The application of artificial intelligence (AI) in medicine has substantially grown in the past few years. Through a variety of applications, researchers are attempting to extend the use of AI to boost patient outcomes, save health care costs, and provide better patient care. Beginning in the 1970s, models were initially developed in the field of internal medicine to aid in the development of a clinical hypothesis or diagnosis based on previously recorded clinical data.¹ Today, we observe the extensive application of AI in a variety of medical disciplines, including arranging appointments or testing for patients, clinical apps suggesting diagnoses based on lab results and symptoms, and even robotic surgical systems in the operating room.

Outside of hospitals, AI is also utilized when assessing wearable technology. The Apple Watch can now detect abnormal cardiac rhythms and blood oxygen levels in newer models. For patients with epilepsy, the U.S. Food and Drug Administration approved the use of Embrace and Empatica wristbands in 2018. The bracelet uses electrodermal sensors to detect generalized tonic-clonic seizures and transmits this information together with the patient’s location to caregivers and medical professionals.²

A number of urology subspecialties have begun to advance and integrate AI into clinical practice. AI has been used in endourology to both predict stone composition and identify stones on CT and US imaging. In 2019 Parakh and colleagues were able to develop a neural network to identify a stone in the urinary system with 90% accuracy.³ A total of 535 adult individuals who were suspected of having urolithiasis were included in this retrospective analysis. The neural network assessed a total of 100 scans in order to accurately map the urinary tract and then the presence of a stone.

In pediatric urology, Bägli and colleagues utilized computerized artificial neural networks to assess outcomes after pyeloplasty using US imaging.⁴ All US scans had been assessed by a single radiologist, and a 4-layer network representing the 4 possible outcomes—significantly improved, improved, same, and worse—was built. In each of the 16 cases, the artificial neural network successfully identified the sonographic outcomes following pyeloplasty. As we observe the incorporation of AI in benign prostatic hyperplasia care, urologic oncology, urogynecology, as well as renal transplant, urologists continue to remain at the forefront of innovation in the field of AI.

A paradigm shift toward the use of AI in clinical decision-making and surgical practice is now occurring in the medical field.⁵ I believe that AI will progressively be incorporated into clinical recommendations as we continue to improve it and apply it to surgical practice. With greater technological advancements and continued research, it is surreal to be part of the growing field of urology.

Since 2002, the AUA Residents and Fellows Committee has represented the voice of trainee members. The Committee’s mission is to address the educational and professional needs of urology residents and fellows and promote engagement with the AUA. The Committee welcomes your input and feedback! To contact us, or inquire about ways to be involved, please email rescommittee@AUAnet.org.