mlsanityData to 7 Oct 2026

CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study

arXiv 2608.02663 ↗First posted 1 Aug 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 33 references that are in the map. First posted on arXiv 1 Aug 2026.

Builds on

13 of 33 references.

References · 13

  1. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  2. 2017Multitask learning and benchmarking with clinical time series datacited by 287
  3. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  4. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  5. 2019Continuous Graph Neural Networkscited by 114
  6. 2021Predicting Patient Outcomes with Graph Representation Learningcited by 21
  7. 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
  8. 2024Predictive Modeling with Temporal Graphical Representation on Electronic Health Recordscited by 9
  9. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 8
  10. 2018Modeling Irregularly Sampled Clinical Time Seriescited by 5
  11. 2020Deep Learning with Heterogeneous Graph Embeddings for Mortality Prediction from Electronic Health Recordscited by 5
  12. 2024Time-aware Heterogeneous Graph Transformer with Adaptive Attention Merging for Health Event Predictioncited by 1
1 more
  1. 2024CIDER: Counterfactual-Invariant Diffusion-based GNN Explainer for Causal Subgraph Inferencecited by 1

Built on by

Not cited yet.