Artificial intelligence-based decision support system (AI-DSS) implementation in radiology residency: Introducing residents to AI in the clinical setting.

PURPOSE

The aim of this study was to evaluate residents' real-time experiences and perceptions in using artificial intelligence-based decision support system (AI-DSS) applications in the clinical setting and provide recommendations on how to improve artificial intelligence (AI) curriculums in residency programs.

METHODS

We implemented AI-DSS in our radiology workflow and integrated it into the radiology residency curriculum as a step in developing an AI-targeted curriculum. Fifteen senior residents were granted AI-DSS access for clinical use. Post-implementation, residents were anonymously surveyed to assess the utility of AI-DSS in addressing their learning needs and to determine the perceived impact of AI on their career choice and future professional development.

RESULTS

Most residents (91.6%) support incorporating AI into the curriculum and found AI-DSS useful in supplementary roles of triaging (83.3%) and troubleshooting (66.7%), rather than for diagnostic purposes of speed (41.7%), accuracy (33.3%), or diagnosis determination (16.7%). Residents found it useful to have earlier exposure to AI (66.7%), although the exact timeline in training for when to introduce residents to AI-DSS was debated and unclear. Most residents (83.3%) had a positive outlook on the impact of AI on radiology and 50.0% were excited to further their understanding of AI.

CONCLUSIONS

Our experience implementing AI-DSS in the clinical setting was a desirable and positive experience for our residents that will better prepare them as radiologists and help them capitalize on future opportunities in AI advancements. We hope our experience will provide incentive and guidance for other institutions to establish an AI program for their trainees.