Objective: Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy.
Methods: ChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories-overconclusiveness, supplementary information, and incompleteness-were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines.
Results: Out of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%).
Conclusion: ChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings.
Keywords: Artificial intelligence; ChatGPT; Lumbar disk herniation with radiculopathy; North American Spine Society guidelines; Qualitative study.