Artificial intelligence in hepatology: a comparative analysis of ChatGPT-4, Bing, and Bard at answering clinical questions
Bibliographic record
Abstract
Abstract Background and Aims The role of artificial intelligence (AI) in hepatology is rapidly expanding. However, the ability of AI chat models such as ChatGPT to accurately answer clinical questions remains unclear. This study aims to determine the ability of large language models (LLMs) to answer questions in hepatology, as well as compare the accuracy and quality of responses provided by different LLMs. Methods Hepatology questions from the Digestive Diseases Self-Education Platform were entered into three LLMs (OpenAI’s ChatGPT-4, Microsoft’s Bing, and Google’s Bard) between September 7 and 13, 2023. Questions were posed with and without multiple-choice answers. Generated responses were assessed based on accuracy and number of correct answers. Statistical analysis was performed to determine the number of correct responses per LLM per category. Results A total of 144 questions were used to query the AI models. ChatGPT-4’s accuracy was 62.3%, Bing’s accuracy was 53.5%, and Bard’s accuracy was 38.2% (P < .001) for multiple-choice questions. For open-ended questions, ChatGPT-4’s accuracy was 44.4%, Bing’s was 28.5%, and Bard’s was 21.4% (P < .001). ChatGPT-4 and Bing attempted to answer 100% of the questions, whereas Bard was unable to answer 11.8% of the questions. All 3 LLMs provided a rationale in addition to an answer, as well as counselling where appropriate. Conclusions LLMs demonstrate variable accuracy when answering clinical questions related to hepatology, though show comparable efficacy when presented with questions in an open-ended versus multiple choice (MCQ) format. Further research is required to investigate the optimal use of LLMs in clinical and educational contexts.
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 | 0.024 | 0.143 |
| 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 | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 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".