Attention: Restrictions on use of AUA, AUAER, and UCF content in third party applications, including artificial intelligence technologies, such as large language models and generative AI.
You are prohibited from using or uploading content you accessed through this website into external applications, bots, software, or websites, including those using artificial intelligence technologies and infrastructure, including deep learning, machine learning and large language models and generative AI.

FROM THE RESIDENTS & FELLOWS COMMITTEE: Use of Artificial Intelligence in Urology

By: Karan K. Arora, MD, Mayo Clinic, Phoenix, Arizona | Posted on: 09 Mar 2023

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.

  1. Schwartz WB, Patil RS, Szolovits P. Artificial intelligence in medicine. N Engl J Med. 1987;316(11):685-688.
  2. Regalia G, Onorati F, Lai M, Caborni C, Picard RW. Multimodal wrist-worn devices for seizure detection and advancing research: focus on the Empatica wristbands. Epilepsy Res. 2019;153:79-82.
  3. Parakh A, Lee H, Lee J, Eisner BH, Sahani DV, Do S. Urinary stone detection on CT images using deep convolutional neural networks: evaluation of model performance and generalization. Radiol Artif Intell. 2019;1(4):e180066.
  4. Bägli DJ, Agarwal SK, Venkateswaran S, et al. Artificial neural networks in pediatric urology: prediction of sonographic outcome following pyeloplasty. J Urol. 1998;160(3 Pt 2):980-983.
  5. Shah M, Naik N, Somani BK, Hameed BM. Artificial intelligence (AI) in urology—current use and future directions: an iTRUE study. Turk J Urol. 2020;46(Suppl 1):S27-S39.

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.

advertisement

advertisement