Recommender Systems in Health Professions Education: Protocol for a Scoping Review
Bibliographic record
Abstract
BACKGROUND: In health professions education (HPE), the concept of precision education is being explored, with the intention of tailoring learning experiences to the unique needs of learners. Recommender systems can assist academic decision-making. They can be used to personalize content delivery, suggest appropriate learning pathways, propose schedules, recommend suitable institutes, supervisors, and courses, and provide learner feedback. Given abundant learning resources, selecting the right one can be daunting. Recommender systems may address this challenge by offering tailored suggestions that align with learners' requirements and abilities. OBJECTIVE: This study aims to examine the literature related to the use of recommender systems in HPE. METHODS: This review will be conducted following the methodological framework proposed by Arksey and O'Malley. A comprehensive search will be conducted across the MEDLINE, CINAHL Plus with Full Text, ERIC, Academic Search Premier, and Web of Science databases, as well as gray literature sources including arXiv and Google Scholar. These searches will focus on the period from January 2000 to February 2025. In addition, backward and forward citation searching will be carried out. Articles will be screened independently by 2 reviewers; discrepancies resolved by consensus or a third reviewer. The selection process will involve an initial screening of titles and abstracts to identify potentially relevant articles. If initial screening is inconclusive, full-text review will ensure articles meet inclusion criteria. The main eligibility criteria for inclusion in the review are studies involving health professions students or educators, focusing on the concept, development, or application of recommender systems. Data extraction will be performed using a customized data charting template covering article, study, and recommender system details. The extracted data will be analyzed and displayed in both tabular and graphical formats, supplemented by a narrative interpretation. The findings will be synthesized by mapping the existing literature to identify key concepts, research gaps, and types of evidence, highlighting similarities and differences in how recommender systems are applied in HPE. This reporting will be in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Data extraction and analysis will be conducted using Covidence. RESULTS: The current phase of the study involves selecting studies for the scoping review as specified in this protocol. The search, screening, and data extraction will begin in February 2025. The results of the study and the submission of a manuscript for peer review are expected in the winter of 2025. CONCLUSIONS: This study aims to comprehensively map the extent of recommender systems in HPE. By identifying effective practices and existing gaps, it will serve as a valuable resource for health professions educators, enabling them to make informed decisions about integrating these systems into educational applications. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/69979.
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 | 0.079 | 0.105 |
| Meta-epidemiology (narrow) | 0.005 | 0.005 |
| Meta-epidemiology (broad) | 0.015 | 0.017 |
| Bibliometrics | 0.020 | 0.017 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.009 | 0.009 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.008 | 0.008 |
| Insufficient payload (model declined to judge) | 0.101 | 0.017 |
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".