Large-scale identification of social and behavioral determinants of health from clinical notes: comparison of Latent Semantic Indexing and Generative Pretrained Transformer (GPT) models
These results demonstrate that the LSI approach performs comparable to more recent large language models, such as GPT-3.5 and GPT-4.0, when using the same set of documents. Importantly, LSI is robust, deterministic, and does not have document-size limitations or cost implications, which make it more amenable to real-world applications in health systems.
Authors
- Sujoy Roy (ORCID: https://orcid.org/0000-0002-4411-1859)
- Ramin Homayouni (ORCID: https://orcid.org/0000-0003-0186-5076)
- Lili Zhao (ORCID: https://orcid.org/0000-0002-0634-0482)
- S. Morrell
Institutions
- Pioneer (United States) (US)
- Oakland University (US)
- Beaumont Health (US)
- Corewell Health
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2024-10-10
- DOI
- https://doi.org/10.1186/s12911-024-02705-x
- Citations
- 4
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 1.39