Utility of word embeddings from large language models in medical diagnosis.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 39786898

Abstract

OBJECTIVE: This study evaluates the utility of word embeddings, generated by large language models (LLMs), for medical diagnosis by comparing the semantic proximity of symptoms to their eponymic disease embedding ("eponymic condition") and the mean of all symptom embeddings associated with a disease ("ensemble mean").

Authors

  • Shahram Yazdani
    Department of Pediatrics, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90095, United States.
  • Ronald Claude Henry
    Department of Civil Engineering, University of Southern California, Los Angeles, CA 90089, United States.
  • Avery Byrne
    San Francisco, CA 94129, United States.
  • Isaac Claude Henry
    Kennewick, WA 99338, United States.

Keywords

External Resources

Popular Topics
Recent Journals