Development and Validation of a Generative Artificial Intelligence-Based Pipeline for Automated Clinical Data Extraction From Electronic Health Records: Technical Implementation Study
We demonstrated the successful integration of an LLM-based extraction system within an existing clinical outcomes database, achieving rapid, comprehensive data extraction at minimal cost. UODBLLM provides a scalable, efficient solution for automating clinical data extraction while maintaining protected health information security. This approach could significantly accelerate research timelines and expand feasible clinical studies, particularly for large-scale database projects.
Authors
- Robert Krumm
- Andrew W. Liu (ORCID: https://orcid.org/0000-0001-8033-2598)
- Janet E. Cowan (ORCID: https://orcid.org/0000-0003-1852-8260)
- Peter R. Carroll (ORCID: https://orcid.org/0000-0002-1086-4334)
- Anobel Y. Odisho (ORCID: https://orcid.org/0000-0003-0975-0812)
- William A. Pace
- Matthew R. Cooperberg (ORCID: https://orcid.org/0000-0003-4339-6685)
- Marvin N. Carlisle (ORCID: https://orcid.org/0009-0007-6467-0758)
Institutions
- University of Massachusetts Chan Medical School (US)
- University of California, San Francisco (US)
- UCSF Helen Diller Family Comprehensive Cancer Center (US)
Publication Details
- Journal
- JMIR Bioinformatics and Biotechnology
- Published
- 2025-10-21
- DOI
- https://doi.org/10.2196/70708
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00