Applying machine learning and predictive modeling to retention and viral suppression in South African HIV treatment cohorts.

HIV treatment programs face challenges in identifying patients at risk for loss-to-follow-up and uncontrolled viremia. We applied predictive machine learning algorithms to anonymised, patient-level HIV programmatic data from two districts in South Africa, 2016-2018. We developed patient risk scores for two outcomes: (1) visit attendance ≤ 28 days of the next scheduled clinic visit and (2) suppression of the next HIV viral load (VL). Demographic, clinical, behavioral and laboratory data were investigated in multiple models as predictor variables of attending the next scheduled visit and VL results at the next test. Three classification algorithms (logistical regression, random forest and AdaBoost) were evaluated for building predictive models. Data were randomly sampled on a 70/30 split into a training and test set. The training set included a balanced set of positive and negative examples from which the classification algorithm could learn. The predictor variable data from the unseen test set were given to the model, and each predicted outcome was scored against known outcomes. Finally, we estimated performance metrics for each model in terms of sensitivity, specificity, positive and negative predictive value and area under the curve (AUC). In total, 445,636 patients were included in the retention model and 363,977 in the VL model. The predictive metric (AUC) ranged from 0.69 for attendance at the next scheduled visit to 0.76 for VL suppression, suggesting that the model correctly classified whether a scheduled visit would be attended in 2 of 3 patients and whether the VL result at the next test would be suppressed in approximately 3 of 4 patients. Variables that were important predictors of both outcomes included prior late visits, number of prior VL tests, time since their last visit, number of visits on their current regimen, age, and treatment duration. For retention, the number of visits at the current facility and the details of the next appointment date were also predictors, while for VL suppression, other predictors included the range of the previous VL value. Machine learning can identify HIV patients at risk for disengagement and unsuppressed VL. Predictive modeling can improve the targeting of interventions through differentiated models of care before patients disengage from treatment programmes, increasing cost-effectiveness and improving patient outcomes.

An assessment of the HIV/TB knowledge and skills of home-based carers working in the North West province in South Africa: a cross-sectional study.

BACKGROUND: Home-based carers (HBCs) play a critical role in ensuring the success of the primary health care re-engineering strategy in South Africa. Their role includes ensuring improved access to and delivery of primary health care at the household level, and better co-ordination and improved linkages between community and health facilities for HIV/TB services. The objective of this study was to assess the knowledge, skills, challenges and training needs of HBCs involved in HIV/TB care in one sub-district in the North-West province of South Africa. METHODS: We conducted a descriptive, cross-sectional study in which 157 HBCs were interviewed to assess their knowledge and skills regarding HIV and TB. Data were collected using a pre-tested semi-structured questionnaire. Quantitative and qualitative data were analysed using SPSS statistical software and thematic analysis respectively. RESULTS: One hundred and forty-four (92%) of the interviewees were female and 13 (8%) were male. The median age of the participants was 35 years (interquartile range (IQR): 22-27). The median score for knowledge of both HIV and TB questions was 66% (IQR: 57-75). In general, HIV knowledge scores were higher than TB knowledge scores (73% versus 66%). A significant association was found between knowledge scores and formal training (p < 0.05), and knowledge scores and highest educational levels (p < 0.05). Irrespective of knowledge, HBCs reported providing a variety of services to support HIV/TB services in the communities in which they worked. HBCs also reported facing various challenges in their jobs related to stigma and the social contexts in which they work. CONCLUSION: The study showed that the overall knowledge of HBCs was limited, given the skills required and the services they provide. Given the increasing role of HBCs in various health initiatives, targeted interventions are required to support and improve their competencies and service provision.

Understanding and addressing socio-cultural barriers to medical male circumcision in traditionally non-circumcising rural communities in sub-Saharan Africa.

Given recent clinical trials establishing the safety and efficacy of adult medical male circumcision (MMC) in Africa, attention has now shifted to barriers and facilitators to programmatic implementation in traditionally non-circumcising communities. In this study, we attempted to develop a fuller understanding of the role of cultural issues in the acceptance of adult circumcision. We conducted four focus-group discussions with 28 participants in Mutoko, Zimbabwe, and 33 participants in Vulindlela, KwaZulu-Natal, South Africa, as well as 19 key informant interviews in both settings. We found the concept of male circumcision to be an alien practice, particularly as expressed in the context of local languages. Cultural barriers included local concepts of ethnicity, social groups, masculinity and sexuality. On the other hand, we found that concerns about the impact of HIV on communities resulted in willingness to consider adult male circumcision as an option if it would result in lowering the local burden of the epidemic. Adult MMC-promotional messages that create a synergy between understandings of both traditional and medical circumcision will be more successful in these communities.

Mobile VCT: reaching men and young people in urban and rural South African pilot studies (NIMH Project Accept, HPTN 043).

Mounting evidence exists that mobile voluntary counselling and testing (VCT) is able to extend coverage to new localities and populations. We describe two feasibility and acceptability pilot studies conducted in rural and urban South Africa in preparation for the larger NIMH Project Accept HIV prevention trial. A total of 1,015 individuals participated in the pilot studies. Participants in rural Vulindlela were younger (median 22 years) compared to urban Soweto (p < 0.001). Young people were more likely to be first time testers in both sites (p = 0.01 in Vulindlela, p < 0.001 in Soweto), with significantly more men likely to be first time testers than women (p = 0.01 in Vulindlela, p < 0.001 in Soweto). User satisfaction with mobile VCT was extremely high in both sites. Our study shows that providing mobile, high-quality and easy to access services in a high prevalence context is a feasible way to engage youth, men and more rural populations in HIV counselling and testing.

Looking to the future: South African men and women negotiating HIV risk and relationship intimacy.

