[The use of artificial intelligence, virtual, augmented, and mixed reality, and 3D technologies in the treatment of...

Urolithiasis is a common urological disease. Modern minimally invasive treatment methods require a high degree of precision. Artificial intelligence (AI), virtual reality (VR), augmented reality (AR), mixed reality (MR), and 3D modeling technologies are increasingly being introduced into clinical practice and medical education to improve the effectiveness of interventions.

To systematically analyze current data on the use of AI, VR, AR, MR, and 3D technologies in the diagnosis and treatment of urolithiasis and in medical education.

An analytical review of the literature was performed. Relevant publications were searched primarily in PubMed and The Journal of Urology. Particular emphasis was placed on studies published within the past 5 years, although earlier publications were also included to address historical and fundamental aspects.

These technologies demonstrate considerable potential in several key areas. 1) AI: prediction of treatment outcomes, including sepsis, percutaneous nephrolithotomy (PCNL) success, and spontaneous stone passage, with AUC values of up to 0.95; automated detection and segmentation of stones on CT and endoscopic images, with Dice similarity coefficient (DSC) values of up to 0.97; and determination of stone composition. 2) 3D technologies: preoperative 3D modeling and printing improve PCNL planning, shorten operative time, and increase the accuracy of percutaneous access. Uro Dyna-CT enables accurate intraoperative assessment of residual stone fragments. 3) AR/MR/VR: navigation systems reduce puncture time and the number of puncture attempts during PCNL. VR simulators, such as Uro Mentor, significantly improve endourological skills in trainees, reducing procedure time and the number of errors.

Integration of AI, VR, AR, MR, and 3D modeling into the management of urolithiasis facilitates treatment personalization, improves procedural accuracy, reduces the risk of complications, and enables the development of effective training systems. Further studies, particularly in complex clinical scenarios, and validation in real-world clinical practice are required before these technologies can be widely implemented.