This paper is in the following e-collection/theme issue:

Scoping Review Protocols (250) e-Learning and Digital Medical Education (901) mHealth in Medical Education and Training (121) New Methods and Approaches in Medical Education (373) Precision Medicine (159) Machine Learning (2072) Artificial Intelligence (AI) in Medical Education (182)

Published on in Vol 14 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/69979, first published .
Recommender Systems in Health Professions Education: Protocol for a Scoping Review

Recommender Systems in Health Professions Education: Protocol for a Scoping Review

Recommender Systems in Health Professions Education: Protocol for a Scoping Review

Authors of this article:

Padraig Mark Healy1, 2 Author Orcid Image ;   Colm O'Tuathaigh1 Author Orcid Image ;   Ciara Heavin3 Author Orcid Image ;   Nora McCarthy1 Author Orcid Image ;   Syed Latifi2 Author Orcid Image
Article Authors Cited by Tweetations Metrics

    Protocol

    1School of Medicine, Medical Education Unit, University College Cork, Cork, Ireland

    2Division of Medical Education, Weill Cornell Medicine – Qatar, Doha, Qatar

    3Cork University Business School, University College Cork, Cork, Ireland

    Corresponding Author:

    Padraig Mark Healy, BSc, MSc

    School of Medicine

    Medical Education Unit

    University College Cork

    Brookfield Health Sciences Complex, College Road

    Cork, T12 V821

    Ireland

    Phone: 353 (0)21 490 1575

    Email: pmh2003@qatar-med.cornell.edu


    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

    JMIR Res Protoc 2025;14:e69979

    doi:10.2196/69979

    Keywords

    recommender systems; precision education; personalized learning; health professions education; HPE 


    Overview

    The magnitude of medical information and learning resources available online, while advantageous to the user, can also be overwhelming [1-4]. The sheer volume and varying quality can lead to information overload [5-7]. This can be a stressor, making it difficult for one to evaluate the relevance and quality of the information available, ultimately impacting the individual and inhibiting effective decision-making [8-10]. In addition, there are concerns about the credibility and validity of medical and health-related information found on widely used information-sharing platforms [11,12]. A systematic review by Wang et al [13] showed an increasing trend in health-related misinformation on topics such as vaccination, Ebola, and Zika virus. Coincidentally, the article was published a month before the COVID-19 pandemic started making headlines, which itself garnered attention from online “misinformation superspreaders” [14]. Furthermore, YouTube has been identified as a source of misinformation regarding the human papillomavirus vaccine [15]. Studies have also highlighted the spread of cancer misinformation on Facebook [16,17], misinformation related to e-cigarettes and nicotine on Twitter [18], and misinformation about rheumatoid arthritis across various platforms [19]. These issues are problematic because they can lead to public health risks, such as vaccine hesitancy [20], poor disease management [21], and the spread of harmful health practices [22].

    In response to these challenges of information overload and the accuracy of information, recommender systems are emerging as a powerful tool [23-25]. Recommender systems, also known as recommendation systems, platforms, engines, or algorithms, are essential tools in information filtering and personalization [26,27]. Their use can improve user experiences, boost engagement, and aid decision-making [28]. A seminal article by Resnick and Varian [29] characterized a recommender system as one in which recommendations are provided as inputs by people, which the system then aggregates and directs to appropriate recipients. Burke [30] described them as systems that generate tailored recommendations or assist users in a personalized way to choose from an array of options. These systems use algorithms to tailor recommendations by filtering, curating content, and guiding the user toward pertinent resources [31,32]. Thus, recommender systems play a pivotal role in alleviating the burden of information overload.

    Recommender systems have already seamlessly integrated into our everyday lives. Serving as intelligent guides, they suggest relevant content to users in contexts ranging from social media to e-commerce and streaming services. According to a report by MacKenzie et al [33], 35% of Amazon purchases and 75% of Netflix viewing choices can be attributed to recommendations by such algorithms. In recent years, approaches such as machine learning, natural language processing, and deep learning [34-37] have brought advancements to recommender systems. These systems are not only prevalent in commercial applications but are also increasingly being adopted in educational settings [38,39]. A recent systematic review by Thongchotchat et al [40] found that while attribute- or characteristic-type recommender systems dominate education, there is an emerging trend of varied systems, including hints, clues, prompts, and tutoring, but these are in the early stages and require exploration and development. Combining theories of learning styles may enhance the flexibility and effectiveness of recommendations [40]. A recent bibliometric analysis [39] noted an increase in research dedicated to exploring recommendation techniques with the objective of enhancing the accuracy of recommendations made by educational recommender systems, driven by the ever-increasing amount of available learning resources. Large language models (LLMs) now enhance conversational recommender systems by leveraging their contextual understanding, potentially improving recommendation quality [41,42]. Recommender systems fall under 1 of 4 types of filtering approaches [43-45]. Table 1 provides a detailed description of each type, including its respective strengths and limitations, as well as examples.

