Constructing synthetic datasets with generative artificial intelligence to train large language models to classify acute renal failure from clinical notes.

Journal: Journal of the American Medical Informatics Association : JAMIA

PMID: 38622901

OBJECTIVES: To compare performances of a classifier that leverages language models when trained on synthetic versus authentic clinical notes.

Onkar Litake

Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, La Jolla, CA 92037, United States.
Brian H Park

Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, La Jolla, CA 92037, United States.
Jeffrey L Tully

Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, La Jolla, California.
Rodney A Gabriel

Department of Medicine, Division of Biomedical Informatics, University of California, San Diego, La Jolla, CA, USA.

Acute Kidney Injury Area Under Curve Artificial Intelligence Datasets as Topic Electronic Health Records Humans Natural Language Processing ROC Curve

View on PubMed Access via DOI PubMed (38622901)