Search

This study aims to explore the potential of Internet of Things (IoT) devices and explainable Artificial Intelligence (AI) techniques in predicting biomarker values associated with GDM when measured 13–16 weeks prior to diagnosis. We developed a system that forecasts biomarkers such as LDL, HDL, triglycerides, cholesterol, HbA1c, and results from the Oral Glucose Tolerance Test (OGTT) including fasting glucose, 1-hour, and 2-hour post-load glucose values. These biomarker values are predicted based on sensory measurements collected around week 12 of pregnancy, including continuous glucose levels, short physical movement recordings, and medical background information. To the best of our knowledge, this is the first study to forecast GDM-associated biomarker values 13 to 16 weeks prior to the GDM screening test, using continuous glucose monitoring devices, a wristband for activity detection, and medical background data. We applied machine learning models, specifically Decision Tree and Random Forest Regressors, along with Coupled-Matrix Tensor Factorisation (CMTF) and Elastic Net techniques, examining all possible combinations of these methods across different data modalities. The results demonstrated good performance for most biomarkers. On average, the models achieved Mean Squared Error (MSE) between 0.29 and 0.42 and Mean Absolute Error (MAE) between 0.23 and 0.45 for biomarkers like HDL, LDL, cholesterol, and HbA1c. For the OGTT glucose values, the average MSE ranged from 0.95 to 2.44, and the average MAE ranged from 0.72 to 0.91. Additionally, the utilisation of CMTF with Alternating Least Squares technique yielded slightly better results (0.16 MSE and 0.07 MAE on average) compared to the well-known Elastic Net feature selection technique. While our study was conducted with a limited cohort in South Africa, our findings offer promising indications regarding the potential for predicting biomarker values in pregnant women through the integration of wearable devices and medical background data in the analysis. Nevertheless, further validation on a larger, more diverse cohort is imperative to substantiate these encouraging results.

Children exposed to alcohol in utero may suffer from cognitive and physical sequelae. The most impactful damage in terms of daily functioning is to higher order cognitive functions involved in planning and goal-directed behaviour, referred to as executive functions. Cognitive training interventions are used as a remedial tool for executive function deficits but require implementation by professionals. For the South African context, where resources are limited, a tablet computer-based cognitive training game was developed. This study aimed to establish the feasibility of implementing and evaluating this intervention in South Africa for children exposed to alcohol prenatally. This was a three-arm feasibility randomised control trial comparing an alcohol exposed intervention arm, to an alcohol exposed control arm, and a non-exposed normative arm. Arm allocation was based on self-reported maternal alcohol use during a structured interview. To assess feasibility, we evaluated participant recruitment and barriers to implementation. Executive functions were measured at baseline and following intervention to evaluate the preliminary impact of the intervention. No significant differences were found between the three arms on the post-intervention assessments. The retention rate was acceptable for a randomised control trial; however, there was significant variance in the length of time spent playing the game overall. The majority of participants learned to play the game quickly and progressed through the difficulty levels. In conclusion, a full randomised control trial using the recruitment, randomisation and implementation method would be suitable in the South African context. The statistical outcomes of this trial do not support a full-scale randomised control trial of this intervention.

Background:Continuous monitoring of glucose (CGM) via subcutaneous patch is an accurate self-monitoring tool of blood glucose, but also introduces a range of additional benefits such as real-time feedback. While its value among pregnant women with gestational diabetes mellitus (GDM) is established in high-income countries, little is known about the feasibility and acceptability among pregnant women without GDM in low-resource settings in low- and middle-income countries.Objectives:This study aims to assess the feasibility and acceptability of CGM with pregnant mothers in South Africa and to explore the value of a collected data set for GDM prevention.Methods:Ten women between 12 and 18 weeks pregnant were recruited from the antenatal clinic at Chris Hani Baragwanath Academic Hospital into a prospective mixed-methods pilot study. Demographic and anthropometric data, HbA1c and a lipid panel were collected. Women then wore two consecutive Freestyle Libre 2 patches for a total of 28 days. In-depth interviews were undertaken with all 10 women on study exit to explore themes of acceptability and the use of technology during pregnancy. Thematic analysis was performed on the qualitative data while exploratory data-analysis techniques were applied to the CGM data.Results:Pregnant women (n = 10) had a mean (SD) age of 29.81 years (4.39), with most being unemployed (8), unmarried (8) and without a tertiary degree (7). Analysis suggests that fear of use was greater than the actual discomfort experienced during use of the CGM patch. The main barrier to use was the patch falling off and women being uncomfortable to reapply it. This was borne out by all 10 women wearing the first patch for at least 12 of the 14 days, but only 4 managing the same with patch two – primarily applied by themselves at home. Women expressed support for the use of technology during pregnancy, especially as it related to feeling that their pregnancy was being monitored and that they were being supported.Conclusion:In this pilot study, women overwhelmingly found the wearing of a CGM patch during pregnancy to be acceptable. Feasibility was reasonable with most data being successfully retrieved from the devices over a two-week period. Longer use was found to have additional challenges. The use of CGM patches appear to be a possible candidate for inclusion in GDM prevention or behavioural interventions during pregnancy in South Africa.

