Search

Background. Machine learning (ML) refers to computational algorithms designed to learn from patterns in data to provide insights or predictions related to that data. Objective. Multiple studies report the development of predictive models for triage or identification of critically ill children. In this study, we validate machine learning models developed in South Africa for the identification of critically ill children presenting to a tertiary hospital. Results. The validation sample comprised 267 patients. The event rate for the study outcome was 0.12. All models demonstrated good discrimination but weak calibration. Artificial neural network 1 (ANN1) had the highest area under the receiver operating characteristic curve (AUROC) with a value of 0.84. ANN2 had the highest area under the precision-recall curve (AUPRC) with a value of 0.65. Decision curve analysis demonstrated that all models were superior to standard strategies of treating all patients or treating no patients at a proposed threshold probability of 10%. Confidence intervals for model performance overlapped considerably. Post hoc model explanations demonstrated that models were logically coherent with clinical knowledge. Conclusions. Internal validation of the predictive models correlated with model performance in the development study. The models were able to discriminate between critically ill children and non-critically ill children; however, the superiority of one model over the others could not be demonstrated in this study. Therefore, models such as these still require further refinement and external validation before implementation in clinical practice. Indeed, successful implementation of machine learning in practice within the South African setting will require the development of regulatory and infrastructural frameworks in conjunction with the adoption of alternative approaches to electronic data capture, such as the use of mobile devices. [ABSTRACT FROM AUTHOR]

Purpose: Our objectives were to investigate the utility of 99m Tc-ethylenedicysteine-deoxyglucose (ECDG) in identifying active disease in the joints of patients with rheumatoid arthritis (RA), as well as to evaluate the biodistribution of this radiopharmaceutical., Methods: A prospective study was conducted at the Department of Nuclear Medicine of the University of the Free State/Universitas Academic Hospital in Bloemfontein, South Africa. Twenty-two participants from the rheumatology department diagnosed with RA according to the ACR/EULAR classification criteria were enrolled. Participants were injected with 20-25 mCi of 99m Tc-ECDG. Flow, blood pool, whole body, delayed static, and SPECT/CT images were acquired. Known sites of disease were qualitatively assessed for intensity of uptake, and disease severity was graded (Grade 0-3)., Results: Twenty-two participants were studied. The median (interquartile range) age was 59 (49-68) years, and the majority ( n  = 21; 95.5%) were females. There was abnormal increased uptake of 99m Tc-ECDG noted in majority of the sites of known disease, including unknown sites. SPECT/CT imaging localized radiotracer uptake specifically to the synovial space. Similar biodistribution of radiotracer was noted in all patients, irrespective of disease severity or fasting status., Conclusion: 99m Tc-ECDG can efficiently assess disease activity in the joints of patients with RA. It accumulates in sites of both clinical and subclinical disease and might be a very useful tool for the rheumatologist in the management of patients with RA., Competing Interests: Conflict of InterestEvbuomwan Osayande, Barend Jansen Van Rensburg, Engelbrecht Gerrit, Cathryn Driver, Mathys Labuschagne, Sempa Joseph, and Je'nine Horn-Lodewyk declare that they have no competing interests., (© The Author(s) 2023.)