提出可解释的时序脓毒症预测框架，兼顾高精度与临床可读性。
Temporal Sepsis Modeling: a Relational and Explainable-by-Design Framework
- 用关系建模将电子病历转为可读特征，再用选择性分数朴素贝叶斯分类
- 在MIMIC-III上达AUC 0.983，仅用98个变量，模型仅1MB大小
- 原生四重可解释性，适合临床决策支持系统开发
脓毒症是重症监护中最为复杂且异质的综合征之一。尽管深度学习模型在早期脓毒症预测中表现优异，但其决策过程往往难以临床解读，可解释性通常依赖事后方法。本文提出一种基于关系建模的原生可解释性框架：将时序电子病历数据以关系模式表示，通过基于最小描述长度（MDL）的命题化转换为紧凑的人类可读特征，并使用选择性分数朴素贝叶斯分类器进行分类。在MIMIC-III数据集（3,940名患者，10折交叉验证）上，该方法取得AUC = 0.983，性能媲美XGBoost（0.985）和CatBoost（0.985），优于LSTM（0.945），仅需98个变量，模型体积仅为1 MB。与事后解释方法不同，本框架天然具备四重可解释性：单变量、全局、局部和反事实解释。
原文摘要 · Abstract (English)
Sepsis remains one of the most complex and heterogeneous syndromes in intensive care. While deep learning models achieve competitive performance in early sepsis prediction, their decision processes often remain difficult to interpret clinically, and explainability is typically added only through post-hoc methods. We propose an explainable-by-design framework based on a relational approach: temporal EHR data are represented in a relational schema, flattened via MDL-based propositionalisation into compact human-readable features, and classified using a selective Fractional Naive Bayes classifier. Evaluated on MIMIC-III (3,940 patients, 10-fold cross-validation), our approach achieves AUC = 0.983 - competitive with XGBoost (0.985) and CatBoost (0.985), and superior to LSTM (0.945) - with only 98 selected variables and a 1 MB model footprint. Unlike post-hoc methods, interpretability is native and fourfold: univariate, global, local, and counterfactual.
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。