Abstract and Introduction
Purpose of Review: This review aims to shed light on recent applications of artificial intelligence in urologic oncology.
Recent Findings: Artificial intelligence algorithms harness the wealth of patient data to assist in diagnosing, staging, treating, and monitoring genitourinary malignancies. Successful applications of artificial intelligence in urologic oncology include interpreting diagnostic imaging, pathology, and genomic annotations. Many of these algorithms, however, lack external validity and can only provide predictions based on one type of dataset.
Summary: Future applications of artificial intelligence will need to incorporate several forms of data in order to truly make headway in urologic oncology. Researchers must actively ensure future artificial intelligence developments encompass the entire prospective patient population.
Artificial intelligence is often depicted in popular culture as robots with aberrantly acquired malevolent behaviors. Real-world applications of artificial intelligence, however, run the gamut from self-driving vehicles to curating social media streams, and evidently to healthcare. The boom in computational power and the advent of increased data acquisition through many different platforms have fueled the widespread use of artificial intelligence in everyday life. Artificial intelligence harnesses vast amounts of acquired data to achieve predetermined humanoid tasks like problem-solving on new, unseen data. These systems employ algorithms that may even autonomously modify themselves until the desired output is optimized, as with deep-learning. Artificial intelligence has the potential to improve evidence-based decisions, lower costs, and improve cancer outcomes; thus, urologists must remain informed of headway made in the field. Urologic oncology specifically is primed for widespread use of artificial intelligence, as the natural course of cancer care results in meticulous and longitudinal patient histories, detailed imaging, tissue biopsies, and even genomic information, providing a rich trove of data for analysis and application of artificial intelligence algorithms. The 2020 United States Congress is considering establishing a task force responsible for developing a national artificial intelligence research cloud. Additionally, the National Cancer Institute (NCI) listed artificial intelligence as one of three major emerging areas that pose exciting opportunities for cancer research in their proposed 2021 budget. Along with the Department of Energy, the NCI aims to develop new artificial intelligence supercomputing capabilities for precision oncology. In the private sector, seven of Forbes magazine's 50 Most Promising Artificial Intelligence Companies are health-related. One of these companies recently secured $10 million in funding and has already shown promise in selecting a cancer treatment for in-vivo testing.[8,9] Urologic oncology is likely to be privy to many of the innovations brought on by these private and government-funded ventures and may lighten burdens experienced by patients and clinicians alike.
This article contextualizes some of the recent literature on artificial intelligence applications to urologic oncology, highlighting its use in imaging, pathology, and genomics. We will also discuss integrating artificial intelligence into clinical practice, future artificial intelligence endeavors, and barriers to its widespread use.
Curr Opin Urol. 2020;30(6):748-753. © 2020 Wolters Kluwer Health, Inc.