用可解释的集成模型，精准预测中风患者住院时长
A SHAP-based explainable multi-level stacking ensemble learning method for predicting the length of stay in acute stroke
- 构建多层级堆叠集成模型，融合患者、临床与系统三类因素
- 缺血性中风预测AUC达0.824，显著优于传统模型
- 通过SHAP分析揭示关键影响因素，提升临床可解释性
急性中风患者住院时长（LOS）预测对优化护理规划至关重要。现有机器学习模型存在性能不足、泛化能力弱及忽略系统层面因素的问题。本研究通过优化预测变量并构建可解释的多层级堆叠集成模型，提升预测效率、性能与可解释性。数据来自澳大利亚每两年一次的中风基金会急性审计（2015、2017、2019、2021）。分别针对缺血性和出血性中风建模，结局为延长住院时长（高于75百分位数）。候选预测变量共89个（缺血性）和83个（出血性），分为患者、临床与系统三类。采用基于相关性的特征选择方法筛选关键变量。模型评估包括区分度（AUC）、校准曲线与可解释性（SHAP图）。缺血性中风（N=12,575）延长住院≥9天，出血性中风（N=1,970）≥11天。集成模型在缺血性中风中表现更优（AUC: 0.824，95% CI: 0.801–0.846），显著优于逻辑回归（AUC: 0.805，95% CI: 0.782–0.829；P=0.0004）。但在出血性中风中，模型（AUC: 0.843，95% CI: 0.790–0.895）未显著优于逻辑回归（AUC: 0.828，95% CI: 0.774–0.882；P=0.136）。SHAP分析识别出两类中风共有的关键预测因子：康复评估、尿失禁、卒中单元治疗、无法独立行走、物理治疗及卒中护理协调员参与。该可解释集成模型有效预测缺血性中风患者的延长住院时长，出血性中风需更大队列进一步验证。
原文摘要 · Abstract (English)
Length of stay (LOS) prediction in acute stroke is critical for improving care planning. Existing machine learning models have shown suboptimal predictive performance, limited generalisability, and have overlooked system-level factors. We aimed to enhance model efficiency, performance, and interpretability by refining predictors and developing an interpretable multi-level stacking ensemble model. Data were accessed from the biennial Stroke Foundation Acute Audit (2015, 2017, 2019, 2021) in Australia. Models were developed for ischaemic and haemorrhagic stroke separately. The outcome was prolonged LOS (the LOS above the 75th percentile). Candidate predictors (ischaemic: n=89; haemorrhagic: n=83) were categorised into patient, clinical, and system domains. Feature selection with correlation-based approaches was used to refine key predictors. The evaluation of models included discrimination (AUC), calibration curves, and interpretability (SHAP plots). In ischaemic stroke (N=12,575), prolonged LOS was >=9 days, compared to >=11 days in haemorrhagic stroke (N=1,970). The ensemble model achieved superior performance [AUC: 0.824 (95% CI: 0.801-0.846)] and statistically outperformed logistic regression [AUC: 0.805 (95% CI: 0.782-0.829); P=0.0004] for ischaemic. However, the model [AUC: 0.843 (95% CI: 0.790-0.895)] did not statistically outperform logistic regression [AUC: 0.828 (95% CI: 0.774-0.882); P=0.136] for haemorrhagic. SHAP analysis identified shared predictors for both types of stroke: rehabilitation assessment, urinary incontinence, stroke unit care, inability to walk independently, physiotherapy, and stroke care coordinators involvement. An explainable ensemble model effectively predicted the prolonged LOS in ischaemic stroke. Further validation in larger cohorts is needed for haemorrhagic stroke.
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。