Performance of an automated deep learning algorithm to identify hepatic steatosis within noncontrast computed tomography scans among people with and without HIV
Torgersen J, Akers S, Huo Y, Terry J, Carr J, Ruutiainen A, Skanderson M, Levin W, Lim J, Taddei T, So‐Armah K, Bhattacharya D, Rentsch C, Shen L, Carr R, Shinohara R, McClain M, Freiberg M, Justice A, Re V. Performance of an automated deep learning algorithm to identify hepatic steatosis within noncontrast computed tomography scans among people with and without HIV. Pharmacoepidemiology And Drug Safety 2023, 32: 1121-1130. PMID: 37276449, PMCID: PMC10527049, DOI: 10.1002/pds.5648.Peer-Reviewed Original ResearchMeSH KeywordsCross-Sectional StudiesDeep LearningFatty LiverHIV InfectionsHumansRetrospective StudiesTomography, X-Ray ComputedConceptsSevere hepatic steatosisHepatic steatosisHIV statusLiver attenuationHounsfield unitsPredictive valueRadiologist assessmentUS Veterans Health AdministrationNoncontrast abdominal CTVeterans Health AdministrationCross-sectional studySample of patientsNegative predictive valueReal-world studyPositive predictive valueAbdominal CTLiver fatTomography scanSteatosisCT imagesHealth AdministrationPharmacoepidemiologic studiesRadiologist reviewHIVPercent agreement