文献速递肝病

基于机器学习的全球前瞻性肝硬化住院患者死亡预测模型及外部验证

Enhancement of Inpatient Mortality Prognostication With Machine Learning in a Prospective Global Cohort of Patients With Cirrhosis With External Validation.
PubMed 文献 · Gastroenterology · 2025-07-23

研究利用全球前瞻性CLEARED队列中7239例肝硬化住院患者入院日数据,比较机器学习与逻辑回归对住院死亡的预测效能。随机森林模型AUROC最高(0.815),优于参数逻辑回归(0.774,P < .001)和LASSO模型(0.787,P = .004),并在28670例美国退伍军人住院患者中外部验证AUROC为0.859。

要点

  • 随机森林模型AUROC 0.815,优于逻辑回归(0.774)和LASSO(0.787),校准度高。
  • 按国家收入分层,随机森林仍优于逻辑回归:高收入国家AUROC 0.806,中高收入国家0.867,低/中低收入国家0.768。
  • 外部验证(美国退伍军人)AUROC 0.859,住院死亡率为4%(n = 1158)。

核心结论

  • 基于全球前瞻性肝硬化队列训练的随机森林模型优于传统逻辑回归方法,在不同国家收入水平间表现一致,并在美国退伍军人住院人群中成功完成外部验证。

研究设计与样本

  • 研究使用全球前瞻性慢性肝病演变与事件及失代偿登记(CLEARED)队列,纳入肝硬化住院患者,采用入院日数据预测住院死亡,比较机器学习方法与逻辑回归,并进行内部验证(75/25拆分)及按世界银行收入状态分层分析。

主要发现

  • CLEARED队列纳入来自全球115个中心的7239例肝硬化住院患者(64%为男性;平均[SD]年龄56[13]岁;终末期肝病模型-钠评分中位数=25),其中22.5%来自低/中低收入国家,41%来自中高收入国家,34%来自高收入国家;11.1%患者(n = 808)住院期间死亡。
  • 随机森林模型AUROC为0.815,校准度高,显著优于参数逻辑回归模型(AUROC 0.774;P < .001)和LASSO模型(AUROC 0.787;P = .004)。
  • 按国家收入分层,随机森林模型AUROC仍高于逻辑回归:高收入国家AUROC 0.806,中高收入国家AUROC 0.867,低/中低收入国家AUROC 0.768。
  • 外部验证在美国28670例退伍军人住院患者中进行(96%为男性,平均[SD]年龄67.8[10.3]岁,终末期肝病模型-钠评分中位数=15),住院死亡率为4%(n = 1158);CLEARED衍生随机森林模型AUROC为0.859。

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

BACKGROUND & AIMS: Cirrhosis is a major global burden requiring frequent hospitalizations and has high inpatient mortality. Traditional prognostic tools focused on inpatient mortality are affected by global disparities, which impacts timely management. We aimed to deploy machine learning (ML) approaches to enhance inpatient mortality prognostication. METHODS: Using the prospective Chronic Liver Disease Evolution and Registry for Events and Decompensation (CLEARED) cohort, which enrolled inpatients with cirrhosis globally, we used admission-day data to predict inpatient mortality with ML approaches vs logistic regression. Internal validation (75/25 split) and subdivision using World Bank income status (low/low-middle-income countries, upper-middle income countries, and high-income countries) were performed. The ML model with the best area under the receiver operating characteristic curve (AUROC) was externally validated in a US veteran inpatient population with cirrhosis. RESULTS: The CLEARED cohort included 7239 inpatients with cirrhosis (64% were men; mean [SD] age, 56 [13] years; median Model for End-Stage Liver Disease-Sodium score = 25) from 115 centers globally; 22.5% were from low/low-middle-income countries, 41% were from upper-middle-income countries, and 34% were from high-income countries; 11.1% of patients (n = 808) died in the hospital. Random forest (RF) showed the best AUROC (0.815) with high calibration, which was significantly better vs parametric logistic regression and LASSO models (AUROC, 0.774; P < .001 and AUROC, 0.787; P = .004, respectively). RF was the ML method with the highest AUROC and remained better than logistic regression, regardless of country income level (high-income countries: AUROC, 0.806; upper middle-income countries: AUROC, 0.867; and low/low-middle-income countries: AUROC, 0.768). External validation was performed in 28,670 veterans (96% were men, mean [SD] age, 67.8 [10.3] years, median Model for End-Stage Liver Disease-Sodium score = 15) with 4% (n = 1158) inpatient mortality. The AUROC using the CLEARED-derived RF model was 0.859. CONCLUSIONS: RF analysis trained on a global prospective cirrhosis cohort enhances mortality prediction over traditional methods, was consistent across country income levels, and was successfully validated externally in a US veteran population.

来源:Gastroenterology,查看原文。版权归原作者所有。

引用

  1. Silvey S, Kamath PS, George J, et al. Enhancement of Inpatient Mortality Prognostication With Machine Learning in a Prospective Global Cohort of Patients With Cirrhosis With External Validation. Gastroenterology. 2025. PMID: 40712932. doi:10.1053/j.gastro.2025.07.015

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。