Symptoms for early diagnosis of chronic kidney disease in children - a machine learning-based score.

The objective of this study was to reveal the signs and symptoms for the classification of pediatric patients at risk of CKD using decision trees and extreme gradient boost models for predicting outcomes. A case-control study was carried out involving children with 376 chronic kidney disease (cases) and a control group of healthy children (n = 376). A family member responsible for the children answered a questionnaire with variables potentially associated with the disease. Decision tree and extreme gradient boost models were developed to test signs and symptoms for the classification of children. As a result, the decision tree model revealed 6 variables associated with CKD, whereas twelve variables that distinguish CKD from healthy children were found in the "XGBoost". The accuracy of the "XGBoost" model (ROC AUC = 0.939, 95%CI: 0.911 to 0.977) was the highest, while the decision tree model was a little lower (ROC AUC = 0.896, 95%CI: 0.850 to 0.942). The cross-validation of results showed that the accuracy of the evaluation database model was like that of the training. CONCLUSION: In conclusion, a dozen symptoms that are easy to be clinically verified emerged as risk indicators for chronic kidney disease. This information can contribute to increasing awareness of the diagnosis, mainly in primary care settings. Therefore, healthcare professionals can select patients for more detailed investigation, which will reduce the chance of wasting time and improve early disease detection. WHAT IS KNOWN: • Late diagnosis of chronic kidney disease in children is common, increasing morbidity. • Mass screening of the whole population is not cost-effective. WHAT IS NEW: • With two machine-learning methods, this study revealed 12 symptoms to aid early CKD diagnosis. • These symptoms are easily obtainable and can be useful mainly in primary care settings.

Strategy to Enable and Accelerate Kidney Transplant in Small Children and Results of the First 130 Transplants in Children ≤15 kg in a Single Center.

BACKGROUND: Proper care of young children in need of kidney transplant (KT) requires many skilled professionals and an expensive hospital structure. Small children have lesser access to KT. METHODS: We describe a strategy performed in Brazil to enable and accelerate KT in children ≤15 kg based on the establishment of one specialized transplant center, focused on small children, and cooperating with distant centers throughout the country. Actions on 3 fronts were implemented: (a) providing excellent medical assistance, (b) coordinating educational activities to disseminate expertise and establish a professional network, and (c) fostering research to promote scientific knowledge. We presented the number and outcomes of small children KT as a result of this strategy. RESULTS: Three hundred forty-six pediatric KTs were performed in the specialized center from 2009 to 2017, being 130 in children ≤15 kg (38%, being 41 children ≤10 kg) and 216 in >15 kg (62%). Patient survival after 1 and 5 years of the transplant was 97% and 95% in the "small children" group, whereas, in the "heavier children" group, it was 99% and 96% (P = 0.923). Regarding graft survival, we observed in the "small children" group, 91% and 87%, whereas in the "heavier children" group, 94% and 87% (P = 0.873). These results are comparable to the literature data. Groups were similar in the incidence of reoperation, vascular thrombosis, posttransplant lymphoproliferative disease, and estimated glomerular filtration rate. CONCLUSIONS: The strategy allowed an improvement in the number of KT in small children with excellent results. We believe this experience may be useful in other locations.

Inequality in pediatric kidney transplantation in Brazil.

BACKGROUND: The aim of this study was to describe the access and factors associated with kidney transplantation for children in different regions of Brazil. METHODS: We analyzed a cohort of 1211 children enrolled on the transplant list from January 2011 to December of 2013. We fitted regression models to investigate factors associated with: (a) undergoing kidney transplantation from a deceased donor, and (b) being removed from the waiting list. RESULTS: The incidence of transplantation was uneven across regions, with the lowest rate at 0.4 per million age-related population (pmarp) in the Midwest and the highest incidence rate of 8.3 cases pmarp in the South. Children from the North and the Midwest regions had a 3-4 times lower probability of undergoing a deceased donor transplant (p < 0.05). Apart from the geographic region, age of recipients and GDP influenced the outcome. The likelihood of undergoing transplantation was very low in the youngest children in the North and Midwest. The number of transplant centers was not associated with either outcome. CONCLUSIONS: Factors of inequality in transplantation in Brazil are of macroeconomic origin, but there is room to reduce inequalities. Training existing transplant center professionals in the care of children could diminish the discrepancies.