    Table 1. Comparison of recommender system filtering types.
    Filtering typeDescriptionStrengthsLimitationsExamples
    ContentA recommendation is made based on user characteristics or past behavior (ie, a user’s data) [46].
    • Gray sheep: adapts to users with unique profiles [47].
    • Recommendations can be shared without the user sharing a profile, thereby ensuring privacy [48].
    • Can recommend new, rare, or unpopular items [49].
    • Lack of serendipity: may not suggest unexpected items, as it does not rely on data from other users [50].
    • New user problem: difficult to make recommendations in the absence of historical data to understand the user [51].
    		A study app that recommends quiz questions similar to those the user is practicing.
    CollaborativeA recommendation is made by identifying patterns among similar users [52].
    • Leverages the power of the collective user behavior [53].
    • Can recommend items that a user may not have found independently [54].
    • Cold start problem: difficult to make recommendations with little or no historical data [55].
    • Sparsity: many user-item interactions may be unknown [56].
    • May only recommend popular items [57].
    • Raises privacy concerns, as data must be shared [27].
    • Gray sheep: Not effective for users with unique profiles [58].
    		A clinical skills training app that recommends practice scenarios frequently used by other students.
    KnowledgeA recommendation is made based on explicit domain user knowledge and recommendation criteria [59].
    • Useful when there is explicit knowledge about an item or user preferences [60].
    • New item problem: can be managed effectively, as it does not rely on past user-item interactions [61].
    • Knowledge acquisition bottleneck: requires explicit knowledge, which may not always be obtainable [62].
    • Lack of serendipity: may not suggest unexpected items, as it relies on the user’s requirements rather than on data from other users [63].
    		An advising system that recommends research opportunities and projects based on a student’s academic background and research interests.
    Hybrid filteringThis approach uses ≥2 filtering techniques [30].
    • Combines techniques to overcome the limitations of a single approach [64].
    • Sensitive to the strengths and weaknesses of the techniques used [65].
    		A study platform that, for learners of a specific module, may adopt a hybrid approach— (1) content-based: recommend additional resources similar to those used in the module, and (2) collaborative-based: recommend resources that other learners studying the same module found helpful.

    Recent Advances in Artificial Intelligence and LLMs in Recommender Systems

    The integration of generative artificial intelligence and LLMs has advanced the development of recommender systems. These technologies enhance natural language processing, facilitate natural-sounding dialogues, and improve recommendation accuracy and user interaction experiences [66-68]. Approaches such as retrieval-augmented generation models combine retrieval models and generative models to integrate specific knowledge sources, aiding complex recommendations while also addressing issues such as hallucinations and cold starts [69,70]. These advances, however, are not just restricted to text-based systems. Multimodal recommender systems are emerging in popularity, integrating various types of input data such as text, image, and audio. By leveraging the capabilities of LLMs to process this multimodal data, more comprehensive and accurate recommendations are possible [71,72]. Despite these advancements, challenges remain. Biases in LLM-based recommendations [73] and ethical concerns continue to pose challenges [74]. As these systems continue to evolve, they will offer more efficient and personalized solutions.

    Merits and Use Cases in Health Professions Education

    Learners in health care seek reliable materials for their education online [75,76], while others turn to the internet to understand their health conditions, treatment options, and preventive measures [77-81]. YouTube, a popular educational resource among health profession students [82,83], raises concerns for health care educators regarding the quality of information presented to students. This concern is supported by findings from Helming et al [84], who found that many YouTube videos on medical education are of low quality, even those created by academic physicians. Metrics such as views and likes, while popular among learners for navigating their choices, can be superficial and unreliable indicators of quality or accuracy [11,83,85]. Similarly, a study by Camm et al [86] found no correlation between video quality as assessed by a scoring tool and commonly used preference metrics (ie, hits, likes, dislikes, or search page rankings). When it comes to the videos recommended by the platform, the rationale behind the algorithm for suggesting specific content remains unclear? By developing a proprietary recommender system curated by experts in the subject matter, the suggested information and learning resources could be moderated, ensuring the quality and relevance of the materials recommended to learners.

    Educational recommender systems are information systems designed for use in educational settings to recommend various resources to different stakeholders, including learners, educators, researchers, and others [87]. Leveraging advanced algorithms and data analytics, educational recommender systems provide tailored recommendations that enhance the educational experience by addressing individual learner needs and preferences [1,38]. They facilitate efficient resource discovery, aiding personalized learning and informed decision-making in academic applications [38,40]. These systems are used in a variety of ways, with the goal of assisting students with academic decisions. They are used to recommend suitable institutes, study topics, and courses [88-90]. They can be used to propose personalized syllabi and scheduling [91-93], learning materials [94-97], scholarships [98], supervisors [99], and career paths [100]. These systems can also be used to offer learners feedback on summative assessments [101]. In education, personalized learning centers on learners, acknowledging their inherent differences—variations in strengths, weaknesses, and learning preferences [102]. This recognition of differences suggests that a uniform or “one-size-fits-all” approach may not be optimal for all learners. Koestner et al [103] conducted a meta-analysis that revealed that learners are more likely to achieve their goals when those goals are (1) self-concordant and (2) accompanied by an implementation plan. The concept of agency, as defined by Bandura [104], refers to the capacity to initiate actions with intention and purpose. In education, this concept manifests as learner agency—a framework that embodies self-directed learning [105,106]. Learners actively pursue knowledge aligned with personal goals and interests, facilitated by strategic guidance from educators [107,108]. Educators play a crucial role in this process by providing the necessary guidance and support to ensure that learners have access to high-quality and relevant resources. In addition to the information overload highlighted earlier, learners may sometimes be unaware of what to search for [109]. Deschênes [110] highlighted that recommender systems are valuable for curating educational resources tailored to the needs of individual learners, empowering informed choices, guiding learners to resources (that they may not have encountered unprompted), and fostering an environment conducive to autonomous yet guided education.

