用可解释的多模态模型提前预测重症患者死亡风险
Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution
- 融合生命体征与临床文本，用双模型分别处理
- 在MIMIC-III上AUPRC达0.565，优于单模型
- 每例患者都能看出体征和病历的贡献度
早期识别住院重症患者死亡风险有助于及时干预和高效资源配置。尽管现有机器学习方法表现优异，但缺乏透明性与鲁棒性，限制了临床应用。我们提出一种轻量级、可解释的多模态集成模型，融合患者入住ICU前48小时的生命体征时序数据与非结构化临床笔记。采用逻辑回归融合两个模态专用模型：用于体征的双向LSTM和用于笔记的微调ClinicalModernBERT Transformer。该可追溯架构支持多层次可解释性：每个模态内部特征归因，以及针对每例患者的模态贡献量化，明确体征与病历对决策的影响。在MIMIC-III基准上，该晚期融合集成模型在区分度上超越最优单模型（AUPRC 0.565 vs. 0.526；AUROC 0.891 vs. 0.876），同时保持良好校准性。当某一模态缺失时，系统仍通过校准退避机制维持稳健性能。结果表明，该模型兼具竞争力与可靠、可审计的风险评估能力，其透明且可预测的操作对临床落地至关重要。
原文摘要 · Abstract (English)
Early identification of intensive care patients at risk of in-hospital mortality enables timely intervention and efficient resource allocation. Despite high predictive performance, existing machine learning approaches lack transparency and robustness, limiting clinical adoption. We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay. A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes. This traceable architecture allows for multilevel interpretability: feature attributions within each modality and direct per-case modality attributions quantifying how vitals and notes influence each decision. On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model (AUPRC 0.565 vs. 0.526; AUROC 0.891 vs. 0.876) while maintaining well-calibrated predictions. The system remains robust through a calibrated fallback when a modality is missing. These results demonstrate competitive performance with reliable, auditable risk estimates and transparent, predictable operation, which together are crucial for clinical use.
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。