堆叠集成机器学习预测危重烧伤患者CRRT非计划性中断
本研究为回顾性队列研究,纳入666例接受CRRT的危重烧伤患者,通过多因素logistic回归筛选12个独立相关变量并系统评估47种机器学习算法,构建整合bayesglm、fda、knn和naive_bayes的堆叠集成模型。时间验证队列中模型AUC达0.963、准确率0.943、灵敏度1.000、特异度0.896、Kappa 0.887,校准满意且临床净获益显著。SHAP分析显示血流量、抗凝策略、红细胞压积、滤过分数等为重要预测贡献因素。
要点
- 堆叠集成模型在时间验证队列中AUC 0.963、灵敏度1.000、特异度0.896,区分度良好。
- 血流量、抗凝策略、红细胞压积和滤过分数是预测CRRT非计划性中断的重要贡献因素。
- 模型校准满意且在广泛阈值概率范围内具有显著临床净获益,可支持早期护理监测与个体化管理。
核心结论
- 可解释的堆叠集成模型对危重烧伤患者CRRT非计划性中断表现出稳健的区分度、校准度和临床实用性。
研究设计与样本
- 回顾性队列研究,纳入666例接受CRRT的危重烧伤患者,训练队列2015—2023年n=560,时间验证队列2024—2026年n=106。
- 通过多因素logistic回归识别12个独立相关变量,并系统评估47种机器学习算法。
- 最终构建整合bayesglm、fda、knn和naive_bayes为基学习器的堆叠集成模型。
主要发现
- 时间验证队列中集成模型AUC为0.963,准确率0.943,灵敏度1.000,特异度0.896,Kappa为0.887。
- 模型校准满意,且在广泛阈值概率范围内具有显著临床净获益。
- 两级SHAP分析识别血流量、抗凝策略、红细胞压积、滤过分数及其他CRRT相关参数为预测的重要贡献因素。
临床怎么用
- 模型可支持烧伤重症监护环境中的早期护理监测、个体化CRRT管理和预防性干预,以减少非计划性中断。
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
Unplanned interruption of continuous renal replacement therapy (CRRT) is a frequent complication in critically ill burn patients that may compromise therapeutic efficacy and clinical outcomes, yet accurate risk identification remains challenging due to complex interactions among patient characteristics, coagulation status, and treatment parameters. In this retrospective cohort study of 666 critically ill burn patients undergoing CRRT (training cohort 2015-2023, n=560; temporal validation cohort 2024-2026, n=106), we identified 12 independently associated variables through multivariate logistic regression and systematically evaluated 47 machine learning algorithms, ultimately constructing a stacking ensemble model integrating bayesglm, fda, knn, and naive_bayes as base learners. In the temporal validation cohort, the ensemble model achieved an AUC of 0.963, accuracy of 0.943, sensitivity of 1.000, specificity of 0.896, and a Kappa of 0.887, with satisfactory calibration and significant clinical net benefit across a wide range of threshold probabilities. Two-level SHAP analysis identified blood flow rate, anticoagulation strategy, hematocrit, filtration fraction, and other CRRT-related parameters as substantial contributors to prediction. This interpretable ensemble model demonstrates robust discrimination, calibration, and clinical utility, and may support early nursing surveillance, individualized CRRT management, and preventive interventions to reduce unplanned interruptions in burn intensive care settings.
引用
- Li T, Liu H, Chu Z, et al. Predicting unplanned CRRT interruptions in critically Ill burn patients using stacked ensemble machine learning framework. J Burn Care Res. 2026. PMID: 42730639. doi:10.1093/jbcr/irag163
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。