Harnessing artificial intelligence in bariatric surgery: comparative analysis of ChatGPT-4, Bing, and Bard in generating clinician-level bariatric surgery recommendations
Bibliographic record
Abstract
BACKGROUND: The formulation of clinical recommendations pertaining to bariatric surgery is essential in guiding healthcare professionals. However, the extensive and continuously evolving body of literature in bariatric surgery presents considerable challenge for staying abreast of latest developments and efficient information acquisition. Artificial intelligence (AI) has the potential to streamline access to the salient points of clinical recommendations in bariatric surgery. OBJECTIVES: The study aims to appraise the quality and readability of AI-chat-generated answers to frequently asked clinical inquiries in the field of bariatric and metabolic surgery. SETTING: Remote. METHODS: Question prompts inputted into AI large language models (LLMs) and were created based on pre-existing clinical practice guidelines regarding bariatric and metabolic surgery. The prompts were queried into 3 LLMs: OpenAI ChatGPT-4, Microsoft Bing, and Google Bard. The responses from each LLM were entered into a spreadsheet for randomized and blinded duplicate review. Accredited bariatric surgeons in North America independently assessed appropriateness of each recommendation using a 5-point Likert scale. Scores of 4 and 5 were deemed appropriate, while scores of 1-3 indicated lack of appropriateness. A Flesch Reading Ease (FRE) score was calculated to assess the readability of responses generated by each LLMs. RESULTS: There was a significant difference between the 3 LLMs in their 5-point Likert scores, with mean values of 4.46 (SD .82), 3.89 (.80), and 3.11 (.72) for ChatGPT-4, Bard, and Bing (P < .001). There was a significant difference between the 3 LLMs in the proportion of appropriate answers, with ChatGPT-4 at 85.7%, Bard at 74.3%, and Bing at 25.7% (P < .001). The mean FRE scores for ChatGPT-4, Bard, and Bing, were 21.68 (SD 2.78), 42.89 (4.03), and 14.64 (5.09), respectively, with higher scores representing easier readability. CONCLUSIONS: LLM-based AI chat models can effectively generate appropriate responses to clinical questions related to bariatric surgery, though the performance of different models can vary greatly. Therefore, caution should be taken when interpreting clinical information provided by LLMs, and clinician oversight is necessary to ensure accuracy. Future investigation is warranted to explore how LLMs might enhance healthcare provision and clinical decision-making in bariatric 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 | 0.023 | 0.193 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| 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".