Performance of an automated deep learning algorithm to identify hepatic steatosis within noncontrast computed tomography scans among people with and without HIV.
Jessie TorgersenScott AkersYuankai HuoJames G TerryJ Jeffrey CarrAlexander T RuutiainenMelissa SkandersonWoody LevinJoseph K LimTamar H TaddeiKaku So-ArmahDebika BhattacharyaChristopher T RentschLi ShenRotonya CarrRussell T ShinoharaMichele McClainMatthew FreibergAmy C JusticeVincent Lo RePublished in: Pharmacoepidemiology and drug safety (2023)
ALARM demonstrated excellent accuracy for moderate-to-severe hepatic steatosis regardless of HIV status. Application of ALARM to radiographic repositories could facilitate real-world studies to evaluate medications associated with steatosis and assess differences by HIV status. This article is protected by copyright. All rights reserved.
Keyphrases
- antiretroviral therapy
- hiv positive
- hiv infected
- hiv testing
- computed tomography
- human immunodeficiency virus
- deep learning
- hepatitis c virus
- hiv aids
- men who have sex with men
- machine learning
- type diabetes
- positron emission tomography
- south africa
- insulin resistance
- metabolic syndrome
- dual energy
- convolutional neural network
- image quality
- high fat diet induced