Integrating Large Language Models Into Radiology Education: An Interpretation-Centric Framework for Enhanced Learning While Supporting Workflow.
Uloženo v:
| Název: | Integrating Large Language Models Into Radiology Education: An Interpretation-Centric Framework for Enhanced Learning While Supporting Workflow. |
|---|---|
| Autoři: | Lyo SK; Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania; Department of Radiology, Baptist Health, Miami, Florida; Member, Society of Imaging Informatics in Medicine Members in Training Committee; American College of Radiology Informatics Advisory Council. Electronic address: shawn.kt.lyo@gmail.com., Cook TS; Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania; Past Chair, Executive Committee for the Society of Imaging Informatics in Medicine; Director, 3-D and Advanced Imaging Laboratory, Center for Practice Transformation in Radiology at the University of Pennsylvania; Fellowship Director, Imaging Informatics at the University of Pennsylvania; Vice Chair, Practice Transformation in Radiology at the University of Pennsylvania. Electronic address: https://twitter.com/asset25. |
| Zdroj: | Journal of the American College of Radiology : JACR [J Am Coll Radiol] 2025 Nov; Vol. 22 (11), pp. 1271-1280. Date of Electronic Publication: 2025 Jul 12. |
| Způsob vydávání: | Journal Article |
| Jazyk: | English |
| Informace o časopise: | Publisher: Elsevier Country of Publication: United States NLM ID: 101190326 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1558-349X (Electronic) Linking ISSN: 15461440 NLM ISO Abbreviation: J Am Coll Radiol Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: New York, NY : Elsevier, c2004- |
| Výrazy ze slovníku MeSH: | Radiology*/education , Workflow* , Models, Educational* , Education, Medical, Graduate* , Language*, Humans ; Large Language Models |
| Abstrakt: | Radiology education is challenged by increasing clinical workloads, limiting trainee supervision time and hindering real-time feedback. Large language models (LLMs) can enhance radiology education by providing real-time guidance, feedback, and educational resources while supporting efficient clinical workflows. We present an interpretation-centric framework for integrating LLMs into radiology education subdivided into distinct phases spanning predictation preparation, active dictation support, and postdictation analysis. In the predictation phase, LLMs can analyze clinical data and provide context-aware summaries of each case, suggest relevant educational resources, and triage cases based on their educational value. In the active dictation phase, LLMs can provide real-time educational support through processes such as differential diagnosis support, completeness guidance, classification schema assistance, structured follow-up guidance, and embedded educational resources. In the postdictation phase, LLMs can be used to analyze discrepancies between trainee and attending reports, identify areas for improvement, provide targeted educational recommendations, track trainee performance over time, and analyze the radiologic entities that trainees encounter. This framework offers a comprehensive approach to integrating LLMs into radiology education, with the potential to enhance trainee learning while preserving clinical efficiency. (Copyright © 2025 The Authors. Published by Elsevier Inc. All rights reserved.) |
| Contributed Indexing: | Keywords: Artificial intelligence; large language models; precision education; radiology education |
| Entry Date(s): | Date Created: 20250714 Date Completed: 20251105 Latest Revision: 20251105 |
| Update Code: | 20251106 |
| DOI: | 10.1016/j.jacr.2025.07.003 |
| PMID: | 40659238 |
| Databáze: | MEDLINE |
Nájsť tento článok vo Web of Science | Abstrakt: | Radiology education is challenged by increasing clinical workloads, limiting trainee supervision time and hindering real-time feedback. Large language models (LLMs) can enhance radiology education by providing real-time guidance, feedback, and educational resources while supporting efficient clinical workflows. We present an interpretation-centric framework for integrating LLMs into radiology education subdivided into distinct phases spanning predictation preparation, active dictation support, and postdictation analysis. In the predictation phase, LLMs can analyze clinical data and provide context-aware summaries of each case, suggest relevant educational resources, and triage cases based on their educational value. In the active dictation phase, LLMs can provide real-time educational support through processes such as differential diagnosis support, completeness guidance, classification schema assistance, structured follow-up guidance, and embedded educational resources. In the postdictation phase, LLMs can be used to analyze discrepancies between trainee and attending reports, identify areas for improvement, provide targeted educational recommendations, track trainee performance over time, and analyze the radiologic entities that trainees encounter. This framework offers a comprehensive approach to integrating LLMs into radiology education, with the potential to enhance trainee learning while preserving clinical efficiency.<br /> (Copyright © 2025 The Authors. Published by Elsevier Inc. All rights reserved.) |
|---|---|
| ISSN: | 1558-349X |
| DOI: | 10.1016/j.jacr.2025.07.003 |