Evaluating the Reliability of OpenAI’s ChatGPT-4 in Providing Pre-colonoscopy Patient Guidance
Bibliographic record
Abstract
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.
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 | 0.062 | 0.250 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".