A Blinded Comparison of Three Generative Artificial Intelligence Chatbots for Orthopaedic Surgery Therapeutic Questions
Bibliographic record
Abstract
Objective To compare the quality of responses from three chatbots (ChatGPT, Bing Chat, and AskOE) across various orthopaedic surgery therapeutic treatment questions. Design We identified a series of treatment-related questions across a range of subspecialties in orthopaedic surgery. Questions were "identically" entered into one of three chatbots (ChatGPT, Bing Chat, and AskOE) and reviewed using a standardized rubric. Participants Orthopaedic surgery experts associated with McMaster University and the University of Toronto blindly reviewed all responses. Outcomes The primary outcomes were scores on a five-item assessment tool assessing clinical correctness, clinical completeness, safety, usefulness, and references. The secondary outcome was the reviewers' preferred response for each question. We performed a mixed effects logistic regression to identify factors associated with selecting a preferred chatbot. Results Across all questions and answers, AskOE was preferred by reviewers to a significantly greater extent than both ChatGPT (P<0.001) and Bing (P<0.001). AskOE also received significantly higher total evaluation scores than both ChatGPT (P<0.001) and Bing (P<0.001). Further regression analysis showed that clinical correctness, clinical completeness, usefulness, and references were significantly associated with a preference for AskOE. Across all responses, there were four considered as having major errors in response, with three occurring with ChatGPT and one occurring with AskOE. Conclusions Reviewers significantly preferred AskOE over ChatGPT and Bing Chat across a variety of variables in orthopaedic therapy questions. This technology has important implications in a healthcare setting as it provides access to trustworthy answers in orthopaedic surgery.
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 | 0.067 | 0.247 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".