Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
cs.CL, cs.AI
Submitted: 2026-08-04
Updated: 2026-10-12
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability.
Terminology
Abstract
Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability. Graph neural networks (GNNs) complement LMs by incorporating inter-patient relationships and enabling reference-patient attribution, yet they rely on high-quality patient representations. We propose Patients-like-me (PLM), a unified LM--GNN framework that integrates local patient semantics with global cohort structure. To train PLM efficiently, we introduce a Variational Expectation-Maximization algorithm that alternates LM and GNN updates under a supervised variational objective. Extensive experiments on MIMIC-III and MIMIC-IV show that PLM consistently outperforms state-of-the-art methods, with improvements generalizing across encoder-only and decoder-only LM backbones. These gains are achieved with only modest additional computational overhead. PLM also provides reference-patient explanations by retrieving influential similar patients, while edge-masking experiments confirm that the highest-ranked references have the greatest impact on model predictions.
Sources
- Leveraging graph neural networks for supporting Automatic Triage of Patients
- Large Language Models are Powerful Electronic Health Record Encoders
- ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
- Auto-Encoding Variational Bayes
- Large Language Model Distilling Medication Recommendation Model
- Predicting Patient Outcomes with Graph Representation Learning
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering