Saved in:
Bibliographic Details
Main Authors: Rajamohan, Haresh Rengaraj, Gao, Xiang, Zhu, Weicheng, Huang, Shih-Lun, Chen, Long, Cho, Kyunghyun, Deniz, Cem M., Razavian, Narges
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.00574
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915367781138432
author Rajamohan, Haresh Rengaraj
Gao, Xiang
Zhu, Weicheng
Huang, Shih-Lun
Chen, Long
Cho, Kyunghyun
Deniz, Cem M.
Razavian, Narges
author_facet Rajamohan, Haresh Rengaraj
Gao, Xiang
Zhu, Weicheng
Huang, Shih-Lun
Chen, Long
Cho, Kyunghyun
Deniz, Cem M.
Razavian, Narges
contents Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Our model is evaluated via zero-shot prediction for forecasting dementia and knee osteoarthritis incidence within 2 and 5 years, and the model performance rivals a fully fine-tuned masked pretrained Transformer baseline, demonstrating that our approach captures complex clinical dependencies without requiring costly task-specific fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00574
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Foundation Models for Clinical Records at Health System Scale
Rajamohan, Haresh Rengaraj
Gao, Xiang
Zhu, Weicheng
Huang, Shih-Lun
Chen, Long
Cho, Kyunghyun
Deniz, Cem M.
Razavian, Narges
Machine Learning
Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Our model is evaluated via zero-shot prediction for forecasting dementia and knee osteoarthritis incidence within 2 and 5 years, and the model performance rivals a fully fine-tuned masked pretrained Transformer baseline, demonstrating that our approach captures complex clinical dependencies without requiring costly task-specific fine-tuning.
title Foundation Models for Clinical Records at Health System Scale
topic Machine Learning
url https://arxiv.org/abs/2507.00574