Assessing the Quality, Readability, and Acceptability of AI-Generated Information in Plastic and Aesthetic Surgery

Within plastic surgery, a patient's most commonly used first point of information before consulting a surgeon is the internet. Free-to-use artificial intelligence (AI) websites like ChatGPT (Generative Pre-trained Transformers) are attractive applications for patient information due to their ability to instantaneously answer almost any query. Although relatively new, ChatGPT is now one of the most popular artificial intelligence conversational software tools. The aim of this study was to evaluate the quality and readability of information given by ChatGPT-4 on key areas in plastic and reconstructive surgery.

The ten plastic and aesthetic surgery topics with the highest worldwide search volume in the 15 years were identified. These were rephrased into question format to create nine individual questions. These questions were then input into ChatGPT-4. The response quality was assessed using the DISCERN. The readability and grade reading level of the responses were calculated using the Flesch-Kincaid Reading Ease Index and Coleman-Liau Index. Twelve physicians working in a plastic and reconstructive surgery unit were asked to rate the clarity and accuracy of the answers on a scale of 1-10 and state 'yes or no' if they would share the generated response with a patient.

All answers were scored as poor or very poor according to the DISCERN tool. The mean DISCERN score for all questions was 34. The responses also scored low in readability and understandability. The mean FKRE index was 33.6, and the CL index was 15.6. Clinicians working in plastics and reconstructive surgery rated the questions well in clarity and accuracy. The mean clarity score was 7.38, and the accuracy score was 7.4.

This study found that according to validated quality assessment tools, ChatGPT-4 produced low-quality information when asked about popular queries relating to plastic and aesthetic surgery. Furthermore, the information produced was pitched at a high reading level. However, the responses were still rated well in clarity and accuracy, according to clinicians working in plastic surgery. Although improvements need to be made, this study suggests that language models such as ChatGPT could be a useful starting point when developing written health information. With the expansion of AI, improvements in content quality are anticipated.