Evaluating the positive predictive value of code-based identification of cirrhosis and its complications utilizing GPT-4
LLM-based classification was highly accurate versus manual chart review in identifying cirrhosis and its complications. This allowed us to assess the performance of code-based classification at scale using LLMs as a silver standard. These results suggest LLMs could augment or replace code-based cohort classification and raise questions regarding the necessity of chart review.
Authors
- Oksana Gologorskaya (ORCID: https://orcid.org/0009-0005-3505-7300)
- Mark J. Pletcher (ORCID: https://orcid.org/0000-0002-6966-1312)
- Jin Ge (ORCID: https://orcid.org/0000-0003-1574-1525)
- Asal Bastani (ORCID: https://orcid.org/0000-0002-2433-1504)
- Chiung‐Yu Huang (ORCID: https://orcid.org/0000-0003-2313-3562)
- Jennifer C. Lai (ORCID: https://orcid.org/0000-0003-2092-6380)
- Albert Lee (ORCID: https://orcid.org/0000-0002-3821-4376)
- Aryana T. Far (ORCID: https://orcid.org/0009-0004-9664-902X)
Institutions
- University of California, San Francisco (US)
Publication Details
- Journal
- Hepatology
- Published
- 2024-10-08
- DOI
- https://doi.org/10.1097/hep.0000000000001115
- Citations
- 10
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 7.08