Search papers, labs, and topics across Lattice.
This paper introduces Patients-like-me (PLM), a novel framework that combines language models (LMs) and graph neural networks (GNNs) to enhance explainability in clinical predictions by integrating local patient semantics with global cohort structures. The authors employ a Variational Expectation-Maximization algorithm to efficiently alternate updates between the LM and GNN, resulting in significant performance improvements on clinical datasets MIMIC-III and MIMIC-IV. Notably, PLM not only outperforms existing methods but also provides interpretable reference-patient explanations, demonstrating the importance of inter-patient relationships in clinical predictions.
PLM achieves superior clinical prediction accuracy while offering interpretable insights through reference-patient explanations, highlighting the critical role of patient interrelationships.
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.
