Prediction of surgical necessity in children with ureteropelvic junction obstruction using machine learning.

Background: Hydronephrosis developing at the ureteropelvic junction due to obstruction poses clinical challenges as it has the potential to cause renal damage.

Aims: This study aims to evaluate how well machine learning models such, as XGBClassifier and Logistic Regression can be used to predict the need for treatment in patients, with hydronephrosis resulting from ureteropelvic junction obstruction.

Methods: Hydronephrosis was diagnosed in the medical records of patients from January 2015 to December 2020. These patients were classified into two groups: those who were not operated upon (n = 194) and those who had surgical procedures (n = 129). Details such as demographics, clinical presentations, and imaging findings were captured. XGBClassifier and Logistic Regression methods were employed to predict the requirement for an operation. The performance of the models was assessed based on ROC-AUC values, sensitivity, and specificity.

Results: The XGBClassifier algorithm gave the best prediction results with a ROC-AUC value of 0.977 and an accuracy rate of 95.4%. The Logistic Regression algorithm, on the other hand, offered the highest prediction during cross-validation. The presence of obstruction on scintigraphy, kidney size, anteroposterior diameter of the renal pelvic and parenchymal thickness observed in hydronephrotic kidney on USG have been identified as important predictive factors.

Conclusions: In predicting the requirement for surgery in cases of hydronephrosis due to obstruction, machine learning algorithms have shown high accuracy and sensitivity rates. Consequently, clinical decision support systems based on these algorithms may lead to better care management of patients and more accurate projections concerning the need for surgical intervention.

Trial registration number and date of registration: ESH/GOEK 2024/88-23/01/2024.