https://ir.unisa.ac.za/handle/10500/11919 Fri, 19 Jun 2026 17:31:59 GMT 2026-06-19T17:31:59Z 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. Tue, 03 Mar 2026 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/32577 2026-03-03T00:00:00Z https://ir.unisa.ac.za/handle/10500/29912 Research collaboration in asymmetric power relations: A study of postgraduate students’ views Van Biljon, Judy; Mwapwele, Samwel Collaboration among researchers and across disciplinary, organisational and cultural boundaries is essential for addressing the increasingly complex challenges and opportunities facing international development. Despite the known advantages and various incentives, research collaboration within Africa (specifically within South Africa) is lacking. To better understand the reasons for this lack of research collaboration, this study explored collaboration between students and supervisors in an information and communication technology for development (ICT4D) postgraduate student project in South Africa. South Africa, a country with major social inequalities and asymmetric power relations, provides an appropriate context. The students’ perspectives provided a space for investigating the collaboration factors by unpacking the capability inputs according to Robeyns’ representation of personal capabilities. Data were captured from a survey and focus groups (FG) with students and supervisors in ICT4D from different universities in South Africa. Thematic analysis was used to identify and link the participants’ expectations of research collaboration with their perceptions of the challenges of such collaborations. The contribution is a conceptualisation of the main components representing research collaboration viewed in terms of personal capabilities, including the factors that influence collaboration. Transdisciplinarity contribution: Research collaboration is fundamental to promoting multi-, inter- and transdisciplinary research. The novelty of this study lies in applying a theoretical lens from the field of human development to explore research collaboration in the transdisciplinary field of ICT4D. Given the research application context and the theoretical lens applied, the findings have implications for initiatives and policies on funding transdisciplinary research collaboration. Thu, 16 Feb 2023 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/29912 2023-02-16T00:00:00Z https://ir.unisa.ac.za/handle/10500/29819 A Conceptual Framework for the Development of Argumentation Skills Using CSCL in a Graduate Students’ Research Course van der Merwe, O. R.; Van Biljon, Judy; Pilkington C, / Developing and presenting a well-formulated research argument is core to the learning journey of a graduate student. In open distance e-learning, computer-supported learning is instrumental in providing a platform for graduate students to develop their argumentation skills. However, there is little guidance on the elements required in using computer supportive collaborative learning (CSCL) to augment argumentation skills development (ASD). This paper reports on elements identified in literature that should be present in a framework using CSCL to augment ASD. The thematically analysed data gathered during the focus group sessions were used to confirm the structure of the argumentation skills development framework (ASDF), and confirmed that there is a need for a framework to provide guidance in using CSCL to augment ASD. The contribution includes the conceptual ASDF using CSCL, comprising seven elements, that provides a strategy of scaffolded learning for implementation in a graduate course to augment ASD. Thu, 07 Jul 2022 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/29819 2022-07-07T00:00:00Z https://ir.unisa.ac.za/handle/10500/29612 Reflections on the Maturity of the Mobile Communication Technology for Development (M4D) Landscape: 2008 - 2016 Van Biljon, Judy; Renaud, Karen The 2018 M4D conference marks a decade of dynamic growth in the Mobile Communication Technology for Development (M4D) discipline. This paper reflects on the developments and maturity of the field based on a systematic literature review of the research papers published in the biennial M4D conference series (2008-2016). The findings offer a comprehensive overview of what was studied (application domains), where the research took place (geographic locations), by whom (the researchers affiliations), how the research was carried out (methodologies) and how the research contributed to the maturity of the M4D field. We conclude by summarising the insights gained from our investigation, with the goal of enriching discussions on how M4D research has evolved, where research gaps may exist and what can be gained by retaining a M4D theoretical corpus. Mon, 01 Jan 2018 00:00:00 GMT https://ir.unisa.ac.za/handle/10500/29612 2018-01-01T00:00:00Z