Artificial Intelligence and Machine Learning for Stone Management - 02/07/25

Doi : 10.1016/j.ucl.2025.04.011

Adithya Balasubramanian, MD ^a,^b,^⁎ , Hriday Bhambhvani, MD ^a,^b, Justin Lee, MD ^b, Ojas Shah, MD ^b
^a Department of Urology, Weill Cornell Medical College, Starr Pavilion, 525 East 68th Street 9th Floor, New York, NY 10065, USA
^b Department of Urology, Columbia Irving Medical Center, 161 Ft. Washington Avenue, 11th Floor, New York, NY 10032, USA

^∗Corresponding author. Department of Urology, Weill Cornell Medical College, Starr Pavilion, 525 East 68th Street 9th Floor, New York, NY 10065.Department of UrologyWeill Cornell Medical CollegeStarr Pavilion, 525 East 68th Street 9th FloorNew YorkNY10065

Resumen

Stone disease management is continuously evolving through the introduction of novel tools and technologies. Artificial intelligence and machine learning (ML) promise a new technological frontier for the enhancement of urolithiasis diagnosis, treatment, and prevention. This article focuses on the potential for ML algorithms to improve urolithiasis-directed imaging and enhance outcome prediction for spontaneous stone passage, ureteroscopy, shockwave lithotripsy, and percutaneous nephrolithotomy. We also discuss how ML optimizes stone composition evaluation and urinary abnormality detection. Ultimately, we aim to shed light on how ML-based innovations will help personalize treatment and improve the efficiency of stone disease management.

El texto completo de este artículo está disponible en PDF.

Keywords : Artificial intelligence, Machine learning, Kidney stones, Urolithiasis, Shock wave lithotripsy, Ureteroscopy, Percutaneous nephrolithotomy, Stone analysis