Metraipolis › archive › dc_cae0c62ec288
Federated generative event models for tokenized electronic health records — arXiv:2608.02939
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02939
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:32:29.272Z
- SHA-256 of the archived text
390e162db862d4e26d15fbe50c09ab2783afe7cfeeb791c6e8bb5b554f664479- Stable URL of this page
https://metraipolis.com/documento/dc_cae0c62ec288
How to cite
Federated generative event models for tokenized electronic health records — arXiv:2608.02939 — arXiv (en), https://arxiv.org/abs/2608.02939 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cae0c62ec288 (Metraipolis archive dc_cae0c62ec288, sha256 390e162db862d4e26d15fbe50c09ab2783afe7cfeeb791c6e8bb5b554f664479)
BibTeX
@misc{dccae0c62ec288,
title = {Federated generative event models for tokenized electronic health records — arXiv:2608.02939},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02939},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cae0c62ec288; sha256 390e162db862d4e26d15fbe50c09ab2783afe7cfeeb791c6e8bb5b554f664479},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02939. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Electronic health record foundation models are limited by institutionally siloed data and substantial performance degradation under cross-site transfer. We evaluated federated training of tokenized generative event models (GEMs) across 122,251 intensive care hospitalizations from three independent health systems harmonized to the Common Longitudinal ICU Data Format. Models were assessed on 12 post-24-hour clinical prediction tasks using within-site, cross-site, centralized, and federated training configurations. GEMs achieved the highest mean within-site and cross-site ROC-AUC and were substantially more transportable than conventional supervised models: their average cross-site penalties were 0.025 ROC-AUC and 0.027 PR-AUC, compared with 0.079 and 0.089 for LightGBM. Federated Learning (FedAvg and FedAvgM) approached the performance of centralized GEM training, with most gains obtained within 5-10 communication rounds. However, centralized multi-site training provided only modest improvements over complete local training. Multi-site models were most useful when local training data were limited, with their advantage narrowing as institutional data accumulated. These findings show that federated GEM training is technically feasible and preserves most centralized performance, but that the main open challenge is learning transportable representations to translate larger, but heterogeneous data from multiple health systems into a reliable target-site benefit. Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CY). Categorie arXiv: Machine Learning (cs.LG) ; Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2608.02939 — 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 2026-10-31T12:19:59.097Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).