https://ir.unisa.ac.za/handle/10500/30859 2026-06-19T16:13:58Z https://ir.unisa.ac.za/handle/10500/32642 Loss to follow-up on antiretroviral therapy amongst HIV patients on CCMDD program at Makhado Municipality, Limpopo Province, South Africa Moradi, Rofhiwa Faith Background: Loss to Follow-Up among HIV patients receiving Antiretroviral Therapy (ART) remains a significant barrier to achieving optimal HIV care outcomes in South Africa. The Central Chronic Medicine Dispensing and Distribution (CCMDD) Programme was introduced to improve access to treatment; however, retention challenges persist. Purpose: The study aimed to explore factors contributing to high rates of LTFU among HIV patients enrolled in the CCMDD Programme in the Makhado Local Municipality in the Limpopo Province, South Africa. Study setting: The study was conducted in three purposively selected clinics that implemented the CCMDD Programme in the Makhado Local Municipality, in the Limpopo Province. Method: An exploratory, descriptive qualitative research design was employed. A purpose sample of 34 HIV positive patients, aged 18 years and older, who had defaulted ART within the past twelve months but subsequently returned to care, participated in semi-structured, in-depth interviews. Data were analyzed using Braun and Clarke’s six-step thematic analysis. Trustworthiness was ensured through researcher-led data collection and strategies to enhance credibility and dependability. Results: Five major themes emerged from the data: (1) positive factors of the CCMDD Programme; (2) individual factors; (3) interpersonal factors; (4) community factors; and (5) health system-related factors. The positive aspects of the CCMDD Programme included improved patient adherence to treatment and reduced facility congestion. Contributing barriers included a shortage of medication, long waiting periods, poor data recording, communication breakdowns,Limited understanding of the Programme, distance and travel time, challenges with script renewal, side effects, stigma, nondisclosure, and a lack of social support. Conclusion: The findings of the study highlighted that the key drivers contributing to LTFU include stigma, non-disclosure of HIV status, long travel distances to collection points, lack of social support, and limited knowledge of the CCMDD Programme. Strengthening patient education, improving communication systems, and implementing early tracing strategies may enhance retention and adherence among patients enrolled in the CCMDD Programme. 2026-02-01T00:00:00Z https://ir.unisa.ac.za/handle/10500/32590 U-commerce: exploring the value and adoption strategies for medical scheme administrators in South Africa Hughes, D.B. The purpose of this research is to assess the true value of u-commerce and to address the problem of adoption. The case research analysis the u-commerce implementations of Discovery Health, a leading South African medical scheme administrator, to uncover sources of value and lessons learnt which inform a proposed strategy framework. The findings suggest that strategies focusing on operational efficiencies alone yield marginal value. Strategies should instead focus on solutions that improve the quality of complex decisions by all actors in the value chain by focus attention on context-rich information while simultaneously conserving attention where interactions are mundane and trivial. U-commerce achieves this by matching the electronic channel, user-interface and information density to the space/time context of the process actor seamlessly and intuitively as they traverse their personal work.flow. Implementation threats are rooted in the technology and cultural readiness of the firm and the market. Appropriate leadership, culture and structure are shown to be critical success factors. Text in English with abstract and no authors keywords 2006-11-30T00:00:00Z https://ir.unisa.ac.za/handle/10500/32581 Community based health insurance uptake and utilisation of healthcare in Ethiopia Adane Kebede Gutema Background: Community-Based Health Insurance (CBHI) is widely recognized as a key strategy for improving healthcare access and financial protection among lowincome populations. In Ethiopia, despite sustained efforts to expand CBHI coverage, enrolment remains below the national target of 80%. By 2020, only 49% of eligible households enrolled in Shaggar City, Oromia Region, Ethiopia. This limited coverage continues to expose many households to out-of-pocket healthcare costs, delays in seeking care, and poor health outcomes, thereby constraining broader socioeconomic development. Purpose: This study aimed to investigate the factors influencing CBHI uptake and healthcare utilization and to develop sustainable, evidence-based intervention strategies to enhance enrolment, renewal, and effective service use. Methods: A convergent mixed-methods design, guided by the Socio-Ecological Model (SEM), was employed across six sub-cities of Shaggar City, Oromia Region. The quantitative component involved a cross-sectional survey of 406 households, analyzed using SPSS (version 26) through descriptive statistics and multivariable logistic regression. The qualitative component comprised in-depth interviews with health leaders, CBHI officials, experts, healthcare providers, and community representatives, and was analyzed thematically. Findings from both strands were integrated and further refined using the APEASE framework (Affordability, Practicability, Effectiveness, Acceptability, Safety, and Equity). Results: CBHI