ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports
LMU Klinikum · German Center for Lung Research · +2 more institutions
Abstract
Abstract Objectives To assess the quality of simplified radiology reports generated with the large language model (LLM) ChatGPT and to discuss challenges and chances of ChatGPT-like LLMs for medical text simplification. Methods In this exploratory case study, a radiologist created three fictitious radiology reports which we simplified by prompting ChatGPT with “Explain this medical report to a child using simple language.” In a questionnaire, we tasked 15 radiologists to rate the quality of the simplified radiology reports with respect to their factual correctness, completeness, and potential harm for patients. We used Likert scale analysis and inductive free-text categorization to assess the quality of the…
Citation impact
- FWCI
- 83.48
- Percentile
- 100%
- References
- 22
Authors
11- KJKatharina JeblickCorresponding
LMU Klinikum, German Center for Lung Research, Munich Center for Machine Learning, Ludwig-Maximilians-Universität München
- BSBalthasar Schachtner
LMU Klinikum, Munich Center for Machine Learning, Ludwig-Maximilians-Universität München
- JDJakob Dexl
LMU Klinikum, Munich Center for Machine Learning, Ludwig-Maximilians-Universität München
- AMAndreas Mittermeier
LMU Klinikum, Munich Center for Machine Learning, Ludwig-Maximilians-Universität München
- ATAnna Theresa Stüber
LMU Klinikum, Munich Center for Machine Learning, Ludwig-Maximilians-Universität München
Topics & keywords
- Medicine
- Radiology
- Likert scale
- Quality (philosophy)
- Interventional radiology
- Harm
- Relevance (law)
- Grading (engineering)
- Quality Education