Artificial Intelligence in Medicine: A Specialty-Level Overview of Emerging AI Trends

Abstract

Objective: Artificial intelligence (AI) is a turning point in medical advancement. Despite the burgeoning research in this field, there exists a general lack of overview of where AI is being most utilized. This study reviews and describes techniques and trends of AI in the major medical specialties.

Method: A literature search was conducted through PubMed in 2024 using two different search methods. Twenty-nine medical specialties were included, including all 24 major medical board specialties and five additional subspecialties.

Results: There were 143,578 publications involving AI identified with most these (87%) published in the last ten years (124,206) and 52% (74,239) in the last two years. Radiology and Pathology publications were the largest cohorts, 18% (25,319) and 17% (23,828), respectively. Plastic Surgery (1,053), Hepatobiliary (662), and Allergy/Immunology (449) were the least published. There has been a 10,859% growth rate in annual publications across all medical specialties, with Ophthalmology and Preventative Medicine being the fastest-growing areas of research despite Radiology and Pathology being the most researched to date.

Conclusion: This review underscores AI's profound impact on medical research, highlighting its significant growth and utilization across various specialties. AI's influence is most pronounced in Radiology and Pathology, but the substantial increase in publications in Ophthalmology and Preventative Medicine suggests new emerging areas of focus. The ongoing expansion of AI in medicine presents a promising horizon for addressing complex healthcare challenges, fostering a deeper and more comprehensive integration across all specialties.

Keywords: Artificial intelligence; Computer vision; Healthcare trends; Medical imaging; Multispecialty.

Figure 1.

Design method for group 1 and group 2 searches. In group 1, upon analysis of year-to-year publication data, results were separated into 4 nonmutually exclusive groups, filtering for the last 2, 5, 10, and 20 years. In group 2, only yields in the last 10 years were included.

Figure 2.

Proportions of medical specialties with publications regarding AI.

Figure 3.

Medical specialties and their respective gross number of publications regarding artificial intelligence in the last 20, 10, 5, and 2 years. Bar peaks represent cumulative publications over 20 years, with each bar section representing their own respective periods for publication. Dark blue (2021–2023), orange (2018–2020), green (2013–2017), and light blue (2003–2012).

Figure 4.

Timeline of medical specialties and the number of publications regarding AI per year between 2003 and 2023.

Figure 5.

Medical specialties and their respective number of publications with “artificial intelligence” in the title.

Figure 6.

Medical specialties and their respective number of clinical trials with “artificial intelligence” in the title.

Figure 7.

AI utilization in the medical industry after surveying 80 medical AI products. (A) Number of products per specialty or specific utilization. Primary care includes a variety of applications from internet triaging to wearable medical devices to monitor patient at-home. (B) Proportion of products utilizing computer vision in the medical imaging space, including live intra-operative and endoscopic technology.

Figure 8.

Demonstration of how computer vision AI technology works using the perspective of what the AI “sees” and what that would look like to humans. See Appendix 1 for full details. Created in BioRender. Popover J (2025) https://BioRender.com/d99s727.