Artificial intelligence for assessment in competency-based medical education: current practices and future directions
Bibliographic record
Abstract
BACKGROUND: Competency-Based Medical Education (CBME) relies on frequent, competency-focused assessments, which can be challenging to implement consistently. Artificial Intelligence (AI) holds promise to improve assessment efficiency, objectivity, and feedback in CBME, but its use remains in early stages with limited understanding of current practices and evaluation methods. This study aims to map existing AI applications in CBME assessments to guide future work. METHODS: A comprehensive search was performed in MEDLINE (Ovid), EMBASE (Ovid), PsycINFO, and Scopus using tailored keywords and MeSH terms. Included studies focused on the deployment of AI for assessment within CBME, covering applications in generating, analyzing, or interpreting evaluation data across undergraduate, graduate, and continuing professional education. The PRISMA-ScR guidelines were used to ensure transparent reporting, and findings were synthesized following Levac et al.'s approach. RESULTS: Of the 1002 search results, 32 studies met the inclusion criteria. Key findings indicate a wide application of AI from surgical or procedural skill assessment, to clinical note assessment, communication assessment, feedback generation, projected trainee performance, and analysis of narrative feedback from supervisors. CONCLUSION: This review highlights potential advantages, such as timely evaluations, and challenges, such as lack of granularity, of AI integration. In conclusion, thoughtful integration of AI into competency-based medical education can complement traditional assessment methods and enhance learner outcomes, provided it is supported by robust infrastructure, ethical oversight, and collaborative policy development.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".