E5091. The Impact of Artificial Intelligence in Resident Learning for Neuroradiology (and Beyond)
  1. Jee Moon; Temple University Hospital
  2. Insoo Kim; Temple University School of Medicine
  3. Gary Cohen; Temple University Hospital
  4. Perry Gerard; Westchester Medical Center
  5. Jared Meshekow; Temple University Hospital
This educational exhibit aims to evaluate the utilization of artificial intelligence (AI) and its impact on resident learning in diagnostic residency programs, with a focus in neuroradiology.

Educational Goals / Teaching Points
1) AI influences the resident learning experience. 2) When applied to radiology, AI programs encompass many benefits and pitfalls, which impacts resident education. 3) With adequate training, AI in neuroradiology can provide significant benefits in the educational setting.

Key Anatomic/Physiologic Issues and Imaging Findings/Techniques
The integration of AI software in neuroradiology has aided in improving the accuracy and efficiency of diagnosis. The implementation process involves selection of appropriate software, integration with imaging systems, and provision of training for residents. Resident education is necessary to best understand the capabilities and limitations of AI software. Overall, AI has assisted in resident learning and diagnostic accuracy, as well as the ability to identify various neurological pathologies. This educational exhibit will detail the utilization of popular AI systems such as AIDOC, RapidAI, and VisAI, and their respective advantages and influence on resident education.

AI software has improved diagnostic radiology programs and education by improving diagnostic accuracy, optimizing efficiency, and improving the resident educational experience in neuroradiology. However, more research is needed to evaluate the long-term impact of AI on resident learning in diagnostic residency programs.