Home delivery and monitoring of antiretroviral therapy (ART) is convenient, overcomes logistical barriers, and could increase individual ART adherence and viral suppression. With client payment and sufficient health benefits, this strategy could be scalable. The aim of the Deliver Health Study was to test the acceptability and efficacy of a user fee for home ART monitoring and delivery.

This study uses the bioecological framework and methodology to select items for and to test a multidimensional structure of a measure of children’s economic well-being in a multi-community sample of children (7–11 years) and their households (N= 1958) from KwaZulu-Natal, a poor and under-served region of South Africa. Economic well-being was assessed using questionnaires completed by children’s caregivers and household heads. Exploratory factor analysis of four random split halves identified three dimensions of economic well-being: Fiscal Appraisal (subjective experiences of access to/allocation of resources), Material Assets (durable goods and living environment), and Fiscal Capacity (traditional measures of poverty: income, expenditures, employment). Confirmatory factor analysis verified the higher order model of economic well-being with the three dimensions. Invariance testing using multiple group factor analysis indicated confidence for use of this measure with varying types of communities in South Africa. The results reflect the multidimensional nature of economic well-being. Thus, the often-used money metric measures of poverty likely paint an incomplete picture of children’s actual economic well-being. Because our sample consists of impoverished households, our measure of economic well-being is sensitive to variation at the deep end of poverty. Implications for theory and future research are discussed.

To present the protocol and methods for the prospective longitudinal assessments—including clinical and digital phenotyping approaches—of the Identifying Depression Early in Adolescence Risk Stratified Cohort (IDEA-RiSCo) study, which comprises Brazilian adolescents stratified at baseline by risk of developing depression or presence of depression.

•Residual dependence induced by a measured covariate remains after performing standard LCA. This violates key assumptions of standard LCA hence incorrect inferences•Models accounting for heterogeneity in diagnostic accuracy yield realistic estimates•Carefully consider factors known to affect diagnostic test performance e.g. severe comorbidity•Covariate-adjusted LCA alleviate bias implied by heterogeneity in diagnostic test accuracy. Therefore, we recommended it.

Background: There is an increasingly urgent gap in knowledge regarding the translation of effective HIV prevention and care programming into scaled clinical policy and practice. Challenges limiting the translation of efficacious programming into national policy include the paucity of proven efficacious programs that are reasonable for clinics to implement and the difficulty in moving a successful program from research trial to scaled programming. This study aims to bridge the divide between science and practice by exploring health care providers’ views on what is needed to implement new HIV programs within existing HIV care. Methods: We conducted 20 in-depth interviews with clinic managers and clinic program implementing staff and five key informant interviews with district health managers overseeing programming in the uMgungundlovu District of KwaZulu-Natal Province, South Africa. Qualitative data were analyzed using a template approach. A priori themes were used to construct templates of relevance, including current care context for HIV and past predictors of successful implementation. Data were coded and analyzed by these templates. Results: Heath care providers identified three main factors that impact the integration of HIV programming into general clinical care: perceived benefits, resource availability, and clear communication. The perceived benefits of HIV programs hinged on the social validation of the program by early adopters. Wide program availability and improved convenience for providers and patients increased perceived benefit. Limited staffing capacity and a shortage of space were noted as resource constraints. Programs that specifically tackled these constraints through clinic decongestion were reported as being the most successful. Clear communication with all entities involved in clinic-based programs, some of which include external partners, was noted as central to maximizing program function and provider uptake. Conclusions: Amid the COVID-19 pandemic, new programs are continuously being developed for implementation at the primary health care level. A better understanding of the factors that facilitate and prevent programmatic success will improve public health outcomes. Implementation is likely to be most successful when programs capitalize on endorsements from early adopters, tackle resource constraints, and foster greater communication among partners responsible for implementation.

Male circumcision decreases HIV acquisition by 60%, and antiretroviral therapy (ART) almost eliminates HIV transmission from HIV-positive people who are virally suppressed; however, coverage of these interventions has lagged behind targets. We aimed to assess whether community-based HIV testing with counsellor support and point-of-care CD4 cell count testing would increase uptake of ART and male circumcision.

South Africa currently has the greatest number of people with HIV globally. The country has not yet met its 95-95-95 goals, with different gaps in the HIV care cascade for women and men. This paper reports on a protocol to pilot test a couple-based intervention designed to improve women's antiretroviral therapy (ART) adherence and men's engagement in care in heterosexual couples living in the Vulindlela area of KwaZulu-Natal, South Africa. Study goals are two-fold: (1) assess the acceptability, feasibility, and fidelity of the experimental intervention, START Together, and (2) collect efficacy data on START Together for women's ART adherence, men's engagement in HIV care, and the couple's relationship functioning.

The correct author names are presented above. The original article has been corrected.