S752 Artificial Intelligence for Pre-Colonoscopy Patient Guidance: An Evaluation of ChatGPT's Accuracy Against Clinical Guidelines
Bibliographic record
Abstract
Introduction: The digital revolution has transformed healthcare. Patients use the internet and social media for medical advice. Artificial intelligence (AI)-driven chatbots like OpenAI's ChatGPT are becoming increasingly popular sources of medical advice. Given this increasing interest, it is paramount to ensure the reliability and accuracy of information provided by these AI platforms. This study sought to evaluate the ability of ChatGPT to dispense advice aligned with established guidelines in response to patient queries regarding pre-colonoscopy care. Methods: OpenAI's ChatGPT-4 was presented with a series of 25 patient-like questions, which covered four critical aspects of pre-colonoscopy care. These included the recommended diet, the protocol for bowel preparation, the management of cardiovascular medications (emphasizing anticoagulants, antiplatelets, anti-hypertensives, and diabetes medications), and antibiotic prophylaxis in patients with prosthetic heart valves, heart valve infection, and those with implanted devices like pacemakers, implantable cardioverter-defibrillator (ICDs), inferior vena cava (IVC) filters, or prior joint prosthetics. The responses from ChatGPT were compared with guidelines from esteemed organizations, including the European Society of Gastrointestinal Endoscopy (ESGE), United States Multi-Society Task Force (USMSTF), American College of Gastroenterology-Canadian Association of Gastroenterology (ACG-CAG), American College of Cardiology-American Heart Association (ACC-AHA), American Society for Gastrointestinal Endoscopy (ASGE), and the Australian Diabetes Society (ADS). Results: ChatGPT's responses to all 25 inquiries were found to align with the established guidelines. For queries regarding bowel preparation and diet, the responses were consistent with the ESGE and USMSTF guidelines. ChatGPT accurately mirrored the recommendations from the ACG-CAG for managing anticoagulants and antiplatelets. The AI's guidance on the management of cardiovascular medications and antibiotics prophylaxis conformed with ACC-AHA and ASGE guidelines, respectively. Furthermore, in terms of managing diabetes medications, ChatGPT's advice was in accordance with the ADS guidelines. Conclusion: OpenAI's ChatGPT-4 accurately provides answers to pre-colonoscopy questions consistent with medical society guidelines. While AI-powered chatbots like ChatGPT may serve to enhance patient education and autonomy, they should complement, not replace, personalized advice from healthcare professionals.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.048 | 0.395 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".