用带时间戳的异构图建模重症患者数据，提升死亡预测准确率。
CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study
- 构建连续时间异构医疗图，融合时序与类型信息，无需插补
- 模型在MIMIC-IV上达到0.8618的AUROC，反向边对性能至关重要
- 适合需要高精度危重病预测的研究者和临床决策支持系统
精准的ICU死亡预测需建模异构实体类型的不规则临床观测。现有序列模型处理不规则采样但忽略类型关系；现有图模型假设固定间隔输入。本文提出连续时间异构电子病历图（CT-HEG）架构，在MIMIC-IV v3.1数据集（31,142例ICU住院，持续时间≥48小时，死亡率13.4%）上评估不同架构选择对性能的影响。CT-HEG将每例ICU住院表示为带类型和时间戳的图，包含三类节点（就诊、生命体征、检验事件）及二维边属性（t_hours/48, value_norm），编码时间与数值信息而无需插补。基于此构建CHIRP-Net，一个四层异构GATv2Conv网络，对比逻辑回归、mTAND、Transformer、GRU-D，并进行消融研究。五次种子实验下，单模型平均AUROC为0.8449±0.0071（AUPRC 0.4958±0.0209），集成模型达AUROC 0.8618（95%置信区间：0.8485–0.8745）。移除反向边导致AUROC下降0.1968±0.0073；时间注意力边特征贡献0.0247±0.0093的AUROC提升。将异构边类型合并为单一关系（参数减少7倍）反而在所有种子上表现更优。后校准后ECE为0.0307。临时与人口统计子群分析待后续工作。双向连接对模型有效利用输入至关重要，经验证集温度缩放后模型校准良好。结果支持CT-HEG用于不规则电子病历数据，但外部验证、预设时间评估与公平性审计仍需完成以确认稳健性。
原文摘要 · Abstract (English)
Accurate ICU mortality prediction requires modeling irregular clinical observations across heterogeneous entity types. Existing sequence models handle irregular sampling but ignore typed relational structure; existing graph models assume fixed-interval inputs. We introduce the Continuous-Time Heterogeneous EHR Graph (CT-HEG) schema and evaluate which architectural choices drive predictive performance. CT-HEG encodes each ICU stay as a typed, timestamped graph with three node types (visit, vital, lab_event) and 2D edge attributes (t_hours/48, value_norm) encoding timing and value without imputation. We instantiate CT-HEG as CHIRP-Net, a four-layer heterogeneous GATv2Conv network, evaluated on MIMIC-IV v3.1 (31,142 ICU stays, LOS>=48h, 13.4% mortality) with five seeds and bootstrapped confidence intervals, against logistic regression, mTAND, a Transformer, and GRU-D, plus an ablation study. CHIRP-Net achieved 5-seed mean AUROC 0.8449+/-0.0071 (AUPRC 0.4958+/-0.0209); the ensemble achieved AUROC 0.8618 (95% CI: 0.8485-0.8745). Removing reverse edges disconnected observation nodes from the visit readout, cutting AUROC by 0.1968+/-0.0073. Time-attentive edge features contributed 0.0247+/-0.0093 AUROC. Collapsing heterogeneous edge types into one relation (7x fewer parameters) outperformed the full model on all seeds. Post-calibration ECE was 0.0307. Temporal and demographic subgroup analyses were explored but not reported here, pending follow-up work. Bidirectional connectivity was necessary for the model to use its inputs at all, and CT-HEG was reasonably well calibrated after validation-fitted temperature scaling. These results support CT-HEG for irregular EHR data, while external validation, a pre-specified temporal evaluation, and a demographic fairness audit remain necessary before any claim of robustness. Code: https://github.com/nasiruddinstudents-ctrl/chirp-net-mimic-iv.
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。