enrolment showed a substantial improvement over time. While national and earlier evidence indicated that only 49% of eligible households were enrolled by 2020, the findings of this study revealed that enrolment had increased to 98% among eligible households in the study area by 2025. Despite this significant progress in coverage, both CBHI uptake and healthcare utilization were influenced by interconnected factors operating at multiple levels. Key determinants included individual awareness, perceived quality of healthcare services, household economic status, community trust, and institutional capacity. Qualitative insights further enriched these findings by highlighting persistent challenges related to service quality, limited access to reliable information, and gaps in system responsiveness. Drawing on the integrated evidence, the study developed the Comprehensive Integrated CBHI Uptake and Utilization (CICU) strategy, which focuses on strengthening awareness, improving service delivery, and enhancing sustained community engagement. Conclusion: This study makes a meaningful contribution to the field of health financing by offering an empirically grounded and theoretically informed framework for strengthening the implementation of Community-Based Health Insurance. The proposed Comprehensive Integrated CBHI Uptake and Utilization (CICU) strategy provides practical and context-sensitive guidance for policymakers and practitioners to enhance enrolment, improve service utilization, and address system-level challenges. By promoting more equitable and sustained access to quality healthcare, the study also supports Ethiopia’s ongoing efforts toward achieving Universal Health Coverage (UHC) and Sustainable Development Goal 3 (SDG 3). Keywords: Community-Based Health Insurance, CBHI uptake, healthcare utilization, socio-ecological model, health financing, Shaggar City, Oromia Region, Ethiopia 2026-01-09T00:00:00Z https://ir.unisa.ac.za/handle/10500/32577 A machine learning approach to the prediction of poor diarrheal outcomes among children under five years of age : an evaluation of longer duration diarrhea, chronic malnutrition, and mortality Ogwel, Billy Diarrhea is a public health problem globally, having an incidence of about 1.7 billion childhood diarrheal episodes every year, and an annual mortality of about 1.5 million. The clinical diarrheal outcomes surpass acute dehydration and electrolyte imbalance, and often include: longer duration diarrhea (LDD); chronic malnutrition; and mortality. This diarrheal burden disproportionately affects low- and middle-income countries, and is further exacerbated by delayed care-seeking, inadequate diagnostic capacity, demanding work environments, and provider burnout which can impair clinical judgment and performance. Predictive models can augment clinical decision-making by facilitating the rapid identification of patients at increased risk of poor diarrheal outcomes, facilitating timely and cost-effective interventions to improve prognoses. Existing literature revealed a paucity of research focused on the development of predictive models for diarrheal outcomes. This study aimed to bridge this research gap by: i.) identifying predictors of poor diarrhea outcomes for long duration diarrhea (LDD), chronic malnutrition, and mortality; ii.) deriving and validating patient-level predictive models for poor diarrheal outcomes; iii.) designing an R-shiny product suite for predictive models of poor diarrheal outcomes. A correlational study design that involved a hybrid feature selection strategy to identify predictors, was adopted. Seven machine learning algorithms were utilized for model development and evaluation leveraging data from three pediatric enteric studies conducted in Siaya County, Kenya between 2010 and 2023. Shapley values were estimated to enhance model interpretability and the model with optimal discrimination was selected as the champion model for each outcome. Clinical variables were the primary predictors of poor diarrheal outcomes, although the sets of predictors varied based on the distinct outcome being modeled. The champion models identified were: random forest for LDD iii (AUC [95% CI]: 83.0% [78.6–87.5]); gradient boosting for chronic malnutrition (AUC [95% CI]: 83.5% [81.6–85.4]); and random forest for mortality (AUC [95% CI]: 82.6% [77.1–88.1]). The model AUCs declined by 12% for LDD and 18% for chronic malnutrition during temporal validation. An R-Shiny web application was developed, featuring a consolidated interface that dynamically displays risk profiles and outcome-specific Shapley values upon submission of user inputs. Beyond demonstrating the practical utility of machine learning algorithms in rapid identification of high-risk children supporting clinical decision-making, resource prioritization, and improved management, this work contributes to the growing body of literature on the application of machine learning to predict pediatric risks. However, successful implementation and widespread adoption of the developed tool will require further research, collaboration, and ethical oversight. Consequently, future research is recommended to evaluate the clinical acceptability of these models, as well as their impact on clinical practice and patient outcomes. Moreover, it is essential to assess the broader implications of ML integration, including the operational challenges and the cost-effectiveness of model deployment through a before-after study or decision-analytic modeling framework. 2026-03-03T00:00:00Z