Machine Learning Algorithms Using Routinely Collected Data Do Not Adequately Predict Viremia to Inform Targeted Services in Postpartum Women Living With HIV.

BACKGROUND: Adherence to antiretroviral treatment (ART) among postpartum women with HIV is essential for optimal health and prevention of perinatal transmission. However, suboptimal adherence with subsequent viremia is common, and adherence challenges are often underreported. We aimed to predict viremia to facilitate targeted adherence support in sub-Saharan Africa during this critical period. METHODS: Data are from PROMISE 1077BF/FF, which enrolled perinatal women between 2011 and 2014. This analysis includes postpartum women receiving ART per study randomization or country-specific criteria to continue from pregnancy. We aimed to predict viremia (single and confirmed events) after 3 months on ART at >50, >400, and >1000 copies/mL within 6-month intervals through 24 months. We built models with routine clinical and demographic data using the least absolute shrinkage and selection operator and SuperLearner (which incorporates multiple algorithms). RESULTS: Among 1321 women included, the median age was 26 years and 96% were in WHO stage 1. Between 0 and 24 months postpartum, 42%, 31%, and 28% of women experienced viremia >50, >400, and >1000 copies/mL, respectively, at least once. Across models, the cross-validated area under the receiver operating curve ranged from 0.74 [95% confidence interval (CI): 0.72 to 0.76] to 0.78 (95% CI: 0.76 to 0.80). To achieve 90% sensitivity predicting confirmed viremia >50 copies/mL, 64% of women would be classified as high risk. CONCLUSIONS: Using routinely collected data to predict viremia in >1300 postpartum women with HIV, we achieved moderate model discrimination, but insufficient to inform targeted adherence support. Psychosocial characteristics or objective adherence metrics may be required for improved prediction of viremia in this population.

Combination adherence strategy to support HIV antiretroviral therapy and pre-exposure prophylaxis adherence during pregnancy and breastfeeding: protocol for a pair of pilot randomised trials.

INTRODUCTION: To realise the expected gains from prevention of mother-to-child HIV transmission initiatives, adherence to preventative and therapeutic antiretroviral regimens is critical and interventions deployable in busy programmatic settings with a high HIV burden are needed. Based on formative research, we developed an approach that integrates patient-centred counselling and engagement of an adherence supporter for pregnant and breastfeeding women initiating HIV treatment (ie, antiretroviral therapy (ART)) or biomedical HIV prevention (ie, pre-exposure prophylaxis (PrEP)). METHODS: Tonse Pamodzi 2 is a pilot study designed to provide acceptability, fidelity and clinical outcomes data on a set of behavioural interventions for adherence support. The study comprises two parallel randomised trials, enrolling HIV-positive pregnant women initiating ART (Trial 1, n=100) and HIV-negative pregnant women with risk of HIV acquisition and willing to initiate PrEP (Trial 2, n=200). Within each trial, participants are randomised 1:1 to either the intervention or control group. The Tonse Pamodzi adherence intervention comprises patient-centred counselling (adapted Integrated Next Step Counseling(iNSC)) and external adherence support tailored to the clinical context (ie, for ART or PrEP). Participants randomly assigned to the control group receive standard counselling based on local HIV guidelines. Participants are followed for 6 months. To assess intervention acceptability, we will employ a mixed method approach to describe participant engagement, satisfaction, and discussion content. We will audit and score recorded counselling sessions to evaluate the implementation fidelity of iNSC sessions. We will also assess clinical outcomes at 3 and 6 months for both Trial 1 (retention in care and viral suppression of HIV) and Trial 2 (retention in care, and plasma and intracellular tenofovir drug concentrations). ETHICS AND DISSEMINATION: The study protocol was approved by the Malawi National Health Science Research Committee (19/05/2334) and the University of North Carolina at Chapel Hill Institutional Review Board (19-1060). TRIAL REGISTRATION NUMBER: NCT04330989.

Factors associated with unsuppressed viremia in women living with HIV on lifelong ART in the multi-country US-PEPFAR PROMOTE study: A cross-sectional analysis.

BACKGROUND: Despite recent efforts to scale-up lifelong combination antiretroviral therapy (cART) in sub-Saharan Africa, high rates of unsuppressed viremia persist among cART users, and many countries in the region fall short of the UNAIDS 2020 target to have 90% virally suppressed. We sought to determine the factors associated with unsuppressed viremia (defined for the purpose of this study as >200 copies/ml) among sub-Saharan African women on lifelong cART. METHODS: This cross-sectional analysis was based on baseline data of the PROMOTE longitudinal cohort study at 8 sites in Uganda, Malawi, Zimbabwe and South Africa. The study enrolled 1987 women living with HIV who initiated lifelong cART at least 1-5 years ago. Socio-demographic, clinical, and cART adherence data were collected. We used multivariable Poisson regression with robust variance to identify factors associated with unsuppressed viremia. RESULTS: At enrolment, 1947/1987 (98%) women reported taking cART. Of these, HIV-1 remained detectable in 293/1934 (15%), while 216/1934 (11.2%) were considered unsuppressed (>200 copies/ml). The following factors were associated with an increased risk of unsuppressed viremia: not having household electricity (adjusted prevalence risk ratio (aPRR) 1.74, 95% confidence interval (CI) 1.28-2.36, p<0.001); not being married (aPRR 1.32, 95% CI 0.99-1.78, p = 0.061), self-reported missed cART doses (aPRR 1.63, 95% CI 1.24-2.13, p<0.001); recent hospitalization (aPRR 2.48, 95% CI 1.28-4.80, p = 0.007) and experiencing abnormal vaginal discharge in the last three months (aPRR 1.88; 95% CI 1.16-3.04, p = 0.010). Longer time on cART (aPRR 0.75, 95% CI 0.64-0.88, p<0.001) and being older (aPRR 0.77, 95% CI 0.76-0.88, p<0.001) were associated with reduced risk of unsuppressed viremia. CONCLUSION: Socioeconomic barriers such as poverty, and individual barriers like not being married, young age, and self-reported missed doses are key predictors of unsuppressed viremia. Targeted interventions are needed to improve cART adherence among women living with HIV with this risk factor profile.