Nomogram for predicting chronic kidney disease in children developed using artificial intelligence methods

Background. Modern artificial intelligence algorithms provide new insights into potential risk factors and modeling tools that predict the chronic course of kidney disease in children. Management of chronic kidney disease (CKD) is based on the use of tools that help the physician to timely predict the transition from acute kidney disease to chronic kidney disease and timely refer the child to a nephrologist. Aim. Тo develop a graphical tool to predict chronic kidney disease in children. Methods. The initial data for the development of the graphic tool (nomogram) were our own results published earlier. High quality prognostic model (ROC-AUC>90%) was constructed based on predictors of chronic kidney disease in children that we identified previously (proteinuria, haematuria, IL4 gene C598T polymorphic marker). Results. The constructed nomogram has a high prognostic value – with an accuracy of 98.9% to predict CKD in children. Conclusion: The developed nomogram can be used as a graphical assistant for physicians to predict the chronic course of the disease in patients with acute kidney disease.