Research map / Time series / Foundation models for time series
PathwayLLM: Explainable Clinical Trajectory Modeling with Structured Pathways for Sepsis Prediction
Zhengqiu Yu, Yueping Ding, Xiangrong Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add R-GCN graph encoder (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .854 -> .891 | Improved |
| add Temporal Encoder (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .869 -> .891 | Improved |
| add Pathway Encoder (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .882 -> .891 | Improved |
| add soft-token auxiliary embeddings (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .858 -> .891 | Improved |
| add layer injection of fused representation (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .884 -> .891 | Improved |
| four modality-specific soft tokens instead of a single token (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .879 -> .891 | Improved |
| add LLM stage (Stage 2) (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .867 -> .891 | Improved |
| add CT-LSTM trajectory aggregation (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .849 -> .891 | Improved |
| add Deterioration Attention (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .874 -> .891 | Improved |
| add synthetic reasoning supervision (ablation) | PathwayLLM · MIMIC-IV test | AUPRC: .584 -> .724 | Improved |
| add class-weighted loss (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .812 -> .891 | Improved |
| use LLaMA-3.1-8B instead of Qwen3-8B backbone (ablation) | PathwayLLM · MIMIC-IV test | AUROC: .891 -> .884 | Hurt |
Closest papers by meaning
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.86)
- SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes (ICML 2025 · similarity 0.84)
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.83)
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment (NeurIPS 2025 · similarity 0.83)
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models (NeurIPS 2026 · similarity 0.83)
- DDx-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
