The Consistency and Quality of ChatGPT Responses Compared to Clinical Guidelines for Ovarian Cancer: A Delphi Approach
Bibliographic record
Abstract
INTRODUCTION: In recent years, generative Artificial Intelligence models, such as ChatGPT, have increasingly been utilized in healthcare. Despite acknowledging the high potential of AI models in terms of quick access to sources and formulating responses to a clinical question, the results obtained using these models still require validation through comparison with established clinical guidelines. This study compares the responses of the AI model to eight clinical questions with the Italian Association of Medical Oncology (AIOM) guidelines for ovarian cancer. MATERIALS AND METHODS: The authors used the Delphi method to evaluate responses from ChatGPT and the AIOM guidelines. An expert panel of healthcare professionals assessed responses based on clarity, consistency, comprehensiveness, usability, and quality using a five-point Likert scale. The GRADE methodology assessed the evidence quality and the recommendations' strength. RESULTS: A survey involving 14 physicians revealed that the AIOM guidelines consistently scored higher averages compared to the AI models, with a statistically significant difference. Post hoc tests showed that AIOM guidelines significantly differed from all AI models, with no significant difference among the AI models. CONCLUSIONS: While AI models can provide rapid responses, they must match established clinical guidelines regarding clarity, consistency, comprehensiveness, usability, and quality. These findings underscore the importance of relying on expert-developed guidelines in clinical decision-making and highlight potential areas for AI model improvement.
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 | 0.246 | 0.328 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.008 | 0.005 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.008 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".