Transplant a liver from an HIV-positive mother to her HIV-negative child to save the child's life. A unique case of living donor liver transplantation from an HIV-positive mother to her HIV-negative child in South Africa. Two aspects of this case are ground-breaking. First, it involves living donation by someone who is HIV-positive and second it involves controlled transplant of an organ from an HIV-positive donor into an HIV-negative recipient, with the potential to prevent infection in the recipient. Standard surgical procedure for living donor liver transplantation at our centre was followed. HIV-prophylaxis was administered preoperatively. Extensive, ultrasensitive HIV testing, over and above standard diagnostic assays, was undertaken to investigate recipient serostatus and is ongoing. Both mother and child are well, over 1 year posttransplantation. HIV seroconversion in our recipient was detected with serological testing at day 43 posttransplant. However, a decline in HIV antibody titres approaching undetectable levels is now being observed. No plasma, or cell-associated HIV-1 DNA has been detected in the recipient at any time-point since transplant. This case potentially opens up a new living liver donor pool which might have clinical relevance in countries where there is a high burden of HIV and a limited number of deceased donor organs or limited access to transplantation. However, our recipient's HIV status is equivocal at present and additional investigation regarding seroconversion events in this unique profile is ongoing.

Purpose of Review: To describe existing applications of artificial intelligence (AI) in sepsis management and the opportunities and challenges associated with its implementation in the paediatric intensive care unit. Recent Findings: Over the last decade, significant advances have occurred in the use of AI techniques, particularly in relation to medical image analysis. Increasingly, these techniques are being applied to a broad array of datasets. The availability of both structured and unstructured data from electronic health records, omics data and digital technologies (for example, portable sensors) is rapidly extending the range of applications for AI. These techniques offer the exciting potential to improve the recognition of sepsis and to help us understand the pathophysiological pathways and therapeutic targets of sepsis. Summary: Although AI has great potential to improve sepsis management in children, significant challenges need to be overcome before it can be successfully implemented to change healthcare delivery.

Objectives: The performance of mortality prediction models remain a challenge in lower- and middle-income countries. We developed an artificial neural network (ANN) model for the prediction of mortality in two tertiary pediatric intensive care units (PICUs) in South Africa using free to download and use software and commercially available computers. These models were compared to a logistic regression model and a recalibrated version of the Pediatric Index of Mortality 3.Design: This study used data from a retrospective cohort study to develop an artificial neural model and logistic regression model for mortality prediction. The outcome evaluated was death in PICU.Setting: Two tertiary PICUs in South Africa.Patients: 2,089 patients up to the age of 13 completed years were included in the study.Interventions: None.Measurements and Main Results: The AUROC was higher for the ANN (0.89) than for the logistic regression model (LR) (0.87) and the recalibrated PIM3 model (0.86). The precision recall curve however favors the ANN over logistic regression and recalibrated PIM3 (AUPRC = 0.6 vs. 0.53 and 0.58, respectively. The slope of the calibration curve was 1.12 for the ANN model (intercept 0.01), 1.09 for the logistic regression model (intercept 0.05) and 1.02 (intercept 0.01) for the recalibrated version of PIM3. The calibration curve was however closer to the diagonal for the ANN model.Conclusions: Artificial neural network models are a feasible method for mortality prediction in lower- and middle-income countries but significant challenges exist. There is a need to conduct research directed toward the acquisition of large, complex data sets, the integration of documented clinical care into clinical research and the promotion of the development of electronic health record systems in lower and middle income settings.

Objectives: Failures in identification, resuscitation and appropriate referral have been identified as significant contributors to avoidable severity of illness and mortality in South African children. In this study, artificial neural network models were developed to predict a composite outcome of death before discharge from hospital or admission to the PICU. These models were compared to logistic regression and XGBoost models developed on the same data in cross-validation.Design: Prospective, analytical cohort study.Setting: A single centre tertiary hospital in South Africa providing acute paediatric services.Patients: Children, under the age of 13 years presenting to the Paediatric Referral Area for acute consultations.Outcomes: Predictive models for a composite outcome of death before discharge from hospital or admission to the PICU.Interventions: None.Measurements and main results: 765 patients were included in the data set with 116 instances (15.2%) of the study outcome. Models were developed on three sets of features. Two derived from sequential floating feature selection (one inclusive, one parsimonious) and one from the Akaike information criterion to yield 9 models. All developed models demonstrated good discrimination on cross-validation with mean ROC AUCs greater than 0.8 and mean PRC AUCs greater than 0.53. ANN1, developed on the inclusive feature-et demonstrated the best discrimination with a ROC AUC of 0.84 and a PRC AUC of 0.64 Model calibration was variable, with most models demonstrating weak calibration. Decision curve analysis demonstrated that all models were superior to baseline strategies, with ANN1 demonstrating the highest net benefit.Conclusions: All models demonstrated satisfactory performance, with the best performing model in cross-validation being an ANN model. Given the good performance of less complex models, however, these models should also be considered, given their advantage in ease of implementation in practice. An internal validation study is now being conducted to further assess performance with a view to external validation.

Supervised machine learning models (SMLMs) are likely to be a prevalent approach in the literature on medical machine learning. These models have considerable potential to improve clinical decision-making through enhanced prediction and classification. In this review, we present an overview of SMLMs. We provide a discussion of the conceptual domains relevant to machine learning, model development, validation, and model explanation. This discussion is accompanied by clinical examples to illustrate key concepts.

Globally, policymakers often describe informal settlements and slums in terms of health problems. In this paper we trace the way housing and planning have been linked to health concerns in the history of South Africa and we assess post-apartheid literature on the topic. We note that researchers continue to rely on a biomedical understanding of the relationship between housing, planning and health although, we argue, the links between them are tenuous. We propose the capabilities approach as a way to understand this relationship. Reframing the relationship between housing, planning and health within the capabilities approach may improve the current understanding of this link. Aim: This paper discusses the historical links between housing, planning and health in South Africa, assesses post-apartheid policy, and reviews post-apartheid literature on the relationship between housing, planning and health. Results and conclusions: We find it is assumed that the link between housing, planning and health is a biomedical concern and not a social concern. We argue that scholars thinking about this relationship should consider the opportunities embedded in the capabilities approach to understand health outside the biomedical frame.