建模病历中文本与诊断码的因果关系，提升临床风险预测准确性
THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction
- 构建多模态因果图，捕捉文本与诊断码间的时序和层级因果关系
- 在MIMIC-III/IV数据集上，对多种疾病编码的预测性能优于现有方法
- 适用于需要高可靠性风险预测的医疗场景，如重症监护决策支持
从电子健康记录（EHR）中实现自动化临床风险预测，需同时建模结构化的诊断代码与非结构化的病历文本。然而，以往方法大多将两类信息分开处理，或采用简单融合策略，忽略了文本观察引发诊断、风险跨住院期传播的定向层级因果关系。本文提出THCM-CAL：一种带合取校准的时间-层级因果模型。该框架构建了一个多模态因果图，节点来自两类信息：从病历文本中提取的语义命题，以及映射到文本描述的ICD代码。通过层级因果发现，模型推断出三类临床合理的交互：同时间片内同模态序列关系、同时间片内跨模态触发关系、跨时间片的风险传播关系。为提升预测可靠性，我们将合取预测扩展至多标签ICD编码，校准复杂共现下的每类编码置信区间。在MIMIC-III和MIMIC-IV数据集上的实验表明，THCM-CAL表现更优。
原文摘要 · Abstract (English)
Automated clinical risk prediction from electronic health records (EHRs) demands modeling both structured diagnostic codes and unstructured narrative notes. However, most prior approaches either handle these modalities separately or rely on simplistic fusion strategies that ignore the directional, hierarchical causal interactions by which narrative observations precipitate diagnoses and propagate risk across admissions. In this paper, we propose THCM-CAL, a Temporal-Hierarchical Causal Model with Conformal Calibration. Our framework constructs a multimodal causal graph where nodes represent clinical entities from two modalities: Textual propositions extracted from notes and ICD codes mapped to textual descriptions. Through hierarchical causal discovery, THCM-CAL infers three clinically grounded interactions: intra-slice same-modality sequencing, intra-slice cross-modality triggers, and inter-slice risk propagation. To enhance prediction reliability, we extend conformal prediction to multi-label ICD coding, calibrating per-code confidence intervals under complex co-occurrences. Experimental results on MIMIC-III and MIMIC-IV demonstrate the superiority of THCM-CAL.
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。