为糖尿病合并房颤患者开发可解释的重症监护死亡预测模型
Clinically Interpretable Mortality Prediction for ICU Patients with Diabetes and Atrial Fibrillation: A Machine Learning Approach
- 基于早期临床数据，用两阶段特征选择提取19个可解释变量
- 逻辑回归模型表现最优，28天死亡预测准确率（AUROC）达0.825
- 结果可直观解读，适合临床医生用于重症患者早期分诊
糖尿病和房颤患者在重症监护病房中死亡风险更高，但针对该高危人群的预测模型仍有限。本研究基于MIMIC-IV数据库中1,535名成年糖尿病合并房颤患者，利用早期临床数据构建可解释机器学习模型，以预测28天死亡率。通过中位数/众数填补、z-score标准化及早期时序特征工程进行数据预处理。采用单变量筛选（ANOVA F检验）与随机森林多变量排序的两步特征选择流程，最终选出19个可解释特征。在分层5折交叉验证下，结合SMOTE过采样训练七种机器学习模型。通过消融实验和累积局部效应（ALE）分析评估模型可解释性。结果显示，逻辑回归模型表现最佳，AUROC为0.825（95%置信区间：0.779–0.867），优于更复杂的模型。关键预测因子包括肾素-血管紧张素系统（RAS）状态、年龄、胆红素水平和气管拔管情况。ALE图揭示了年龄相关的风险加速效应及胆红素阈值效应等直观非线性关系。结论表明，该可解释模型能提供准确的风险预测与临床洞察，适用于糖尿病合并房颤患者的早期重症监护分诊。
原文摘要 · Abstract (English)
Background: Patients with both diabetes mellitus (DM) and atrial fibrillation (AF) face elevated mortality in intensive care units (ICUs), yet models targeting this high-risk group remain limited. Objective: To develop an interpretable machine learning (ML) model predicting 28-day mortality in ICU patients with concurrent DM and AF using early-phase clinical data. Methods: A retrospective cohort of 1,535 adult ICU patients with DM and AF was extracted from the MIMIC-IV database. Data preprocessing involved median/mode imputation, z-score normalization, and early temporal feature engineering. A two-step feature selection pipeline-univariate filtering (ANOVA F-test) and Random Forest-based multivariate ranking-yielded 19 interpretable features. Seven ML models were trained with stratified 5-fold cross-validation and SMOTE oversampling. Interpretability was assessed via ablation and Accumulated Local Effects (ALE) analysis. Results: Logistic regression achieved the best performance (AUROC: 0.825; 95% CI: 0.779-0.867), surpassing more complex models. Key predictors included RAS, age, bilirubin, and extubation. ALE plots showed intuitive, non-linear effects such as age-related risk acceleration and bilirubin thresholds. Conclusion: This interpretable ML model offers accurate risk prediction and clinical insights for early ICU triage in patients with DM and AF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。