Abstract
This study assesses the feasibility of Large Language Models like GPT-4 (OpenAI, San Francisco, CA, USA) to summarize interventional radiology (IR) procedural reports to improve layperson understanding and translate medical texts into multiple languages. 200 reports from eight categories were summarized using GPT-4. Readability was assessed with Flesch-Kincaid Reading Level (FKRL) and Flesch Reading Ease Score (FRES). Accuracy was assessed by 8 IRs. Summaries were translated into Spanish, Korean, Chinese, and Swahili and their accuracy were assessed by eight bilingual IRs. The original reports' FKRL of 10.7 and FRES of 41.9 improved to 7.0, and 73.0, respectively. Summaries were mostly accurate, with minimal misinformation. Translations introduced an increase in number of misinformation but no significant increase in critically wrong information. Layperson comprehension scores improved significantly from 2.5 to 4.3 out of 5 after summarization. Overall, GPT-4 enhanced report readability and comprehension, suggesting potential for broader application in improving patient communication.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call