This week on BackTable Urology, urologists Dr. Aditya Bagrodia (UC San Diego) and Dr. Giovanni Cacciamani, assistant professor of urology at the University of Southern California, discuss how artificial intelligence can improve urology practice and research.

---

SHOW NOTES

First, Dr. Cacciamani explains the origin of artificial intelligence (AI) and machine learning, which started with Alan Turing. AI learns from a large amount of data and adds on layers of knowledge as it increases the quantity of data it collects. For this reason, Dr. Cacciamani explains the principles behind algorithmic learning and the concept of generative AI. Large language models are examples of generative AI that can generate original videos, images, and text. Next, Dr. Cacciamani explains how his interest in AI started at USC. During the pandemic, he had free time and wanted to find a solution to the repetitive tasks that caused burnout in fellows, residents, attendings. He learned more about AI principles and established the first AI center of urology in the world at USC in order to integrate AI into academia.

Then, he and Dr. Bagrodia discuss the potential areas of AI applications, such as scribing, billing, constructing nomograms for early detection and prognosis, and imaging interpretations. Additionally, Dr. Cacciamani shares research about how AI is helping radiologists to improve the accuracy of diagnostic imaging. He encourages academic institutions to be involved in AI product development in biotech companies as well. Then, the doctors discuss the use of AI in surgery, which can serve as a co-pilot minimally invasive surgery. Dr. Cacciamani shares about the USC ICAROS lab, which explores ways to use AI to detect intraoperative complications and near miss events.

The episode ends with a discussion about the ethics of using AI in medicine. The doctors discuss concepts of data privacy, accountability, and explainability. Dr. Cacciamani emphasizes the importance of establishing multiple regulatory agencies to monitor AI use and create guidelines for generative AI in academia. Dr. Bagrodia agrees that AI should never take away from the physician-patient relationship, but in contrast, enhance the time the physician spends with the patient.

---

RESOURCES

“Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again” by Eric Topol

World Health Organization: Ethics and Governance of Artificial Intelligence for Health
https://www.who.int/publications/i/item/9789240029200

Cacciamani GE, Anvar A, Chen A, Gill I, Hung AJ. How the use of the artificial intelligence could improve surgical skills in urology: state of the art and future perspectives. Curr Opin Urol. 2021 Jul 1;31(4):378-384.
https://pubmed.ncbi.nlm.nih.gov/33965984/