There is a paucity of air quality data in sub-Saharan African countries to inform science driven air quality management and epidemiological studies. We investigated the use of available remote-sensing aerosol optical depth (AOD) data to develop spatially and temporally resolved models to predict daily particulate matter (PM₁₀) concentrations across four provinces of South Africa (Gauteng, Mpumalanga, KwaZulu-Natal and Western Cape) for the year 2016 in a two-staged approach. In stage 1, a Random Forest (RF) model was used to impute Multiangle Implementation of Atmospheric Correction AOD data for days where it was missing. In stage 2, the machine learner algorithms RF, Gradient Boosting and Support Vector Regression were used to model the relationship between ground-monitored PM₁₀ data, AOD and other spatial and temporal predictors. These were subsequently combined in an ensemble model to predict daily PM₁₀ concentrations at 1 km × 1 km spatial resolution across the four provinces. An out-of-bag R² of 0.96 was achieved for the first stage model. The stage 2 cross-validated (CV) ensemble model captured 0.84 variability in ground-monitored PM₁₀ with a spatial CV R² of 0.48 and temporal CV R² of 0.80. The stage 2 model indicated an optimal performance of the daily predictions when aggregated to monthly and annual means. Our results suggest that a combination of remote sensing data, chemical transport model estimates and other spatiotemporal predictors has the potential to improve air quality exposure data in South Africa's major industrial provinces. In particular, the use of a combined ensemble approach was found to be useful for this area with limited availability of air pollution ground monitoring data.

The sustainable operation of ambient air quality monitoring stations in developing countries is not always possible. Intermittent failures and breakdowns at air quality monitoring stations often affect the continuous measurement of data as required. These failures and breakdowns result in missing data. This study aimed to impute NO₂, SO₂, O₃, and PM 10 to produce complete data sets of daily average exposures from 2010 to 2017. Models were built for (a) an individual pollutant at a monitoring station, (b) a combined model for the same pollutant from different stations, and (c) a data set with all the pollutants from all the monitoring stations. This study sought to evaluate the efficacy of the Multiple Imputation by Chain Equations (MICE) algorithm in successfully imputing air quality data that are missing at random. The application of classification and regression trees (CART) analysis using the MICE package in the R statistical programming language was compared with the predictive mean matching (PMM) method. The CART method performed better, with the pooled R-squared statistics of the imputed data ranging from 0.3 to 0.7, compared to a range of 0.02 to 0.25 for PMM. The MICE algorithm successfully resolved the incompleteness of the data. It was concluded that the CART method produced better reliable data than the PMM method. However, in this study, the pooled R² values were accurate for NO₂, but not so much for other pollutants.

There are unanswered questions with regards to acute respiratory outcomes, particularly asthma, due to environmental exposures. In contribution to asthma research, the current study explored a computational intelligence paradigm of artificial neural networks (ANNs) called self-organizing maps (SOM). To train the SOM, air quality data (nitrogen dioxide, sulphur dioxide and particulate matter), interpolated to geocoded addresses of asthmatics, were used with clinical data to classify asthma outcomes. Socio-demographic data such as age, gender and race were also used to perform the classification by the SOM. All pollutants and demographic traits appeared to be important for the correct classification of asthma outcomes. Age was more important: older patients were more likely to have asthma. The resultant SOM model had low quantization error. The study concluded that Kohonen self-organizing maps provide effective classification models to study asthma outcomes, particularly when using multidimensional data. SO₂ was concluded to be an important pollutant that requires strict regulation, particularly where frail subpopulations such as the elderly may be at risk.