    While the topic of recommender systems has been extensively studied in both health care [111,112] and education [113-115], to the best of the authors’ knowledge, there appears to be a gap in the literature regarding their application in health professions education (HPE). For example, a topic search (covering the title, abstract, and keywords) on Web of Science using the terms “recommender system*” and “health professions education” returned only 2 articles. This scoping review aims to comprehensively map the extent of recommender systems in the HPE domain.

    Practical Implementations in HPE

    In reviewing the literature for applications of such systems in HPE, several innovative implementations with diverse purposes have been identified. One system provides adaptive, competence-based recommendations tailored to each student’s unique needs [116]. Another is used to evaluate nursing competencies and to recommend targeted learning materials to address skill gaps [117]. Liou and Chen [118] presented an e-learning platform that recommended personalized learning activities for medical interns. Another system assists second-language nurses in patient care charting by suggesting optimal terms during documentation [119]. Liou [120] introduced a recommender system for an online discussion forum that personalized article recommendations based on individual preferences.

    Objectives

    This scoping review aims to identify the different use cases of recommender systems in HPE. In addition, this review aims to determine the filtering techniques used by these systems, analyze their attributes or features, and explore the user experiences of both learners and educators. Furthermore, this review seeks to identify gaps in the current literature and provide suggestions for future research on the use of recommender systems in HPE.


    Ethical Considerations

    This study is based on the analysis of published literature, both scientific and gray. It does not involve patients, medical research, or any type of personal information, and, as such, no ethics approval is required. The results of this scoping review will be submitted for publication in a peer-reviewed international journal and presented at scientific meetings and conferences related to HPE.

    Protocol Design

    Overview

    Scoping reviews have gained popularity in recent years as a research methodology [121]. The objective of a scoping review is to identify and map the evidence available on a given topic [122]. Munn et al [123] elaborated on the objectives of conducting a scoping review by outlining six distinct components: (1) catalog the breadth of evidence available, (2) clarify concepts or definitions, (3) examine how the available research is conducted, (4) identify key characteristics of the topic, (5) ascertain the feasibility of conducting a systematic review, and (6) identify gaps in the existing literature. The methodology used in this scoping review is based on that of Arksey and O’Malley [122]. To ensure rigor, quality, and reproducibility, a recommended checklist [124,125] will be followed: the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) [126]. The output will be displayed using a flow diagram.

    Stage 1: Identifying the Research Question

    The objective of this scoping review is to gain a better understanding of the current use of recommender systems in HPE. Specifically, we will investigate the following questions:

    1. How are recommender systems being applied in HPE? That is, what is the recommendation element?
    2. What filtering technique or techniques are used by recommender systems in HPE?
    3. What are the attributes or features of these HPE recommender systems?
    4. What are the experiences of users, that is, learners and educators in the health professions, regarding the use of recommender systems?
    5. What are the gaps in the current research on the use of recommender systems in HPE?
    Stage 2: Identifying Relevant Studies

    A literature search will be conducted across the selected databases, consisting of the medical-specific source (MEDLINE), the nursing and allied health database (CINAHL Plus with Full Text), the educational search engine (Education Resources Information Center), and the multidisciplinary databases (Academic Search Premier and Web of Science). Gray literature will be searched via the arXiv repository for preprints and Google Scholar. For gray literature sources, we will review the first 100 results, ranked by the platform’s relevancy sorting feature. For Google Scholar, the searches will be limited to article titles, an approach recommended by Haddaway et al [127] for conducting systematic reviews. This comprehensive approach will ensure a high-quality literature review by retrieving a wide range of potentially relevant articles from a broad multidisciplinary perspective.

    A search-string development strategy will be developed in accordance with the 3-step recommendations provided by the Joanna Briggs Institute [128]. First, an initial limited search will be conducted in 3 databases: Academic Search Premier, CINAHL, and MEDLINE, with the relevance of the terms used being evaluated. Next, the text in the returned articles (titles, abstracts, and keywords) will be analyzed. A comprehensive search will then be performed using these terms across the databases. Finally, citations in the retrieved results will be manually reviewed to identify any additional relevant studies not captured in the database or gray literature searches.

    The search strategy will include title and abstract searches with terms related to HPE and recommender systems, connected using Boolean operators (AND, OR, and NOT). Controlled vocabulary terms (eg, Medical Subject Headings [MeSH] terms, subject headings, or subject terms) will be used when available in the database to enhance the search, independent of the title and abstract search parameters. These terms will help identify synonyms and related concepts, thereby broadening the search scope. Truncations (or stemming) will be used to capture the root of words, ensuring that different endings of the term of interest are included. For example, using “recommend* system” would capture “recommendation system,” “recommender system,” and “recommending system.” In addition, we will implement word proximity searches to ensure that terms of interest are situated within a specified number of words from each other. This approach will allow us to capture relevant phrases and contexts that are not caught through truncation alone. For example, when we search for “recommender N2 system*,” articles in which “recommender” appears within 2 words of any variation of “system” will be returned. For instance, it would capture a sentence such as, “The recommender model system enhanced student learning outcomes,” which would otherwise be missed.

    The following are examples:

    1. TI = (recommender NEAR/2 system* OR recommendation NEAR/2 system*) OR AB = (recommender NEAR/2 system* OR recommendation NEAR/2 system*)
    2. TI = (medical OR nurs*) OR AB = (medical OR nurs*)
    3. 1 AND 2

    This example includes a title and abstract search, making use of Boolean operators (AND and OR), stemming (eg, recommend*), and proximity search (eg, NEAR/2).

