Machine learning approaches to predict 24-hour urine collection results based on self-reported beverage intake.

OBJECTIVE: Repeated 24-hour urine collections are used to evaluate risk factors for recurrence of kidney stones but are costly and burdensome. This study aimed to develop and validate machine learning models to predict 24-hour urine volume from patients' self-reported beverage intake and classify compliance with guidelines for preventing kidney stone recurrence. DESIGN AND METHODS: Data were extracted from two clinical trials: trial 1 (development dataset: n=380) and trial 2 (validation dataset: n=142). Regression models (linear regression, regression trees, random forest, support vector machine) were trained to predict continuous 24-hour urine volume, while classification models (logistic regression, classification trees, random forest, support vector machine) were trained to predict low urine volume (<2L). RESULTS: No differences were found between the development and validation datasets on demographic characteristics, 24-hour urine volume, or self-reported beverage intake. Random Forest model performed best in predicting 24-hour urine volume on both training and external validation datasets. Random Forest also excelled at predicting high urine output in the development dataset but with overfitting risks. All classification models had high negative predictive values, reliably identifying individuals with low urine volume. CONCLUSION: Machine learning models based on self-reported beverage intake and demographic characteristics can predict 24-hour urine volume in kidney stone patients. They reliably identified patients with >2 L/d urine output but perform poorly for identifying those with low output volumes. Additional inputs should be considered to improve prediction and help identify patients who would benefit from targeting fluid intake for stone prevention.