This paper examines the approaches heterosexual men and women in South Africa use to engage their partners in discussions of HIV and risk factors in their relationships. These strategies entail balancing the risks of infection while managing the challenges of maintaining a relationship. In a context in which there is a great deal of insecurity in relationships it is especially challenging to discuss HIV risks with partners. Our findings reveal that concerns about children or the desire to have children provided a legitimate basis for discussing HIV risk with partners. The focus of these discussions is on the future for their children. Research in South Africa should attend to men's and women's desires to have and to raise children. HIV prevention and treatment programmes can capitalise on concerns regarding children, and the future of the family, to engage men and women in discussing mutually acceptable strategies for preventing infection and ensuring safe conception.

Evaluation of a peer network-based sexual risk reduction intervention for men in beer halls in Zimbabwe: results from a randomized controlled trial.

While much emphasis has been placed on involving men in AIDS prevention in sub-Saharan Africa, there remain few rigorously evaluated interventions in this area. A particularly appealing point of intervention is the sexual risk behavior associated with men's alcohol consumption. This article reports the outcomes of The Sahwira HIV Prevention Program, a male-focused, peer-based intervention promoting the idea that men can assist their friends in avoiding high-risk sexual encounters associated with alcohol drinking. The intervention was evaluated in a randomized, controlled trial (RCT) implemented in 24 beer halls in Harare, Zimbabwe. A cadre of 413 male beer hall patrons (~20% of the patronage) was trained to assist their male peers within their friendship networks. Activities included one-on-one interactions, small group discussions, and educational events centering on the theme of men helping their male friends avoid risk. Venues were randomized into 12 control versus 12 intervention beer halls with little cross-contamination between study arms. The penetration and impact of the intervention were assessed by pre- and post-intervention cross-sectional surveys of the beer hall patronage. The intervention was implemented with a high degree of fidelity to the protocol, with exposure to the intervention activities significantly higher among intervention patrons compared to control. While we found generally declining levels of risk behavior in both study arms from baseline to post-intervention, we found no evidence of an impact of the intervention on our primary outcome measure: episodes of unprotected sex with non-wife partners in the preceding 6 months (median 5.4 episodes for men at intervention beer halls vs. 5.1 among controls, P = 0.98). There was also no evidence that the intervention reduced other risks for HIV. It remains an imperative to find ways to productively engage men in AIDS prevention, especially in those venues where male bonding, alcohol consumption, and sexual risk behavior are intertwined.

Beyond sugar daddies: intergenerational sex and AIDS in urban Zimbabwe.

In a survey of 1,313 men reporting on 2,465 partnerships recruited at beer halls in Harare, Zimbabwe, 2.5% met a definition of "sugar daddy": men with a non-marital partner at least 10 years younger and under 20 years old, and exchanged cash or goods for sex. Men engaging in intergenerational sex with a teenage woman had similar HIV prevalence, incomes, and condom use as men in other partnerships. Most men (62.3%) had partners 5 or more years younger, with wider age gaps in longer-term relationships. Condom use was less common within married and steady partnerships compared to casual and more common with younger women. The most common form of intergenerational sex, with the widest age gap and lowest condom use, occurs within marriages and steady partnerships. Such "conventional" intergenerational sex may play the pivotal role in sustaining a generalized epidemic across generations and present the most difficult challenge to prevention.

USING PARTICIPATORY METHODS AND GEOGRAPHIC INFORMATION SYSTEMS (GIS) TO PREPARE FOR AN HIV COMMUNITY-BASED TRIAL IN VULINDLELA, SOUTH AFRICA (Project Accept-HPTN 043).

Recent attempts to integrate geographic information systems (GIS) and participatory techniques, have given rise to terminologies such as participatory GIS and community-integrated GIS. Although GIS was initially developed for physical geographic application, it can be used for the management and analysis of health and health care data. Geographic information systems, combined with participatory methodology, have facilitated the analysis of access to health facilities and disease risk in different populations. Little has been published about the usefulness of combining participatory methodologies and GIS technology in an effort to understand and inform community-based intervention studies, especially in the context of HIV. This article attempts to address this perceived gap in the literature. The authors describe the application of participatory research methods with GIS in the formative phase of a multisite community-based social mobilization trial, using voluntary counseling and testing and post-test support as the intervention.

A comparison of HIV stigma and discrimination in five international sites: the influence of care and treatment resources in high prevalence settings.

What accounts for differences in HIV stigma across different high prevalence settings? This study was designed to examine HIV stigma and discrimination in five high prevalence settings. Qualitative data were collected as part of the U.S. National Institute of Mental Health (NIMH) Project Accept, a multi-site community randomized trial of community-based HIV voluntary counseling and testing. In-depth interviews were conducted with 655 participants in five sites, four in Sub-Saharan Africa and one in Southeast Asia. Interviews were conducted in the local languages by trained research staff. Data were audiotaped, transcribed, translated, coded and computerized for thematic data analysis. Participants described the stigmatizing attitudes and behaviors perpetuated against people living with HIV/AIDS (PLWHA). The factors that contribute to HIV stigma and discrimination include fear of transmission, fear of suffering and death, and the burden of caring for PLWHA. The family, access to antiretrovirals and other resources, and self-protective behaviors of PLWHA protected against HIV stigma and discrimination. Variation in the availability of health and socioeconomic resources designed to mitigate the impact of HIV/AIDS helps explain differences in HIV stigma and discrimination across the settings. Increasing access to treatment and care resources may function to lower HIV stigma, however, providing services is not enough. We need effective strategies to reduce HIV stigma as treatment and care resources are scaled up in the settings that are most heavily impacted by the HIV epidemic.