arXiv：cs.AI· Xinyu Wang, Yixuan Li, Hanwei Wu, Qincheng Lu, Chi-Kuang Yeh, Xiao-Wen Chang, Ziyang Song·· 6 小时前
Patients-like-me：可解释临床预测的变分 LM-GNN 框架
Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
AI 导读
研究提出 Patients-like-me（PLM）统一 LM-GNN 框架，将局部患者语义与全局队列结构结合，并用变分期望最大化算法交替更新 LM 与 GNN。
正文
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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.04193 [cs.CL] |
| (or arXiv:2608.04193v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.04193 arXiv-issued DOI via DataCite |
Submission history
From: Ziyang Song [view email]
[v1]
Tue, 4 Aug 2026 19:51:52 UTC (10,087 KB)
[v2]
Mon, 12 Oct 2026 00:07:32 UTC (9,504 KB)
来源：arXiv：cs.AI · arxiv.org