Machine learning models based on fluid immunoproteins that predict non-AIDS adverse events in people with HIV
Thomas A. Premeaux,
Scott Bowler,
Courtney M. Friday,
Carlee B. Moser,
Martin Hoenigl,
Michael M. Lederman,
Alan L. Landay,
Sara Gianella,
Lishomwa C. Ndhlovu
Affiliations
Thomas A. Premeaux
Division of Infectious Diseases, Department of Medicine, Weill Cornell Medicine, New York, NY, USA; Corresponding author
Scott Bowler
Division of Infectious Diseases, Department of Medicine, Weill Cornell Medicine, New York, NY, USA
Courtney M. Friday
Division of Infectious Diseases, Department of Medicine, Weill Cornell Medicine, New York, NY, USA
Carlee B. Moser
Center for Biostatistics in AIDS Research in the Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
Martin Hoenigl
Division of Infectious Diseases, Department of Medicine, University of California San Diego, San Diego, CA, USA; Division of Infectious Diseases, Department of Internal Medicine, Medical University of Graz, Graz, Austria
Michael M. Lederman
Department of Medicine, Division of Infectious Diseases and HIV Medicine, Case Western Reserve University, Cleveland, OH, USA
Alan L. Landay
Department of Internal Medicine, Rush University Medical Center, Chicago, IL, USA
Sara Gianella
Division of Infectious Diseases, Department of Medicine, University of California San Diego, San Diego, CA, USA
Lishomwa C. Ndhlovu
Division of Infectious Diseases, Department of Medicine, Weill Cornell Medicine, New York, NY, USA
Summary: Despite the success of antiretroviral therapy (ART), individuals with HIV remain at risk for experiencing non-AIDS adverse events (NAEs), including cardiovascular complications and malignancy. Several surrogate immune biomarkers in blood have shown predictive value in predicting NAEs; however, composite panels generated using machine learning may provide a more accurate advancement for monitoring and discriminating NAEs. In a nested case-control study, we aimed to develop machine learning models to discriminate cases (experienced an event) and matched controls using demographic and clinical characteristics alongside 49 plasma immunoproteins measured prior to and post-ART initiation. We generated support vector machine (SVM) classifier models for high-accuracy discrimination of individuals aged 30–50 years who experienced non-fatal NAEs at pre-ART and one-year post-ART. Extreme gradient boosting generated a high-accuracy model at pre-ART, while K-nearest neighbors performed poorly all around. SVM modeling may offer guidance to improve disease monitoring and elucidate potential therapeutic interventions.