Zero-shot medical event prediction using a generative pretrained transformer on electronic health records
This capability enhances the versatility of predictive healthcare models and reduces the need for task-specific training, enabling more scalable applications in clinical settings.
Authors
- Corey W Arnold (ORCID: https://orcid.org/0000-0002-4119-8143)
- William F Speier (ORCID: https://orcid.org/0000-0002-0890-8684)
- Brian T. Hill
- Aaron Chin (ORCID: https://orcid.org/0000-0001-9490-6580)
- Melika Emami (ORCID: https://orcid.org/0000-0002-4740-9626)
- Mara Pleasure
- Rushikesh Kulkarni
- Ekaterina Redekop
- Zichen Wang (ORCID: https://orcid.org/0000-0001-8940-6792)
- Hamid Reza Hassanzadeh (ORCID: https://orcid.org/0000-0002-1096-2727)
Institutions
- University of California, Los Angeles (US)
- Optum (United States) (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-09-19
- DOI
- https://doi.org/10.1093/jamia/ocaf160
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.48