    The search period will span from January 2000 to February 2025. Our decision to start the scoping review in 2000 is informed by existing literature on recommender systems in education. The systematic review by Urdaneta-Ponte et al [129] focused on literature from 2015 onward, while the work by Kamal et al [89] covered 2011 onward. The literature review by Lampropoulos [114] traced studies on the use of recommender systems in education back to 2001. By selecting the earliest date from these studies, we establish a conservative starting point, minimizing the risk of overlooking relevant literature. The search strategy targets students and educators in specific health professions, including medicine, nursing, dentistry, pharmacy, public health, allied health, clinical education, veterinary medicine, paramedical sciences, occupational therapy, physiotherapy, speech therapy, audiology, mental health, biomedical sciences, nutrition, dietetics, midwifery, chiropractic, and podiatry. The inclusion criteria will be limited to studies reporting on the concept, development, or application of recommender systems applied to diverse educational or training offerings designed for these health professions students or educators (eg, undergraduate, postgraduate, continuing professional development). Studies involving mixed populations, that is, health professions and non–health professions students, will be excluded. For a detailed view of how search lines 1 and 2 in the example above are combined, a sample search strategy can be found in Multimedia Appendix 1.

    All identified references will be imported into the reference management software, EndNote [130], to merge and manage the citations and remove any duplicate entries. Once the data cleansing is complete, the citations will be imported to Covidence [131] for the study selection screening and charting stages.

    Stage 3: Study Selection

    Next, a 2-stage screening process will be implemented. The first stage involves scanning titles and abstracts to identify relevant articles. To be eligible for the second stage, the title or the abstract (or both) must (1) focus on the use of recommender systems and (2) target HPE. The second stage involves a full-text review of articles. In both stages, reviewers will screen articles against the eligibility criteria outlined in Textbox 1. Any uncertainty about whether an article should be included during the initial screening will result in its progression to the full-text review stage. Disagreements about the relevance of an article during the full-text review will be discussed among the reviewers, and if no consensus is reached, a third reviewer will be consulted to decide whether to include the article. The reasons for excluding the articles will be documented in the scoping review report.

    Textbox 1. Full inclusion and exclusion criteria.

    Inclusion criteria

    • Population: studies involving health profession students or educators (including undergraduate, postgraduate, and continuing professional development [CPD]).
    • Concept: studies focused on the concept, development, or application of recommender systems.
    • Context: any geographic location
    • Types of evidence: all primary studies of all designs; systematic reviews; full-text conference proceedings; full-text articles; articles published from 2000 to February 2025
    • Language: any

    Exclusion criteria

    • Population: studies that exclude health profession students or educators (eg, those centered on patients or the public); studies with mixed populations (ie, health professions and non–health professions students)
    • Concept: studies that do not address recommender systems (eg, studies focused on unrelated technologies)
    • Context: none
    • Types of evidence: articles published before 2000; meeting abstracts
    Stage 4: Charting the Data

    Data extraction will be conducted by 2 independent reviewers (reviewers 1 and 2) to ensure consistency and reliability. A standardized data extraction form, developed by the research team and configured in Microsoft Excel, will be used to chart the relevant data from all included studies (Table 2). The extracted data will cover 4 domains: article details, study details, specifics of the recommender system, and user experience. Each domain will be carefully examined to ensure that the collected data aligns with the research questions, and discrepancies will be noted for further analysis.

    For article details, information such as article type (eg, original research, review, and case study), authors’ names, affiliations or institutions, year of publication, and the country of the study’s origin will be included to help contextualize the study within the broader literature. The study details will cover the study design (eg, observational, longitudinal, randomized controlled trial, and qualitative), the primary objective of the study, participant demographics, and the main outcomes of the study, providing insights into methodologies and key findings. In addition, details about the recommender system will be documented, including its application (ie, what it is recommending), the filtering techniques used, the attributes or features of the recommender system, and the user experiences of learners and educators, revealing practical applications and features, as well as highlighting user feedback. Data charting will be conducted using Covidence, a cloud-based resource for scoping review management.

    This form will be piloted on a subset of articles to assess its effectiveness. For instance, certain important characteristics of the articles may not be captured by the current items, requiring adjustments to the instrument. The full-text reviewers will be asked during the pilot stage to identify any additional variables that should be considered for charting, and the form will be revised if deemed necessary. Any disagreements between the reviewers will be resolved through discussion, with a third reviewer (reviewer 3) acting as an arbiter if necessary.

    Table 2. Data charting instrument.
    Domain and subdomainDescription or examples
    Article

    		Article typeOriginal research, review, and case study

    		AuthorsList of authors’ names

    		AffiliationList of authors’ affiliations or institutions

    		Year of publicationYear the article was published

    		CountryCountry of the study’s origin

    		LimitationsAny limitations described or observed in the article
    Study

    		Study designFor example, observational, longitudinal, randomized controlled trial, and qualitative

    		AimPrimary objective or purpose of the study

    		ParticipantsWho were the participants in the study?

    		OutcomesMain results of the study
    Recommender system

    		ElementHow is the recommender system being applied? That is, what is it recommending?

    		Technique or techniquesWhat filtering technique or techniques are used by the recommender system?

    		AttributesWhat are the attributes or features of these health profession education recommender systems?

