Development of prediction models of spontaneous ureteral stone passage through machine learning: Comparison with conventional statistical analysis

Abstract

Objectives To develop a prediction model of spontaneous ureteral stone passage (SSP) using machine learning and logistic regression and compare the performance of the two models. Indications for management of ureteral stones are unclear, and the clinician determines whether to wait for SSP or perform active treatment, especially in well-controlled patients, to avoid unwanted complications. Therefore, suggesting the possibility of SSP would help make a clinical decision regarding ureteral stones. Methods Patients diagnosed with unilateral ureteral stones at our emergency department between August 2014 and September 2018 were included and underwent non-contrast-enhanced computed tomography 4 weeks from the first stone episode. Predictors of SSP were applied to build and validate the prediction model using multilayer perceptron (MLP) with the Keras framework. Results Of 833 patients, SSP was observed in 606 (72.7%). SSP rates were 68.2% and 75.6% for stone sizes 5–10 mm and <5 mm, respectively. Stone opacity, location, and whether it was the first ureteral stone episode were significant predictors of SSP. Areas under the curve (AUCs) for receiver operating characteristic (ROC) curves for MLP, and logistic regression were 0.859 and 0.847, respectively, for stones <5 mm, and 0.881 and 0.817, respectively, for 5–10 mm stones. Conclusion SSP prediction models were developed in patients with well-controlled unilateral ureteral stones; the performance of the models was good, especially in identifying SSP for 5–10-mm ureteral stones without definite treatment guidelines. To further improve the performance of these models, future studies should focus on using machine learning techniques in image analysis.

Artificial intelligence in endourology: emerging technology for individualized care

“…Duration of symptoms was the most influential factor [30]. Several other groups have developed similar models to predict spontaneous stone passage from clinical variables using ANN and machine learning classifiers, with improved accuracies of 80–99%, sensitivities of 71–95%, and specificities of 63–100% (Table 3); several outperform traditional linear and logistic regression models [31,32 ▪ ,33,34].…”

Transforming urinary stone disease management by artificial intelligence-based methods: A comprehensive review

“…[ 32 ] Prediction of SSP Case-control Accuracy of 92.8% Other algorithms with lower performance Park et al. [ 33 ] Prediction of SSP Case-control AUCs of 0.859 (stones of <5 mm) and 0.881 (stones of 5–10 mm) AUC of 0.847 (stones of <5 mm) and 0.817 (stones of 5 mm–10 mm) Poulakis et al. [ 34 ] Prediction of lower pole clearance after ESWL Case-control Accuracy of 92% No comparator Gomha et al.…”

“…Park et al. [ 33 ] used a ML and LR model for SSP estimation. They retrospectively reviewed medical data from 833 patients who attended the emergency department with unilateral ureteral stones.…”

Imaging in stone diagnosis and surgical planning

“…Stone volume has been used to predict stone behavior with some success according to recent investigations. Three studies in the past 2 years have evaluated machine learning models to predict spontaneous ureteral stone passage based on volume, with areas under the curve of 0.83–0.85 [91,93,94 ▪ ]. This may also be applied to predict surgical efficacy.…”