Measuring the performance of HIV self-testing at private pharmacies in Kenya: a cross-sectional study

Women's preferences for HIV prevention service delivery in pharmacies during pregnancy in Western Kenya: a discrete choice experiment

INTRODUCTION

Pharmacy-delivered HIV prevention services might create more options for pregnant women to use HIV prevention tools earlier and more consistently during pregnancy. We quantified preferences for attributes of potential HIV prevention services among women of childbearing age in Western Kenya.

METHODS

From June to November 2023, we administered a face-to-face discrete choice experiment survey to women aged 15-44 in Kenya's Homa Bay, Kisumu and Siaya counties. The survey evaluated preferences for HIV prevention services, described by seven attributes: service location, travel time, type of HIV test, sexually transmitted infection (STI) testing, partner HIV testing, pre-exposure prophylaxis (PrEP) and service fee. Participants answered a series of 12-choice questions. Each question asked them to select one of two service options or no services-an opt-out option. We used hierarchical Bayesian modelling levels to estimate each attribute level's coefficient and understand how attributes influenced service choice.

RESULTS

Overall, 599 participants completed the survey, among whom the median age was 23 years (IQR: 18-27); 33% were married, 20% had a job and worked regularly, and 52% had been pregnant before. Participants, on average, strongly preferred having any HIV prevention service option over none (opt-out preference weight: -5.84 [95% CI: -5.97, -5.72]). The most important attributes were the availability of PrEP (relative importance 27.04% [95% CI: 25.98%, 28.11%]), followed by STI testing (relative importance 20.26% [95% CI: 19.52%, 21.01%]) and partner HIV testing (relative importance: 16.35% [95% CI: 15.79%, 16.90%]). While, on average, participants preferred obtaining services at the clinic more than pharmacies, women prioritized the availability of PrEP, STI testing and partner HIV testing more than the location or cost.

CONCLUSIONS

These findings suggest the importance of providing comprehensive HIV prevention services and ensuring PrEP, STI testing and partner HIV testing are available. If pharmacies can offer these services, women are likely to access those services at pharmacies even if they prefer clinics.

Measuring the performance of computer vision artificial intelligence to interpret images of HIV self-testing results

Introduction

HIV self-testing (HIVST) is highly sensitive and specific, addresses known barriers to HIV testing (such as stigma), and is recommended by the World Health Organization as a testing option for the delivery of HIV pre-exposure prophylaxis (PrEP). Nevertheless, HIVST remains underutilized as a diagnostic tool in community-based, differentiated HIV service delivery models, possibly due to concerns about result misinterpretation, which could lead to inadvertent onward transmission of HIV, delays in antiretroviral therapy (ART) initiation, and incorrect initiation on PrEP. Ensuring that HIVST results are accurately interpreted for correct clinical decisions will be critical to maximizing HIVST's potential. Early evidence from a few small pilot studies suggests that artificial intelligence (AI) computer vision and machine learning could potentially assist with this task. As part of a broader study that task-shifted HIV testing to a new setting and cadre of healthcare provider (pharmaceutical technologists at private pharmacies) in Kenya, we sought to understand how well AI technology performed at interpreting HIVST results.

Methods

At 20 private pharmacies in Kisumu, Kenya, we offered free blood-based HIVST to clients ≥18 years purchasing products indicative of sexual activity (e.g., condoms). Trained pharmacy providers assisted clients with HIVST (as needed), photographed the completed HIVST, and uploaded the photo to a web-based platform. In real time, each self-test was interpreted independently by the (1) client and (2) pharmacy provider, with the HIVST images subsequently interpreted by (3) an AI algorithm (trained on lab-captured images of HIVST results) and (4) an expert panel of three HIVST readers. Using the expert panel's determination as the ground truth, we calculated the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for HIVST result interpretation for the AI algorithm as well as for pharmacy clients and providers, for comparison.

Results

From March to June 2022, we screened 1,691 pharmacy clients and enrolled 1,500 in the study. All clients completed HIVST. Among 854 clients whose HIVST images were of sufficient quality to be interpretable by the AI algorithm, 63% (540/854) were female, median age was 26 years (interquartile range: 22-31), and 39% (335/855) reported casual sexual partners. The expert panel identified 94.9% (808/854) of HIVST images as HIV-negative, 5.1% (44/854) as HIV-positive, and 0.2% (2/854) as indeterminant. The AI algorithm demonstrated perfect sensitivity (100%), perfect NPV (100%), and 98.8% specificity, and 81.5% PPV (81.5%) due to seven false-positive results. By comparison, pharmacy clients and providers demonstrated lower sensitivity (93.2% and 97.7% respectively) and NPV (99.6% and 99.9% respectively) but perfect specificity (100%) and perfect PPV (100%).

Conclusions

AI computer vision technology shows promise as a tool for providing additional quality assurance of HIV testing, particularly for catching Type II error (false-negative test interpretations) committed by human end-users. We discuss possible use cases for this technology to support differentiated HIV service delivery and identify areas for future research that is needed to assess the potential impacts-both positive and negative-of deploying this technology in real-world HIV service delivery settings.

The Acceptability of Pharmacy-Based HPV Vaccination in Western Kenya among Pharmacy Clients and Providers

Vaccine coverage for the human papillomavirus (HPV) remains low globally, and differentiated models of vaccine delivery are needed to expand access. Pharmacy-based models of the HPV vaccination may engage women who could benefit. We assessed the acceptability of such a model among pharmacy clients and providers at 20 private pharmacies in Kisumu County, Kenya. In questionnaires, participants (≥18 years) were asked the extent they agreed (5-point scale) with statements that assessed different acceptability component constructs outlined in the Theoretical Framework of Acceptability (TFA). From March to June 2022, 1500 pharmacy clients and 40 providers were enrolled and completed questionnaires. Most clients liked the intervention (TFA: affective attitude; 96%, 1435/1500) and did not think it would be hard to obtain (TFA: burden; 93%, 1399/1500). All providers agreed the intervention could reduce HPV infection (TFA: perceived effectiveness) and felt confident they could deliver it (TFA: self-efficacy). Among the clients who had received or were planning to receive the HPV vaccine in the future, half (50%, 178/358) preferred a pharmacy-based HPV vaccination. In this study, most Kenyan pharmacy clients and providers perceived a pharmacy-delivered HPV vaccination as highly acceptable; however, more research is needed to test the feasibility and effectiveness of this novel vaccine delivery model in Africa.