    		User experience or experiencesWhat are the experiences of users (ie, learners and educators) in the health professions regarding the use of recommender systems?
    Stage 5: Collating, Summarizing, and Reporting the Results

    Data will be analyzed and summarized, with the study characteristics presented in both tabular and graphical formats, accompanied by a narrative interpretation. To ensure thorough synthesis, we will use a framework that categorizes the data according to our research questions. This will involve mapping the extracted data to each question, identifying patterns, and summarizing the aggregated evidence. For example, we will compare the filtering techniques (eg, content, collaborative, knowledge, or hybrid) used across different studies to understand their application in various HPE contexts. We will create summary tables that outline the key findings from the included studies for each research question. This approach will help us systematically present the different use cases and characteristics. In reporting our results, we will highlight the similarities and differences in how recommender systems are applied in HPE and identify research gaps through a comparative analysis of the studies and their applications. Arksey and O’Malley [122] suggest an optional sixth stage—stakeholder consultation—to gather feedback on the findings uncovered during the scoping review. Although we acknowledge the value of this step, this scoping review is part of a larger study that will later include a qualitative component involving stakeholders. Therefore, this scoping review will not include a stakeholder consultation.

    Table 3 provides an estimated timeline for this scoping review. This timeline is designed to balance the thoroughness required for a comprehensive literature review with the need for timely completion to maintain the relevance of our findings to the academic community.

    Table 3. Data charting instrument.
    StageDescriptionEstimated completion date
    1Identifying the research questionOctober 2024
    2Identifying relevant studiesFebruary 2025
    3Selecting studiesJune 2025
    4Charting the dataSeptember 2025
    5Collating, summarizing, and reporting the resultsNovember 2025

    The study will begin the phase of selecting studies for this review as outlined in the protocol, including the processes of search, screening, and data extraction, in February 2025. We anticipate completing the study and submitting the manuscript for peer review by the winter of 2025. This review aims to provide a detailed overview of the various applications of recommender systems in HPE, including the filtering techniques used and the specific features of these systems.


    Anticipated Findings

    The anticipated findings of this scoping review are expected to provide valuable insights into the diverse applications and potential benefits of recommender systems in HPE. These systems can significantly enhance learning experiences by personalizing the content to the unique needs of individual learners. By providing tailored recommendations, these systems can help bridge knowledge gaps, reinforce learning, and support continuous professional development. The expected findings will provide insights into the experiences of both learners and educators, identifying applications and implementation challenges. The scoping review aims to evaluate existing evidence and identify gaps in the literature concerning the use of recommender systems in HPE.

    Comparison to Prior Work

    Previous studies have highlighted the benefits of recommender systems in various educational contexts of HPE (116-20). A continuously growing number of learning resources has created a need for these systems in education [23-25,39]. Digel et al [38] reported that engaging users in the development process of such systems is crucial to ensure their acceptance and use. It is anticipated that the applications and implementation challenges identified through this scoping review will help health profession educators in developing future systems. This review will build on these findings by specifically focusing on their use with HPE and identifying unique challenges and opportunities in this field.

    Strengths and Limitations

    A strength of this review is its comprehensive methodology, which includes a thorough search across multiple scientific databases and gray literature sources. This approach ensures a broad and inclusive overview of the existing literature. However, some limitations should be acknowledged. First, because the screening processes for scoping review do not assess the quality of the included studies, the robustness of the evidence presented may be impacted [132]. In addition, by focusing exclusively on studies published from 2000 onward, the review may overlook earlier research that could offer valuable insights and increase the potential for systematic bias [133]. Furthermore, while the aim is to cover a broad range of studies related to recommender systems, this breadth may come at the cost of a lack of depth in the analysis [134], making it difficult to draw specific conclusions. Publication bias, in which the likelihood of a study being published is influenced by the nature and direction of its results, creates a systematic difference between published and unpublished studies. Although incorporating gray literature in our study helps mitigate this bias, it does not fully eliminate it, as studies with positive or significant outcomes are still more likely to be published [135].

    Dissemination Plans

    The dissemination strategies for the findings of this scoping review will include publication in a peer-reviewed journal and presentations at national and international conferences. The dissemination activities will commence in the winter of 2025 with the manuscript submission.

    Conclusions

    While recommender systems have been extensively studied in health care and education, there is a significant gap in the literature regarding their application in HPE. To the best of our knowledge, this is the first comprehensive exploration of recommender systems specifically focused on HPE. This scoping review aims to thoroughly map the extent and various applications of these systems within this domain. By identifying effective practices and highlighting existing gaps, this review will serve as a valuable resource for health professions educators, enriching academic discourse and providing practical guidance for effective implementation in HPE.

    Acknowledgments

    The authors would like to recognize and appreciate Mr. Sa’ad Laws, librarian for education and research at Weill Cornell Medicine-Qatar, who contributed to refining the search strategy.

    Data Availability

    Data sharing is not applicable to this paper as no datasets were generated or analyzed during this study.

    Conflicts of Interest

    None declared.

    Multimedia Appendix 1

    Search strategy for the MEDLINE database.

    DOCX File , 24 KB
    Multimedia Appendix 2

    PRISMA-ScR Checklist.

