Machine Learning to Identify Persons at High-Risk of Human Immunodeficiency Virus Acquisition in Rural Kenya and Uganda. (7th November 2019)

• Record Type: Journal Article
• Authors: Balzer, Laura B; Havlir, Diane V; Kamya, Moses R; Chamie, Gabriel; Charlebois, Edwin D; Clark, Tamara D; Koss, Catherine A; Kwarisiima, Dalsone; Ayieko, James; Sang, Norton; Kabami, Jane; Atukunda, Mucunguzi; Jain, Vivek; Camlin, Carol S; Cohen, Craig R; Bukusi, Elizabeth A; Van Der Laan, Mark; Petersen, Maya L
• Is Part Of: Clinical infectious diseases. Volume 71:Number 9(2020)
• Page Start: 2326
• Page End: 2333
• Publication Date: 2019-11-07
• Subjects: clinical prediction rule -- HIV risk score -- HIV prevention -- PrEP -- SEARCH Study; Communicable diseases -- Periodicals; 616.905
• DOI: 10.1093/cid/ciz1096
• Languages: English
• ISSNs: 1058-4838

Abstract

Abstract: Background: In generalized epidemic settings, strategies are needed to prioritize individuals at higher risk of human immunodeficiency virus (HIV) acquisition for prevention services. We used population-level HIV testing data from rural Kenya and Uganda to construct HIV risk scores and assessed their ability to identify seroconversions. Methods: During 2013–2017, >75% of residents in 16 communities in the SEARCH study were tested annually for HIV. In this population, we evaluated 3 strategies for using demographic factors to predict the 1-year risk of HIV seroconversion: membership in ≥1 known "risk group" (eg, having a spouse living with HIV), a "model-based" risk score constructed with logistic regression, and a "machine learning" risk score constructed with the Super Learner algorithm. We hypothesized machine learning would identify high-risk individuals more efficiently (fewer persons targeted for a fixed sensitivity) and with higher sensitivity (for a fixed number targeted) than either other approach. Results: A total of 75 558 persons contributed 166 723 person-years of follow-up; 519 seroconverted. Machine learning improved efficiency. To achieve a fixed sensitivity of 50%, the risk-group strategy targeted 42% of the population, the model-based strategy targeted 27%, and machine learning targeted 18%. Machine learning also improved sensitivity. With an upper limit of 45% targeted, the risk-group strategy correctly classified 58% of seroconversions, the model-based strategy 68%, and machine learning 78%. Conclusions: Machine learning improved classification of individuals at risk of HIV acquisition compared with a model-based approach or reliance on known risk groups and could inform targeting of prevention strategies in generalized epidemic settings. Clinical Trials Registration: NCT01864603. Abstract : Using population-based testing data on 75 558 adults from rural East Africa, we developed and validated a machine learning human immunodeficiency virus (HIV) risk score and found it improved targeting of intensified HIV prevention services compared with model-based and risk group approaches.