Performance of an automated deep learning algorithm to identify hepatic steatosis within noncontrast computed tomography scans among people with and without HIV

• Published in: Pharmacoepidemiology and drug safety Vol. 32; no. 10; pp. 1121 - 1130
• Main Authors: Torgersen, Jessie, Akers, Scott, Huo, Yuankai, Terry, James G., Carr, J. Jeffrey, Ruutiainen, Alexander T., Skanderson, Melissa, Levin, Woody, Lim, Joseph K., Taddei, Tamar H., So‐Armah, Kaku, Bhattacharya, Debika, Rentsch, Christopher T., Shen, Li, Carr, Rotonya, Shinohara, Russell T., McClain, Michele, Freiberg, Matthew, Justice, Amy C., Lo Re, Vincent
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Inc 01.10.2023; Wiley Subscription Services, Inc
• Subjects: Abdomen; Algorithms; Computed tomography; Cross-Sectional Studies; Deep Learning; Fatty liver; Fatty Liver - diagnostic imaging; Fatty Liver - epidemiology; fatty liver disease; hepatic steatosis; HIV; HIV Infections - complications; HIV Infections - diagnostic imaging; Human immunodeficiency virus; Humans; Liver; Liver diseases; machine learning; Performance evaluation; Retrospective Studies; Steatosis; Tomography, X-Ray Computed - methods; validation; machine learning; validation; fatty liver disease; hepatic steatosis
• ISSN: 1053-8569; 1099-1557; 1099-1557
• DOI: 10.1002/pds.5648

Purpose Hepatic steatosis (fatty liver disease) affects 25% of the world's population, particularly people with HIV (PWH). Pharmacoepidemiologic studies to identify medications associated with steatosis have not been conducted because methods to evaluate liver fat within digitized images have not been developed. We determined the accuracy of a deep learning algorithm (automatic liver attenuation region‐of‐interest‐based measurement [ALARM]) to identify steatosis within clinically obtained noncontrast abdominal CT images compared to manual radiologist review and evaluated its performance by HIV status. Methods We performed a cross‐sectional study to evaluate the performance of ALARM within noncontrast abdominal CT images from a sample of patients with and without HIV in the US Veterans Health Administration. We evaluated the ability of ALARM to identify moderate‐to‐severe hepatic steatosis, defined by mean absolute liver attenuation <40 Hounsfield units (HU), compared to manual radiologist assessment. Results Among 120 patients (51 PWH) who underwent noncontrast abdominal CT, moderate‐to‐severe hepatic steatosis was identified in 15 (12.5%) persons via ALARM and 12 (10%) by radiologist assessment. Percent agreement between ALARM and radiologist assessment of absolute liver attenuation <40 HU was 95.8%. Sensitivity, specificity, positive predictive value, and negative predictive value of ALARM were 91.7% (95%CI, 51.5%–99.8%), 96.3% (95%CI, 90.8%–99.0%), 73.3% (95%CI, 44.9%–92.2%), and 99.0% (95%CI, 94.8%–100%), respectively. No differences in performance were observed by HIV status. Conclusions 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.