    DOCX File , 37 KB
    1. Geyer-Schulz A, Hahsler M, Jahn M. Educational and scientific recommender systems: designing the information channels of the virtual university. Int J Eng Educ. 2001;17(12):153-163. [FREE Full text]
    2. Klerings I, Weinhandl AS, Thaler KJ. Information overload in healthcare: too much of a good thing? Z Evid Fortbild Qual Gesundhwes. 2015;109(4-5):285-290. [FREE Full text] [CrossRef] [Medline]
    3. Maggio L, Artino JAJ. Staying up to date and managing information overload. J Grad Med Educ. Oct 2018;10(5):597-598. [FREE Full text] [CrossRef] [Medline]
    4. Smith R. Strategies for coping with information overload. BMJ. Dec 15, 2010;341:c7126. [FREE Full text] [CrossRef] [Medline]
    5. Ioannidis JP, Stuart ME, Brownlee S, Strite SA. How to survive the medical misinformation mess. Eur J Clin Invest. Nov 2017;47(11):795-802. [FREE Full text] [CrossRef] [Medline]
    6. LaPerrière B, Edwards P, Romeder JM, Maxwell-Young L. Using the internet to support self-care. Can Nurse. May 1998;94(5):47-48. [Medline]
    7. Siegel MG, Rossi MJ, Lubowitz J. Artificial intelligence and machine learning may resolve health care information overload. Arthroscopy. Jun 2024;40(6):1721-1723. [FREE Full text] [CrossRef] [Medline]
    8. Phillips-Wren G, Adya M. Decision making under stress: the role of information overload, time pressure, complexity, and uncertainty. J Decis Syst. May 27, 2020;29(sup1):213-225. [CrossRef]
    9. Swar B, Hameed T, Reychav I. Information overload, psychological ill-being, and behavioral intention to continue online healthcare information search. Comput Hum Behav. May 2017;70:416-425. [FREE Full text] [CrossRef]
    10. Zheng H, Chen X, Jiang S, Sun L. How does health information seeking from different online sources trigger cyberchondria? The roles of online information overload and information trust. Inf Process Manag. Jul 2023;60(4):103364. [FREE Full text] [CrossRef]
    11. Osman W, Mohamed F, Elhassan M, Shoufan A. Is YouTube a reliable source of health-related information? A systematic review. BMC Med Educ. May 19, 2022;22(1):382. [FREE Full text] [CrossRef] [Medline]
    12. Suarez-Lledo V, Alvarez-Galvez J. Prevalence of health misinformation on social media: systematic review. J Med Internet Res. Jan 20, 2021;23(1):e17187. [FREE Full text] [CrossRef] [Medline]
    13. Wang Y, McKee M, Torbica A, Stuckler D. Systematic literature review on the spread of health-related misinformation on social media. Soc Sci Med. Nov 2019;240:112552. [FREE Full text] [CrossRef] [Medline]
    14. Yang KC, Pierri F, Hui PM, Axelrod D, Torres-Lugo C, Bryden J, et al. The COVID-19 infodemic: Twitter versus Facebook. Big Data Soc. May 05, 2021;8(1). [FREE Full text] [CrossRef]
    15. Briones R, Nan X, Madden K, Waks L. When vaccines go viral: an analysis of HPV vaccine coverage on YouTube. Health Commun. 2012;27(5):478-485. [FREE Full text] [CrossRef] [Medline]
    16. Johnson SB, Parsons M, Dorff T, Moran M, Ward JH, Cohen SA, et al. Cancer misinformation and harmful information on Facebook and other social media: a brief report. J Natl Cancer Inst. Jul 11, 2022;114(7):1036-1039. [FREE Full text] [CrossRef] [Medline]
    17. Trivedi N, Krakow M, Hyatt Hawkins K, Peterson EB, Chou WY. “Well, the message is from the institute of something”: exploring source trust of cancer-related messages on simulated Facebook posts. Front Commun. Feb 28, 2020;5:12. [FREE Full text] [CrossRef]
    18. Sidani JE, Hoffman BL, Colditz JB, Melcher E, Taneja SB, Shensa A, et al. E-cigarette-related nicotine misinformation on social media. Subst Use Misuse. 2022;57(4):588-594. [FREE Full text] [CrossRef] [Medline]
    19. Singh AG, Singh S, Singh PP. YouTube for information on rheumatoid arthritis--a wakeup call? J Rheumatol. May 2012;39(5):899-903. [FREE Full text] [CrossRef] [Medline]
    20. Ruggeri K, Vanderslott S, Yamada Y, Argyris Y, Većkalov B, Boggio PS, et al. Behavioural interventions to reduce vaccine hesitancy driven by misinformation on social media. BMJ. Jan 16, 2024;384:e076542. [FREE Full text] [CrossRef] [Medline]
    21. Ghenai A, Mejova Y. Fake cures: user-centric modeling of health misinformation in social media. Proc ACM Hum Comput Interact. Nov 2018;2(CSCW):1-20. [FREE Full text] [CrossRef]
    22. Arseniev-Koehler A, Lee H, McCormick T, Moreno M. #Proana: pro-eating disorder socialization on Twitter. J Adolesc Health. Jun 2016;58(6):659-664. [FREE Full text] [CrossRef] [Medline]
    23. Polonioli A. The ethics of scientific recommender systems. Scientometrics. Oct 29, 2020;126(2):1841-1848. [FREE Full text] [CrossRef]
    24. Montaner M, López B, de la Rosa JL. A taxonomy of recommender agents on the internet. Artif Intell Rev. Jun 2003;19(4):285-330. [FREE Full text] [CrossRef]
    25. Raza S, Ding C. News recommender system: a review of recent progress, challenges, and opportunities. Artif Intell Rev. 2022;55(1):749-800. [FREE Full text] [CrossRef] [Medline]
