BackgroundPatient retention in care for HIV/AIDS is a critical challenge for antiretroviral treatment programs. Community-based adherence programs (CBAPs) as compared to health care facility-based adherence programs have been considered as one of the options to provide treatment maintenance support for groups of patients on antiretroviral therapy. Such an approach provides a way of enhancing self-management of the patient’s condition. In addition, CBAPs have been implemented to support antiretroviral treatment expansion in resource-limited settings. CBAPs involve 30 patients that are allocated to a group and meet at either a facility or a community venue for less than an hour every 2 or 3 months depending on the supply of medication. Our study aimed to establish perceived challenges in moving adherence clubs from health facilities to communities.MethodsA qualitative study was conducted in 39 clinics in Mpumalanga and Gauteng Provinces in South Africa between December 2015 and January 2016. Purposive sampling method was used to identify nurses, club managers, data capturers, pharmacists and pharmacy assistants who had been involved in facility-based treatment adherence clubs. Key-informant interviews were conducted. Also, semi-structured interviews were used and thematic content analysis was done.ResultsA total of 53 health care workers, 12 (22.6%) males and 41 (77.4%) females, participated in the study. Most of them 49 (92.5%) indicated that participating in community adherence clubs were a good idea. Reduction in waiting time at the health facilities, in defaulter rate, improvement in adherence to treatment as well as reduction in stigma were some of the perceived benefits. However, security of medication, storage conditions and transportation of the prepacked medication to the distribution sites were the areas of concern.ConclusionHealth care workers were agreeable to idea of the moving adherence clubs from health facilities to communities. Although some challenges were identified, these could be addressed by the key stakeholders. However, government and nongovernmental organizations need to exercise caution when transitioning to community-based adherence clubs.

BackgroundHuman resource planning in healthcare can employ machine learning to effectively predict length of stay of recruited health workers who are stationed in rural areas. While prior studies have identified a number of demographic factors related to general health practitioners’ decision to stay in public health practice, recruitment agencies have no validated methods to predict how long these health workers will commit to their placement. We aim to use machine learning methods to predict health professional’s length of practice in the rural public healthcare sector based on their demographic information.MethodsRecruitment and retention data from Africa Health Placements was used to develop machine-learning models to predict health workers’ length of practice. A cross-validation technique was used to validate the models, and to evaluate which model performs better, based on their respective aggregated error rates of prediction. Length of stay was categorized into four groups for classification (less than 1 year, less than 2 years, less than 3 years, and more than 3 years). R, a statistical computing language, was used to train three machine learning models and apply 10-fold cross validation techniques in order to attain evaluative statistics.ResultsThe three models attain almost identical results, with negligible difference in accuracy. The “best”-performing model (Multinomial logistic classifier) achieved a 47.34% [SD 1.63] classification accuracy while the decision tree model achieved an almost comparable 45.82% [SD 1.69]. The three models achieved an average AUC of approximately 0.66 suggesting sufficient predictive signal at the four categorical variables selected.ConclusionsMachine-learning models give us a demonstrably effective tool to predict the recruited health workers’ length of practice. These models can be adapted in future studies to incorporate other information beside demographic details such as information about placement location and income. Beyond the scope of predicting length of practice, this modelling technique will also allow strategic planning and optimization of public healthcare recruitment.

No abstract

No abstract