Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis
Bibliographic record
Abstract
Background: Artificial intelligence advancements have enabled large language models to significantly impact radiology education and diagnostic accuracy. Objective: This study evaluates the performance of mainstream large language models, including GPT-4, Claude, Bard, Tongyi Qianwen, and Gemini Pro, in radiology board exams. Methods: A comparative analysis of 150 multiple-choice questions from radiology board exams without images was conducted. Models were assessed on their accuracy for text-based questions and were categorized by cognitive levels and medical specialties using χ2 tests and ANOVA. Results: GPT-4 achieved the highest accuracy (83.3%, 125/150), significantly outperforming all other models. Specifically, Claude achieved an accuracy of 62% (93/150; P<.001), Bard 54.7% (82/150; P<.001), Tongyi Qianwen 70.7% (106/150; P=.009), and Gemini Pro 55.3% (83/150; P<.001). The odds ratios compared to GPT-4 were 0.33 (95% CI 0.18-0.60) for Claude, 0.24 (95% CI 0.13-0.44) for Bard, and 0.25 (95% CI 0.14-0.45) for Gemini Pro. Tongyi Qianwen performed relatively well with an accuracy of 70.7% (106/150; P=0.02) and had an odds ratio of 0.48 (95% CI 0.27-0.87) compared to GPT-4. Performance varied across question types and specialties, with GPT-4 excelling in both lower-order and higher-order questions, while Claude and Bard struggled with complex diagnostic questions. Conclusions: GPT-4 and Tongyi Qianwen show promise in medical education and training. The study emphasizes the need for domain-specific training datasets to enhance large language models' effectiveness in specialized fields like radiology.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".