    26. Raza S, Rahman M, Kamawal S, Toroghi A, Raval A, Navah F, et al. A comprehensive review of recommender systems: transitioning from theory to practice. ArXiv. Preprint posted online on July 18, 2024. [FREE Full text]
    27. Roy D, Dutta M. A systematic review and research perspective on recommender systems. J Big Data. May 03, 2022;9(1):59. [FREE Full text] [CrossRef]
    28. Berkovsky S, Kuflik T, Ricci F. Mediation of user models for enhanced personalization in recommender systems. User Model User Adapt Interact. Nov 3, 2007;18(3):245-286. [FREE Full text] [CrossRef]
    29. Resnick P, Varian HR. Recommender systems. Commun ACM. Mar 1997;40(3):56-58. [FREE Full text] [CrossRef]
    30. Burke R. Hybrid recommender systems: survey and experiments. User Model User Adap Inter. 2002;12:331-370. [FREE Full text] [CrossRef]
    31. Jannach D, Zanker M, Felfernig A, Friedrich G. Recommender Systems: An Introduction. Cambridge, UK. Cambridge University Press; 2010.
    32. Ricci F, Rokach L, Shapira B. Introduction to recommender systems handbook. In: Ricci F, Rokach L, Shapira B, Kantor P, editors. Recommender Systems Handbook. Boston, MA. Springer; 2011.
    33. MacKenzie I, Meyer C, Noble S. How retailers can keep up with consumers. McKinsey & Company. Oct 1, 2013. URL: https://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers [accessed 2025-07-31]
    34. Betru BT, Onana CA, Batchakui B. Deep learning methods on recommender system: a survey of state-of-the-art. Int J Comput Appl. Mar 2017;162(10):17-22. [FREE Full text]
    35. Portugal I, Alencar P, Cowan D. The use of machine learning algorithms in recommender systems: a systematic review. Expert Syst Appl. May 2018;97:205-227. [FREE Full text] [CrossRef]
    36. Ramzan B, Bajwa IS, Jamil N, Amin R, Ramzan S, Mirza F, et al. An intelligent data analysis for recommendation systems using machine learning. Sci Program. Oct 31, 2019;2019:1-20. [FREE Full text] [CrossRef]
    37. Zhang S, Yao L, Sun A, Tay Y. Deep learning based recommender system: a survey and new perspectives. ACM Comput Surv. Feb 25, 2019;52(1):1-38. [FREE Full text] [CrossRef]
    38. Digel S, Krause T, Biel C. Enabling individualized and adaptive learning – the value of an AI-based recommender system for users of adult and continuing education platforms. In: Proceedings of the 24th International Conference on Artificial Intelligence in Education. 2023. Presented at: AIED 2023; July 3-7, 2023; Tokyo, Japan. URL: https://doi.org/10.1007/978-3-031-36336-8_121 [CrossRef]
    39. Ariff NM, Bang BL, Nadarajan S, Nor MH. Educational recommender systems: a bibliometric analysis for the period 2002 – 2022. J Qual Meas Anal. 2024;20(2):197-215. [FREE Full text] [CrossRef]
    40. Thongchotchat V, Kudo Y, Okada Y, Sato K. Educational recommendation system utilizing learning styles: a systematic literature review. IEEE Access. 2023;11:8988-8999. [FREE Full text] [CrossRef]
    41. Carraro D, Bridge D. Enhancing recommendation diversity by re-ranking with large language models. ArXiv. Preprint posted online on January 21, 2024. [FREE Full text] [CrossRef]
    42. Lin J, Dai X, Xi Y, Liu W, Chen B, Zhang H, et al. How can recommender systems benefit from large language models: a survey. ArXiv. Preprint posted online on June 9, 2023. [FREE Full text] [CrossRef]
    43. Adomavicius G, Tuzhilin A. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng. Jun 2005;17(6):734-749. [FREE Full text] [CrossRef]
    44. Isinkaye FO, Folajimi YO, Ojokoh BA. Recommendation systems: principles, methods and evaluation. Egypt Inform J. Nov 2015;16(3):261-273. [FREE Full text] [CrossRef]
    45. Shah M, Subhan F. Critical analysis of various recommendation systems. Int J Soc Sci Arch. Mar 2, 2023;5(2). [FREE Full text]
    46. Pazzani MJ, Billsus D. Content-based recommendation systems. In: Brusilovsky P, Kobsa A, Nejdl W, editors. The Adaptive Web. Berlin, Germany. Springer; 2007.
    47. Lops P, Jannach D, Musto C, Bogers T, Koolen M. Trends in content-based recommendation: preface to the special issue on recommender systems based on rich item descriptions. User Model User Adap Inter. Mar 7, 2019;29(2):239-249. [FREE Full text] [CrossRef]
    48. Lam SK, Frankowski D, Riedl J. Do you trust your recommendations? An exploration of security and privacy issues in recommender systems. In: Proceedings of the Emerging Trends in Information and Communication Security. 2006. Presented at: ETRICS 2006; June 6-9, 2006; Freiburg, Germany. URL: https://doi.org/10.1007/11766155_2 [CrossRef]
    49. Sun A, Peng Y. A survey on modern recommendation system based on big data. ArXiv. Preprint posted online on January 18, 2024. [FREE Full text]
