Using electronic health records to identify candidates for human immunodeficiency virus pre-exposure prophylaxis: An application of super learning to risk prediction when the outcome is rare.

Susan GruberDouglas KrakowerJohn T MenchacaKatherine HsuRebecca HawrusikJudith C MaroNoelle M CocorosBenjamin A KruskalIra B WilsonKenneth H MayerMichael Klompas

Published in: Statistics in medicine (2020)

Machine learning was successful at developing a model to predict 1-year risk of acquiring HIV based on a physician-curated set of predictors extracted from EHRs.

Keyphrases

human immunodeficiency virus
electronic health record
antiretroviral therapy
machine learning
hepatitis c virus
hiv infected
clinical decision support
hiv positive
emergency department
primary care
hiv aids
adverse drug
artificial intelligence
hiv testing
big data
deep learning
south africa