Nageen Waseem, MBBS; Muhammad Saad Farooq, MD
WMJ. 2024;123(3):155-156.
The integration of artificial intelligence (AI) has become a game-changing element in the radiology landscape, offering immense potential to enhance patient care. However, it also poses substantial challenges in the training of radiology residents. As AI begins to assume more routine tasks, traditional training curricula must evolve to prepare residents for this new era.
Recent studies demonstrate that AI can significantly improve diagnostic accuracy and efficiency.1,2 Research by Ito et al shows AI integration advances in diagnosing cervical intraepithelial neoplasia (CIN2-3)2-3 and invasive cancer.1 Additionally, AI also can be utilized to diagnose colorectal cancer, leading to remarkable improvements in image-based diagnosis precision and enhanced detection of polyps and adenomas.2 This means that residents will need to acquire new skills to work effectively alongside AI. According to a recent systematic review, it has been observed that the current radiology resident curricula lack AI-related topics.3 This is concerning, as residents will need to understand the limitations and potential biases of AI algorithms, as well as how to integrate AI into their clinical decision-making processes.
To integrate AI into the curriculum, a 5-step approach can be followed. This includes forming an AI expert team, assessing residents’ knowledge, defining learning objectives, matching objectives with effective teaching strategies, and implementing and evaluating the curriculum.4
Some may argue that AI will replace radiologists altogether, making traditional training programs obsolete. However, AI assistants are likely to support radiologists by freeing them up from more complex tasks.5 A study introduced a novel AI approach, labeled “explainable AI,” which aims to strike a balance between human intellect and artificial intelligence, fostering collaboration and compliance with legal requirements.5
In conclusion, we urge all stakeholders in the field of radiology education to recognize the impact of AI on resident training and take proactive steps to adapt training programs accordingly. By including AI-related topics in curricula and prioritizing high-value tasks, we can ensure that residents are fully equipped to work effectively in this new era.
REFERENCES
- Ito Y, Miyoshi A, Ueda Y, et al. An artificial intelligence-assisted diagnostic system improves the accuracy of image diagnosis of uterine cervical lesions. Mol Clin Oncol. 2022;16(2):27. doi:10.3892/mco.2021.2460
- Uchikov P, Khalid U, Kraev K, et al. Artificial intelligence in the diagnosis of colorectal cancer: a literature review. Diagnostics (Basel). 2024;14(5):528. doi:10.3390/diagnostics14050528
- Schuur F, Rezazade Mehrizi MH, Ranschaert E. Training opportunities of artificial intelligence (AI) in radiology: a systematic review. Eur Radiol. 2021;31(8):6021-6029. doi:10.1007/s00330-020-07621-y
- van Kooten MJ, Tan CO, Hofmeijer EI, et al. A framework to integrate artificial intelligence training into radiology residency programs: preparing the future radiologist. Insights Imaging. 2024;15(1):15. doi:10.1186/s13244-023-01595-3
- Sorantin E, Grasser MG, Hemmelmayr A, et al. The augmented radiologist: artificial intelligence in the practice of radiology. Pediatr Radiol. 2022;52(11):2074-2086. doi:10.1007/s00247-021-05177-7