Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.24562 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915945392373760 |
|---|---|
| author | Rajamohan, Haresh Rengaraj Gao, Xiang Zhu, Weicheng Huang, Shih-Lun Chen, Long Schulman, Gabe Jin, Huizhen Li, Shengduo Wang, Yixuan Yang, Huidi Cho, Kyunghyun Deniz, Cem M. Razavian, Narges |
| author_facet | Rajamohan, Haresh Rengaraj Gao, Xiang Zhu, Weicheng Huang, Shih-Lun Chen, Long Schulman, Gabe Jin, Huizhen Li, Shengduo Wang, Yixuan Yang, Huidi Cho, Kyunghyun Deniz, Cem M. Razavian, Narges |
| contents | While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present RAVEN, a novel generative pretraining strategy for sequential EHR data based on Recurrence-Aware next-Visit EveNt prediction. Leveraging a dataset of over one million unique individuals, our model learns to autoregressively generate tokenized clinical events for the next visit conditioned on patient history. 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. Furthermore, we empirically investigate the scaling behaviors in a data-constrained, compute-saturated regime, showing that simply increasing model size is suboptimal without commensurate increases in data volume. We evaluate our model via zero-shot prediction for forecasting the incidence of a diverse set of diseases, where it rivals fully fine-tuned representation-based Transformer models and outperforms both standard simulation-based next-token approaches and a prompted medical large language model baseline. Finally, without additional parameter updates, we show that RAVEN can generalize to an external patient cohort under lossy clinical code mappings and feature coverage gaps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24562 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction Rajamohan, Haresh Rengaraj Gao, Xiang Zhu, Weicheng Huang, Shih-Lun Chen, Long Schulman, Gabe Jin, Huizhen Li, Shengduo Wang, Yixuan Yang, Huidi Cho, Kyunghyun Deniz, Cem M. Razavian, Narges Machine Learning While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present RAVEN, a novel generative pretraining strategy for sequential EHR data based on Recurrence-Aware next-Visit EveNt prediction. Leveraging a dataset of over one million unique individuals, our model learns to autoregressively generate tokenized clinical events for the next visit conditioned on patient history. 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. Furthermore, we empirically investigate the scaling behaviors in a data-constrained, compute-saturated regime, showing that simply increasing model size is suboptimal without commensurate increases in data volume. We evaluate our model via zero-shot prediction for forecasting the incidence of a diverse set of diseases, where it rivals fully fine-tuned representation-based Transformer models and outperforms both standard simulation-based next-token approaches and a prompted medical large language model baseline. Finally, without additional parameter updates, we show that RAVEN can generalize to an external patient cohort under lossy clinical code mappings and feature coverage gaps. |
| title | Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.24562 |