Frontiers in Public Health (May 2024)

Using Google web search to analyze and evaluate the application of ChatGPT in femoroacetabular impingement syndrome

  • Yifan Chen,
  • Shengqun Zhang,
  • Ning Tang,
  • Daniel M. George,
  • Tianlong Huang,
  • JinPing Tang

DOI
https://doi.org/10.3389/fpubh.2024.1412063
Journal volume & issue
Vol. 12

Abstract

Read online

BackgroundChat Generative Pre-trained Transformer (ChatGPT) is a new machine learning tool that allows patients to access health information online, specifically compared to Google, the most commonly used search engine in the United States. Patients can use ChatGPT to better understand medical issues. This study compared the two search engines based on: (i) frequently asked questions (FAQs) about Femoroacetabular Impingement Syndrome (FAI), (ii) the corresponding answers to these FAQs, and (iii) the most FAQs yielding a numerical response.PurposeTo assess the suitability of ChatGPT as an online health information resource for patients by replicating their internet searches.Study designCross-sectional study.MethodsThe same keywords were used to search the 10 most common questions about FAI on both Google and ChatGPT. The responses from both search engines were recorded and analyzed.ResultsOf the 20 questions, 8 (40%) were similar. Among the 10 questions searched on Google, 7 were provided by a medical practice. For numerical questions, there was a notable difference in answers between Google and ChatGPT for 3 out of the top 5 most common questions (60%). Expert evaluation indicated that 67.5% of experts were satisfied or highly satisfied with the accuracy of ChatGPT’s descriptions of both conservative and surgical treatment options for FAI. Additionally, 62.5% of experts were satisfied or highly satisfied with the safety of the information provided. Regarding the etiology of FAI, including cam and pincer impingements, 52.5% of experts expressed satisfaction or high satisfaction with ChatGPT’s explanations. Overall, 62.5% of experts affirmed that ChatGPT could serve effectively as a reliable medical resource for initial information retrieval.ConclusionThis study confirms that ChatGPT, despite being a new tool, shows significant potential as a supplementary resource for health information on FAI. Expert evaluations commend its capacity to provide accurate and comprehensive responses, valued by medical professionals for relevance and safety. Nonetheless, continuous improvements in its medical content’s depth and precision are recommended for ongoing reliability. While ChatGPT offers a promising alternative to traditional search engines, meticulous validation is imperative before it can be fully embraced as a trusted medical resource.

Keywords