Abstract
BACKGROUND: Radiomics and artificial intelligence have shown strong predictive capabilities in urinary stone research, particularly concerning stone composition, characteristics, and treatment outcomes. However, the association of stone radiomics and recurrence has not been well studied. This study aims to develop a machine learning model that combines radiomic features and clinical variables to pre-operatively predict kidney stones recurrence. METHODS: A total of 540 patients with kidney stones from the First Affiliated Hospital of Guangzhou Medical University were randomly divided into an internal training set (n = 378) and an internal test set (n = 162) in a 7:3 ratio. Additionally, 141 patients from Zhongda Hospital Southeast University served as an external test set. Clinical data were collected from all patients, and both univariate and multivariate analyses were performed to identify clinical predictors of kidney stone recurrence. Radiomic features were extracted from non-contrast CT scans to construct the optimal radiomic model. A radiomic scoring nomogram, integrating both independent clinical predictors and the radiomic model, was then developed to assess the risk of kidney stone recurrence. Time-to-recurrence analyses, including Kaplan-Meier estimation of stone-free survival, time-dependent ROC curves at 3, 5, and 7 years, and multivariable Cox regression, were performed to evaluate long-term predictive performance. RESULTS: Among the enrolled patients, 558 (81.9%) experienced recurrence, with 150 cases (26.9%,150/558) being symptomatic. Meanwhile, 123 patients (18.1%) did not experience recurrence. Median recurrence time was 3, 4, and 6 years in the internal training, internal test, and external test sets, respectively. The clinical model identified lower calyx stones and a history of stone disease as independent predictors of kidney stone recurrence. Of the 1688 radiomic features extracted from the kidney stones, 20 features were selected for the final model through the maximum relevance minimum redundancy and least absolute shrinkage and selection operator regression. The radiomic model demonstrated the area under the curve values of 0.797, 0.786, and 0.760 in the internal training, internal testing, and external testing, respectively, showing superior predictive performance compared to the clinical model alone. The combined nomogram model, integrating clinical predictors and radiomic features, further enhanced predictive accuracy with AUC values of 0.820, 0.824, and 0.786 in the respective cohorts. Kaplan-Meier analysis confirmed that patients stratified as high-risk by the nomogram had significantly lower stone-free survival of follow-up (log-rank P < 0.05), and the nomogram maintained robust discriminative performance at 3, 5, and 7 years across all cohorts. CONCLUSIONS: The nomogram, which combines clinical variables and radiomic features, appears to demonstrate potential as a predictive tool for assessing kidney stone recurrence during patient follow-up in this study. CLINICAL TRIAL NUMBER: Not applicable.