多中心机器学习预测低钙血症ICU患者死亡率
研究整合MIMIC-III、MIMIC-IV及中国两家三级甲等医院数据,构建13,979例成人ICU低钙血症(血清总钙<2.12 mmol/L)多中心队列。MIMIC-IV随机分为训练集(n=7,749)和内部验证集(n=1,550),外部验证采用MIMIC-III(n=4,771)和中国多中心数据集(n=209)。LASSO筛选出20个预测变量,XGBoost判别力最高(AUC=0.914;F1=0.844),优于逻辑回归(AUC=0.896;F1=0.829)、LightGBM(AUC=0.909;F1=0.816)及传统ICU评分。校准曲线、决策曲线分析和临床影响曲线在内外验证队列中均证实性能一致且净获益更优。
要点
- 在13,979例成人ICU低钙血症(血清总钙<2.12 mmol/L)患者中,XGBoost模型预测院内死亡的AUC为0.914、F1为0.844,优于逻辑回归(AUC=0.896;F1=0.829)和LightGBM(AUC=0.909;F1=0.816),并优于传统ICU评分。
- LASSO回归保留20个预测变量,SHAP分析显示无创呼吸机使用和住院时长是最具影响力的预测因子。
- 校准曲线、决策曲线分析和临床影响曲线在内部验证(MIMIC-IV,n=1,550)及外部验证(MIMIC-III,n=4,771;中国多中心数据集,n=209)中均表现一致且净获益更优。
- 模型已部署为公开网页应用,可实时提供患者个体化风险估计,辅助ICU早期关键窗口的数据驱动临床决策。
适用人群与场景
- 成人ICU患者,血清总钙<2.12 mmol/L;数据来源于MIMIC-III、MIMIC-IV及中国两家三级甲等医院,共13,979例ICU入住记录。
诊断标准与关键阈值
- 低钙血症定义:血清总钙<2.12 mmol/L。
研究设计与关键结果
- 研究类型为多中心回顾性队列建模研究,整合MIMIC-III、MIMIC-IV及中国两家三级甲等医院数据,共13,979例成人ICU低钙血症(血清总钙<2.12 mmol/L)患者。
- MIMIC-IV随机分为训练集(n=7,749)和内部验证集(n=1,550);外部验证采用MIMIC-III(n=4,771)和中国多中心数据集(n=209)。
- LASSO回归保留20个预测变量,SHAP分析显示无创呼吸机使用(is_noninvasive_ventilator)和住院时长最具影响力。
- XGBoost判别力最高(AUC=0.914;F1=0.844),优于逻辑回归(AUC=0.896;F1=0.829)、LightGBM(AUC=0.909;F1=0.816)及传统ICU评分。
- 校准曲线、决策曲线分析和临床影响曲线在内部和外部验证队列中均证实性能一致且净获益更优。
- 模型已部署为公开网页应用,提供实时患者个体化风险估计。
证据类型、等级与局限
- 证据类型:多中心回顾性队列建模研究(整合MIMIC-III、MIMIC-IV及中国两家三级甲等医院数据)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,该可解释机器学习模型对低钙血症ICU患者院内死亡的预测比现有评分系统更准确,SHAP网页界面可提供实时个体化风险估计,促进ICU早期关键窗口的数据驱动临床决策。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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: Hypocalcemia occurs frequently in intensive care units (ICUs) and is independently associated with excess mortality. Conventional severity scores-such as APACHE II and SOFA-assign fixed weights to a limited set of variables and therefore fail to capture the nonlinear, high-dimensional physiology characteristic of hypocalcemic patients. Although machine learning (ML) approaches can enhance risk stratification, no interpretable model tailored to this cohort has been available.
METHODS: We harmonized de-identified data from MIMIC-III, MIMIC-IV, and two Grade III Level A hospitals in China, generating a multicenter cohort of 13,979 adult ICU admissions with total serum calcium <2.12 mmol L -1 . MIMIC-IV records were randomly divided into a training set (n = 7,749) and an internal validation set (n = 1,550). External validation employed MIMIC-III (n = 4,771) and the Chinese multicenter dataset (n = 209). Predictors were filtered with least absolute shrinkage and selection operator (LASSO) regression and applied to eight ML algorithms: logistic regression, k-nearest neighbors (KNN), support vector machine, decision tree, random forest, artificial neural network, eXtreme Gradient Boosting (XGBoost), and LightGBM. Model discrimination, calibration, and clinical utility were quantified using the area under the receiver operating characteristic curve (AUC), F1-score, sensitivity, specificity, calibration plots, decision curve analysis (DCA), and clinical impact curves (CIC). SHapley Additive exPlanations (SHAP) were used for interpretability, and the final model was deployed as a public web application.
RESULTS: LASSO retained 20 predictive variables; is_noninvasive_ventilator and hospital length of stay were the most influential in SHAP analysis. XGBoost provided the highest discrimination (AUC = 0.914; F1 = 0.844), surpassing logistic regression (AUC = 0.896; F1 = 0.829), LightGBM (AUC = 0.909; F1 = 0.816), and conventional ICU scores. Calibration curves, DCA, and CIC confirmed consistent performance and superior net benefit across internal and external validation cohorts.
CONCLUSIONS: We present and externally validate an interpretable, high-performance ML model that predicts in-hospital mortality in hypocalcemic ICU patients more accurately than established scoring systems. The SHAP-enabled web interface provides real-time, patient-specific risk estimates, facilitating data-driven clinical decisions within the early critical window of ICU care.
参考来源
- Xie L, Jiang L, Xiao M, et al. Multicenter Machine Learning-Based Prediction of Mortality in ICU Patients With Hypocalcemia. Shock. 2025. PMID: 40729554. doi:10.1097/SHK.0000000000002680
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。