癫痫领域适配大语言模型提升从发作表现预测致痫灶的准确性
Epilepsy domain adapted large language models enhance epileptogenic zone prediction from seizure semiology
该研究开发并评估了针对癫痫领域适配的大语言模型,用于基于癫痫发作表现(seizure semiology)预测致痫灶。论文发表于 Communications Medicine,DOI 为 10.1038/s43856-026-01883-1,由来自多所大学和医院的作者团队完成。
Acknowledgements
Author contributors
S.Y. drafted the initial manuscript. S.Y., YC.S., and YT.L. curated the dataset and developed the phenotype definitions. S.Y. and X.J. implemented the model, conducted coding, visualization, and platform deployment. S.Y., X.J., JE.D., X.X., Y.Z. and F.L. contributed to conceptualization and methodology review. YC.S., S.W., N.F., H.S., D.B., V.R.R., I.K., F.R., P.K., and YT.L. performed the evaluation. F.L., S.W., YT.L., and P.K. supervised the project. F.L. acquired funding. S.Y., X.X., YT.L., and F.L. accessed and verified the underlying data. All authors reviewed and revised the manuscript and approved the decision to submit for publication.
Funding
Mr. Shihao Yang, Mr. Jun-En Ding, Dr. Neel Fotedar, Dr. Xiaochen Xian, and Dr. Feng Liu’s efforts are partially supported by the National Institute of Neurological Disorders and Stroke of the National Institutes of Health, United States under Award Number R21NS135482 (PI: Liu). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Author information
Authors and Affiliations
Department of Industrial & Systems Engineering, Rutgers University, Piscataway, NJ, USA
Shihao Yang, Jun-En Ding & Feng Liu
Department of Systems Engineering, Stevens Institute of Technology, Hoboken, NJ, USA
Shihao Yang, Jun-En Ding & Feng Liu
Division of Epilepsy, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan
Yen-Cheng Shih & Yo-Tsen Liu
School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
Yen-Cheng Shih & Yo-Tsen Liu
Dixie L. Leavitt School of Business, Southern Utah University, Cedar City, UT, USA
Xinglong Ju
Department of Neurology, University of Chicago, Chicago, IL, USA
Shasha Wu
Department of Neurology, University Hospitals Cleveland Medical Center, School of Medicine, Case Western Reserve University, Cleveland, OH, USA
Neel Fotedar
Department of Neurosurgery, Rutgers Robert Wood Johnson Medical School, Rutgers University, New Brunswick, NJ, USA
Hai Sun
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA
Xiaochen Xian
Department of Neurology and Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, USA
Danilo Bernardo & Vikram R. Rao
Department of Neurology, Emory University, Atlanta, GA, USA
Ioannis Karakis
Department of Neurology, School of Medicine, University of Crete, Heraklion, Greece
Ioannis Karakis
Epilepsy Center Frankfurt Rhine-Main, Department of Neurology, Goethe University Frankfurt, Frankfurt am Main, Germany
Felix Rosenow
Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA
Yu Zhang
Wu Tsai Neurosciences Institute, Stanford University, Stanford, CA, USA
Yu Zhang
Stanford Institute for Human-Centered AI, Stanford, CA, USA
Yu Zhang
Department of Neuroscience, Monash University, Melbourne, VIC, Australia
Patrick Kwan
Authors
- Shihao Yang
- Yen-Cheng Shih
- Xinglong Ju
- Shasha Wu
- Neel Fotedar
- Hai Sun
- Xiaochen Xian
- Jun-En Ding
- Danilo Bernardo
- Vikram R. Rao
- Ioannis Karakis
- Felix Rosenow
- Yu Zhang
- Patrick Kwan
- Yo-Tsen Liu
- Feng Liu
Corresponding author
Correspondence to Feng Liu.
Ethics declarations
Competing interests
The authors declare no competing 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/.
About this article
Cite this article
Yang, S., Shih, YC., Ju, X. et al. Epilepsy domain adapted large language models enhance epileptogenic zone prediction from seizure semiology. Commun Med (2026). https://doi.org/10.1038/s43856-026-01883-1
Received: 28 March 2026
Accepted: 19 August 2026
Published: 19 October 2026
DOI: https://doi.org/10.1038/s43856-026-01883-1
来源:Nature 健康护理主题 · nature.com