Background: Acute kidney injury remains one of the most prevalent complications in hospitalised patients, with an especially high incidence in the paediatric population. Its diverse pathophysiological aetiologies present significant challenges in its clinical diagnosis. Relying solely on serum creatinine levels and urine output measurements for diagnosis has been shown to be inadequate, particularly for early detection of the disease. The wide range of disease manifestations highlights the importance of exploring diagnostic techniques that can identify patients at risk before disease progression occurs, thereby allowing for the implementation of timely corrective measures. Point-of-care ultrasound is a valuable technique with the potential to aid in the early identification of at-risk patients. Objective: To describe ultrasound parameters associated with the development of acute kidney injury or renal dysfunction in the hospitalised paediatric patient, and to examine their association with its development. This will include an analysis of the specific ultrasound features that may predict or be associated with the occurrence of acute kidney injury, as well as their potential role in identifying at-risk paediatric patients, facilitating timely interventions to mitigate further kidney damage. Methods: A systematic review of existing literature will be performed to assess ultrasound modalities currently associated with the diagnosis of acute kidney injury in the paediatric population. The protocol for this review has been registered with PROSPERO (CDR42024547614) and was developed in accordance with the guidelines set forth by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols (PRISMA). A comprehensive search of scientific literature will be conducted across PubMed, Scopus, Cochrane Library, and CINAHL databases. The data search will be performed independently by the primary researchers (GL and NA), with any disagreements resolved by the third and fourth researchers (MK, PMC). The COVIDENCE Systematic Review Software® 2024 will be utilised for article exportation, review, and data extraction. The QUADAS-2 tool will be applied to assess the risk of bias in the diagnostic accuracy of the studies included in the review. Conclusion: This protocol outlines a systematic review designed to evaluate the application of ultrasonography in identifying paediatric patients at risk of developing acute kidney injury and other forms of renal dysfunction. The review will critically assess the effectiveness of ultrasound techniques, including point-of-care ultrasound, in identifying acute kidney injury in children, with a particular emphasis on early detection. The findings from this review will contribute to a deeper understanding of the role of ultrasonography in clinical practice, with the potential to improve patient outcomes through earlier intervention. The ultrasound techniques identified, including Doppler imaging and flow measurements, will be employed in a subsequent prospective study within the paediatric population to evaluate their role, sensitivity, and accuracy.

Background: Neonatal anaemia is common, particularly in preterm and critically ill infants, and is frequently managed with red blood cell transfusion despite well-recognised associated morbidity. Patient blood management strategies aim to reduce transfusion exposure, and tranexamic acid (TXA) has emerged as a potential pharmacological adjunct. However, evidence supporting the use of TXA in neonates remains limited. Methods: We conducted a comprehensive narrative review of peer-reviewed literature published between January 2015 and December 2025. Searches were performed in PubMed/MEDLINE, Scopus, and Web of Science using Medical Subject Headings and keyword combinations related to neonates, children, blood conservation strategies, and TXA. Eligible studies included systematic reviews, randomised controlled trials, observational cohort studies, and case reports evaluating TXA use in paediatric and neonatal populations across surgical, critical care, and selected medical contexts. Adult-only and animal studies were excluded. Findings were synthesised qualitatively. Results: Seventeen studies met the inclusion criteria. Evidence consistently supports the use of TXA as part of multimodal blood-conservation strategies in elective paediatric surgery with predictable bleeding, particularly in craniosynostosis surgery, where reductions in blood loss and transfusion requirements were observed. In paediatric cardiac surgery and life-threatening haemorrhage, TXA may reduce bleeding and early mortality; however, benefits were less consistent in neonates. Evidence for TXA use in neonatal medical indications was sparse and inconclusive. Safety data suggest a dose- and context-dependent risk of seizures, with limited neonatal-specific adverse event reporting. Conclusion: TXA shows promise as a pharmacological blood conservation strategy in selected paediatric surgical populations, but evidence supporting its routine use in neonates remains limited. The unique haemostatic physiology, immature renal clearance, and neurological vulnerability of neonates necessitate cautious use. High-quality neonatal pharmacokinetic studies and prospective trials are urgently needed to define optimal dosing, safety, and efficacy before widespread adoption in neonatal practice.