Two-Pronged Human Evaluation of ChatGPT Self-Correction in Radiology Report Simplification
This addresses the need to share radiology reports with patients by simplifying them, though it is incremental in applying existing prompting methods to a specific domain.
This study tackled the problem of automatically generating patient-friendly simplifications of technical radiology reports using large language models, finding that self-correction prompting was effective in producing high-quality simplifications as evaluated by radiologists and laypeople.
Radiology reports are highly technical documents aimed primarily at doctor-doctor communication. There has been an increasing interest in sharing those reports with patients, necessitating providing them patient-friendly simplifications of the original reports. This study explores the suitability of large language models in automatically generating those simplifications. We examine the usefulness of chain-of-thought and self-correction prompting mechanisms in this domain. We also propose a new evaluation protocol that employs radiologists and laypeople, where radiologists verify the factual correctness of simplifications, and laypeople assess simplicity and comprehension. Our experimental results demonstrate the effectiveness of self-correction prompting in producing high-quality simplifications. Our findings illuminate the preferences of radiologists and laypeople regarding text simplification, informing future research on this topic.