With advancements in surgical technology along with procedural techniques, this article throws light on the latest developments and applications of artificial intelligence (AI), extended reality, 3D (three-dimensional) printing and robotics in percutaneous nephrolithotomy (PCNL).
This review highlights the applications of AI in PCNL over the past 2 years. Mostly studies have been reported on development of machine learning (ML) based predicting models and identification of stone composition using deep learning convolutional neural network (DL-CNN). But owing to the complexity of the models and lack of generalizability, it is still not incorporated in the routine clinical practice. Extended reality based simulation and training models have enabled trainees to enhance their skills and shorten the learning curve. Similar advantages have been reported with the use of 3D printed models when used to train young and novice endourologists to improve their skills in percutaneous access (PCA). Applications of robotics in PCNL look promising but are still in nascent stages.
Future research on PCNL should focus more on generalizability and adaptability of technological advancements in terms of training and improvement of patient outcomes.
Current opinion in urology. 2023 Jan 10 [Epub ahead of print]
B M Zeeshan Hameed, Milap Shah, Amelia Pietropaolo, Vincent De Coninck, Nithesh Naik, Andreas Skolarikos, Bhaskar K Somani
Department of Urology, Father Muller Medical College, Mangalore, Karnataka, India., iTRUE (International Training and Research in Uro-Oncology and Endourology) Group, Manipal, Karnataka., European Association of Urology - Young Academic Urologists (EAU-YAU) Urolithiasis and Endourology Working Group, Arnhem, The Netherlands., Department of Urology, AZ Klina, Brasschaat, Belgium., Department of Urology, National and Kapodistrian University of Athens, Athens, Greece., Department of Urology, University Hospital Southampton, Southampton, UK.