Metraipolis › archive › dc_489758353d77
Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction — arXiv:2608.04193
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04193
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:13:37.495Z
- SHA-256 of the archived text
67365d81c7c97fd9a425b38661622a9ed44c171250e313eacf962e1bdee89a16- Stable URL of this page
https://metraipolis.com/documento/dc_489758353d77
How to cite
Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction — arXiv:2608.04193 — arXiv (en), https://arxiv.org/abs/2608.04193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_489758353d77 (Metraipolis archive dc_489758353d77, sha256 67365d81c7c97fd9a425b38661622a9ed44c171250e313eacf962e1bdee89a16)
BibTeX
@misc{dc489758353d77,
title = {Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction — arXiv:2608.04193},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04193},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_489758353d77; sha256 67365d81c7c97fd9a425b38661622a9ed44c171250e313eacf962e1bdee89a16},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.04193 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:02:13.488Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).