Evaluating the Reliability of OpenAI's ChatGPT-4 in Providing Pre-colonoscopy Patient Guidance.

BACKGROUND

The integration of artificial intelligence (AI) in healthcare is a growing area of interest. This study aims to evaluate the reliability of OpenAI's ChatGPT-4.0 in providing pre-colonoscopy patient guidance, a critical aspect of gastrointestinal care where patient misconceptions and non-compliance are common challenges.

METHODS

The study employed a qualitative design to assess ChatGPT-4.0 against established clinical guidelines from various medical societies. Twenty-five patient-like queries encompassing dietary recommendations, bowel preparation, cardiovascular medications, antibiotic prophylaxis, and diabetes medications management were presented to ChatGPT-4.0. The AI's responses were independently evaluated and classified in terms of their alignment with the guidelines.

RESULTS

ChatGPT-4 demonstrated high accuracy, with all 25 sample queries' responses aligning with the established clinical guidelines. It provided precise guidance on dietary restrictions, medication management, and bowel preparation in accordance with the European Society of Gastrointestinal Endoscopy (ESGE), the U.S. Multi-Society Task Force on Colorectal Cancer (USMSTF), the American College of Gastroenterology-Canadian Association of Gastroenterology (ACG-CAG), the American College of Cardiology-American Heart Association (ACC-AHA), the American Society for Gastrointestinal Endoscopy (ASGE), and the Australian Diabetes Society (ADS).

CONCLUSION

The high degree of guideline adherence by ChatGPT-4.0 underscores its viability as a dependable resource for patient education. Despite its promising results, the study acknowledges limitations such as the structured nature of patient queries and the lack of real patient interactions. The findings suggest a potential role for AI in augmenting patient education and standardizing information dissemination in healthcare.