CY, Güiza F, Wouters P, et al. Development and validation of the creatinine clearance predictor machine learning models in critically ill adults. Crit Care. 2023. PMID: 37415234. doi:10.1186/s13054-023-04553-z
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。