跳到正文
原文
Nature 健康护理主题·· 2026-10-08AI 评分58

EpiScreen 利用大语言模型从电子健康记录中实现癫痫早期检测

Early epilepsy detection from electronic health records with large language models

AI 导读

EpiScreen 通过微调大语言模型分析电子健康记录中的临床笔记,在 MIMIC-IV 数据集上 AUC 达 0.875,在明尼苏达大学私有队列上达 0.980。在人机协作场景中,使用该工具的神经科医师比未使用工具的专家诊断准确性高出最多 14.3%。研究认为该方法有助于在资源受限地区降低癫痫诊断延迟并避免不必要治疗。

正文

npj Digital Medicine (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

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 14.3%. 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.

Acknowledgements

The Center for Learning Health System Sciences at the University of Minnesota supported this study.

Funding

This work received financial support from the National Institutes of Health, including the National Center for Complementary and Integrative Health (R01AT009457), the National Institute on Aging (R01AG078154), and the National Cancer Institute (R01CA287413). The content of this article represents the authors’ perspectives and does not necessarily reflect the official views of the NIH.

Author information

Authors and Affiliations

  1. Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, MN, USA

    Shuang Zhou, Kai Yu, Huixue Zhou, Min Zeng, Feng Xie & Rui Zhang

  2. College of Science and Engineering, University of Minnesota, Minneapolis, MN, USA

    Zaifu Zhan

  3. Department of Neurology, University of Minnesota, Minneapolis, MN, USA

    Zhiyi Sha

Authors

  1. Shuang Zhou
  2. Kai Yu
  3. Zaifu Zhan
  4. Huixue Zhou
  5. Min Zeng
  6. Feng Xie
  7. Zhiyi Sha
  8. Rui Zhang

Corresponding author

Correspondence to Rui Zhang.

Ethics declarations

Competing interests

Rui Zhang is Associate Editor of npj Digital Medicine. Rui Zhang was not involved in the journal’s review of, or decisions related to, this manuscript. The other authors declare no competing financial or non-financial interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, S., Yu, K., Zhan, Z. et al. Early epilepsy detection from electronic health records with large language models. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03346-2

Download citation

  • Received: 23 March 2026

  • Accepted: 20 September 2026

  • Published: 08 October 2026

  • DOI: https://doi.org/10.1038/s41746-026-03346-2

来源:Nature 健康护理主题 · nature.com