Predictive Modeling of Urinary Stone Composition Using Machine Learning and Clinical Data: Implications for Treatment Strategies and Pathophysiological Insights

Preoperative classification of urinary stones based on community detection

In the treatment of urinary stones, surgical intervention is crucial. Urinary stones composition and type directly affect surgical planning. However, research on preoperative stone composition analysis is limited. This paper aimed to predict urinary stones types preoperatively using clinical data. Data from 1020 patients, including stone composition, clinical biochemical indicators, and demographic information, were collected. A stone composition graph network was constructed using cosine similarity, with stone composition as nodes and biochemical/demographic data as node features. The Louvain community detection algorithm was utilized to divide the network into distinct communities for the classification of stone types, with the effectiveness of the partitioning evaluated by the Modularity score. Stone types were classified, and their distribution across genders and age groups was described. Clinical feature averages were calculated for each community, and patients were assigned to the most similar community. Six machine learning algorithms (RandomForest, GradientBoosting, SVM, KNN, Logistic Regression, XGBoost) were trained to predict stone types. Model performance was evaluated, and the importance of clinical features for prediction was ranked. Six stone types were identified (Modularity = 0.828), namely common COM (Class I), COM with minor AU (Class II), COM with high UA (Class III), COM containing MAP (Class IV), high CAP-MAP (Class V), and high COM-CAP containing DCPD (Class VI). Among males, Class III and Class I were most prevalent; among females, Class V and Class III were most prevalent (χ2 = 95.066, P < 0.001). Patients with Class IV stones were significantly older than those with Class I stones (P = 0.038). GradientBoosting showed the best prediction performance, with an Accuracy of 0.837, Precision of 0.840, Recall of 0.8366, F1 Score of 0.8368, and ROC-AUC area of 0.941. Significant clinical features for prediction included urine specific gravity, white blood cells, pH, and crystals. This paper first analyzed stone categories using a community detection algorithm and then predicted types using machine learning, providing a reference for preoperative surgical planning in urinary stones.

Predicting symptomatic kidney stones using machine learning algorithms: insights from the Fasa adults cohort study (FACS)

OBJECTIVES

To enhance the identification of individuals at risk of developing clinically significant kidney stones.

METHODS

In this study, data from the Fasa Adults Cohort Study were analyzed to explore factors linked to symptomatic and clinically significant kidney stone disease. After cleaning, 10,128 participants with 103 variables were studied. One outcome variable (presence of symptomatic kidney stones) and 102 predictor variables from surveys and tests were assessed. Five Machine learning (ML) algorithms (SVM, RF, KNN, GBM, XGB) were applied to examine kidney stone factors, with performance comparisons made. Data balancing was done using SMOTE, and metrics like accuracy, precision, sensitivity, specificity, F1 score, and AUC were evaluated for each algorithm.

RESULTS

The XGB model outperformed others with AUC of 0.60, while RF, GBM, SVC, and KNN had AUC values of 0.58, 0.57, 0.54, and 0.52. RF, GBM, and XGB showed good accuracy at 0.81, 0.81, and 0.77. Top predictors for kidney stones were serum creatinine, salt intake, hospitalization history, sleep duration, and BUN levels.

CONCLUSIONS

ML models show promise in evaluating an individual's risk of developing painful kidney stones and recommending early lifestyle changes to reduce this risk. Further research can enhance predictive accuracy and tailor interventions for better prevention/management.

Prediction of spontaneous distal ureteral stone passage using artificial intelligence

PURPOSE

Identifying factors predicting the spontaneous passage of distal ureteral stones and evaluating the effectiveness of artificial intelligence in prediction.

MATERIALS AND METHODS

The files of patients presenting with distal ureteral stones were retrospectively evaluated. Those who experienced spontaneous passage were assigned to Group P, while those who did not were assigned to Group N. Demographic and clinical data of both groups were compared. Then, logistic regression analysis was performed to determine the factors predicting spontaneous stone passage. Based on these factors, a logistic regression model was prepared, and artificial intelligence algorithms trained on the dataset were compared with this model to evaluate the effectiveness of artificial intelligence in predicting spontaneous stone passage.

RESULTS

When comparing stone characteristics and NCCT findings, it was found that the stone size was significantly smaller in Group P (4.9 ± 1.7 mm vs. 6.8 ± 1.4 mm), while the ureteral diameter was significantly higher in Group P (3.3 ± 0.9 mm vs. 3.1 ± 1.1 mm) (p < 0.05). Parameters such as stone HU, stone radiopacity, renal pelvis AP diameter, and perirenal stranding were similar between the groups. In multivariate analysis, stone size and alpha-blocker usage were significant factors in predicting spontaneous stone passage. The ROC analysis for the logistic regression model constructed from the significant variables revealed an area under the curve (AUC) of 0.835, with sensitivity of 80.1% and specificity of 68.4%. AI algorithms predicted the spontaneous stone passage up to 92% sensitivity and up to 86% specifity.

CONCLUSIONS

AI algorithms are high-powered alternatives that can be used in the prediction of spontaneous distal ureteral stone passage.