Effect of an Artificial Intelligence Chest X-Ray Disease Prediction System on the Radiological Education of Medical Students: A Pilot Study
Bibliographic record
Abstract
BACKGROUND We aimed to evaluate the feasibility of implementing Chester, a novel web-based chest X-ray (CXR) interpretation artificial intelligence (AI) tool, in the medical education curriculum and explore its effect on the diagnostic performance of undergraduate medical students. METHODS Third-year trainees were randomized in experimental (N=16) and control (N=16) groups and stratified for age, gender, confidence in CXR interpretation, and prior experience. Participants filled a pre-intervention survey, a test exam (Exam1), a final exam (Exam2), and a post-intervention survey. The experimental group was allowed to use Chester during Exam1 while the control group could not. All participants were forbidden from using any resources during Exam2. The diagnostic interpretation of a fellowship-trained chest radiologist was used as the standard of reference. Chester’s performance on Exam1 was 60%. A five-point Likert scale was used to assess students’ perceived confidence before/after the exams as well as Chester’s perceived usefulness. RESULTS Using a mixed model for repeated measures (MMRM), it was found that Chester did not have a statistically significant impact on the experimental group’s diagnostic performance nor confidence level when compared to the control group. The experimental group rated Chester’s usefulness at 3.7/5, its convenience at 4.25/5, and their likelihood to reuse it at 4.1/5. CONCLUSION Our experience highlights the interest of medical students in using AI tools as educational resources. While the results of the pilot project are inconclusive for now, they demonstrate proof of concept for a repeat experiment with a larger sample and establish a robust methodology to evaluate AI tools in radiological education. Finally, we believe that additional research should be focused on the applications of AI in medical education so students understand this new technology for themselves and given the growing trend of remote learning.
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 | 0.005 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".