EpiScreen: Early Epilepsy Detection from Electronic Health Records with Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912989308780544 |
|---|---|
| author | Zhou, Shuang Yu, Kai Zhan, Zaifu Zhou, Huixue Zeng, Min Xie, Feng Sha, Zhiyi Zhang, Rui |
| author_facet | Zhou, Shuang Yu, Kai Zhan, Zaifu Zhou, Huixue Zeng, Min Xie, Feng Sha, Zhiyi Zhang, Rui |
| contents | Epilepsy and psychogenic non-epileptic seizures often present with similar seizure-like manifestations but require fundamentally different management strategies. Misdiagnosis is common and can lead to prolonged diagnostic delays, unnecessary treatments, and substantial patient morbidity. Although prolonged video-electroencephalography is the diagnostic gold standard, its high cost and limited accessibility hinder timely diagnosis. Here, we developed a low-cost, effective approach, EpiScreen, for early epilepsy detection by utilizing routinely collected clinical notes from electronic health records. Through fine-tuning large language models on labeled notes, EpiScreen achieved an AUC of up to 0.875 on the MIMIC-IV dataset and 0.980 on a private cohort of the University of Minnesota. In a clinician-AI collaboration setting, EpiScreen-assisted neurologists outperformed unaided experts by up to 10.9%. Overall, this study demonstrates that EpiScreen supports early epilepsy detection, facilitating timely and cost-effective screening that may reduce diagnostic delays and avoid unnecessary interventions, particularly in resource-limited regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28698 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EpiScreen: Early Epilepsy Detection from Electronic Health Records with Large Language Models Zhou, Shuang Yu, Kai Zhan, Zaifu Zhou, Huixue Zeng, Min Xie, Feng Sha, Zhiyi Zhang, Rui Computation and Language Epilepsy and psychogenic non-epileptic seizures often present with similar seizure-like manifestations but require fundamentally different management strategies. Misdiagnosis is common and can lead to prolonged diagnostic delays, unnecessary treatments, and substantial patient morbidity. Although prolonged video-electroencephalography is the diagnostic gold standard, its high cost and limited accessibility hinder timely diagnosis. Here, we developed a low-cost, effective approach, EpiScreen, for early epilepsy detection by utilizing routinely collected clinical notes from electronic health records. Through fine-tuning large language models on labeled notes, EpiScreen achieved an AUC of up to 0.875 on the MIMIC-IV dataset and 0.980 on a private cohort of the University of Minnesota. In a clinician-AI collaboration setting, EpiScreen-assisted neurologists outperformed unaided experts by up to 10.9%. Overall, this study demonstrates that EpiScreen supports early epilepsy detection, facilitating timely and cost-effective screening that may reduce diagnostic delays and avoid unnecessary interventions, particularly in resource-limited regions. |
| title | EpiScreen: Early Epilepsy Detection from Electronic Health Records with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.28698 |