    50. Putta S, Kulkarni O. Analytical study of content-based and collaborative filtering methods for recommender systems. In: Proceedings of the Futuristic Trends in Networks and Computing Technologies. 2021. Presented at: FTNCT 2021; December 10-11, 2021; Gujarat, India. URL: https://doi.org/10.1007/978-981-19-5037-7_44 [CrossRef]
    51. Lops P, de Gemmis M, Semeraro G. Content-based recommender systems: state of the art and trends. In: Ricci F, Rokach L, Shapira B, Kantor P, editors. Recommender Systems Handbook. Boston, MA. Springer; 2011:73-105.
    52. Goldberg D, Nichols D, Oki BM, Terry D. Using collaborative filtering to weave an information tapestry. Commun ACM. Dec 1992;35(12):61-70. [FREE Full text] [CrossRef]
    53. Najafabadi MK, Mohamed AH, Mahrin MN. A survey on data mining techniques in recommender systems. Soft Comput. Nov 7, 2017;23(2):627-654. [FREE Full text] [CrossRef]
    54. Xie F, Chen Z, Shang J, Fox GC. Grey Forecast model for accurate recommendation in presence of data sparsity and correlation. Knowl Based Syst. Oct 2014;69:179-190. [FREE Full text] [CrossRef]
    55. Ferdaous H, Bouchra F, Brahim O, Imad-eddine M, Asmaa B. Recommendation using a clustering algorithm based on a hybrid features selection method. J Intell Inf Syst. Jan 9, 2018;51(1):183-205. [FREE Full text] [CrossRef]
    56. Najafabadi MK, Mohamed A, Onn CW. An impact of time and item influencer in collaborative filtering recommendations using graph-based model. Inf Process Manag. May 2019;56(3):526-540. [FREE Full text] [CrossRef]
    57. Ekstrand MD, Riedl JT, Konstan JA. Collaborative filtering recommender systems. Found Trends Hum Comput Interact. 2010;4(2):81-173. [CrossRef]
    58. Claypool M, Gokhale A, Miranda T, Murnikov P, Netes D, Sartin M. Combining content-based and collaborative filters in an online newspaper. In: Proceedings of ACM SIGIR Workshop on Recommender Systems. 1999. Presented at: ACM SIGIR 1999; 1999 Aug 19; Berkeley, CA. URL: http://web.cs.wpi.edu/~claypool/papers/content-collab/content-collab.pdf
    59. Burke R. Knowledge-based recommender systems. In: Encyclopedia of Library and Information Science. Boca Raton, FL. CRC Press; 2000.
    60. Uta M, Felfernig A, Le VM, Tran TN, Garber D, Lubos S, et al. Knowledge-based recommender systems: overview and research directions. Front Big Data. 2024;7:1304439. [FREE Full text] [CrossRef] [Medline]
    61. Alabdulrahman R, Viktor H. Catering for unique tastes: targeting grey-sheep users recommender systems through one-class machine learning. Expert Syst Appl. Mar 2021;166:114061. [FREE Full text] [CrossRef]
    62. Felfernig A, Friedrich G, Jannach D, Zanker M. Constraint-based recommender systems. In: Ricci F, Rokach L, Shapira B, editors. Recommender Systems Handbook. Boston, MA. Springer; 2015.
    63. Aggarwal C, Aggarwal C. Knowledge-based recommender systems. In: Recommender Systems. Cham, Switzerland. Springer; 2016.
    64. Widayanti R, Chakim MH, Lukita C, Rahardja U, Lutfiani N. Improving recommender systems using hybrid techniques of collaborative filtering and content-based filtering. J Appl Data Sci. 2023;4(3):289-302. [FREE Full text] [CrossRef]
    65. Çano E, Morisio M. Hybrid recommender systems: a systematic literature review. Intell Data Anal. Nov 15, 2017;21(6):1487-1524. [FREE Full text] [CrossRef]
    66. Zhao Z, Fan W, Li J, Liu Y, Mei X, Wang Y, et al. Recommender systems in the era of large language models (LLMs). IEEE Trans Knowl Data Eng. Nov 2024;36(11):6889-6907. [FREE Full text] [CrossRef]
    67. Tian J, Wang Z, Zhao J, Ding Z. MMREC: LLM based multi-modal recommender system. In: Proceedings of the 19th International Workshop on Semantic and Social Media Adaptation & Personalization. 2024. Presented at: SMAP 2024; November 21-24, 2024; Athens, Greece. URL: https://doi.org/10.1109/SMAP63474.2024.00028 [CrossRef]
    68. Ayemowa MO, Ibrahim R, Khan MM. Analysis of recommender system using generative artificial intelligence: a systematic literature review. IEEE Access. 2024;12:87742-87766. [FREE Full text] [CrossRef]
    69. El Maazouzi Q, Retbi A, Bennani S. Optimizing recommendation systems in e-learning: synergistic integration of lang chain, GPT models, and retrieval augmented generation (RAG). In: Li G, Filipe J, Xu Z, editors. Communications in Computer and Information Science. Cham, Switzerland. Springer; 2024:106-118.
    70. Deldjoo Y, He Z, McAuley J, Korikov A, Sanner S, Ramisa A, et al. A review of modern recommender systems using generative models (Gen-RecSys). In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024. Presented at: KDD '24; August 25-29, 2024; Barcelona, Spain. URL: https://doi.org/10.1145/3637528.3671474 [CrossRef]
    71. Liu Q, Hu J, Xiao Y, Zhao X, Gao J, Wang W, et al. Multimodal recommender systems: a survey. ACM Comput Surv. Oct 10, 2024;57(2):1-17. [FREE Full text] [CrossRef]
    72. Zhou H, Zhou X, Zeng Z, Zhang L, Shen Z. A comprehensive survey on multimodal recommender systems: taxonomy, evaluation, and future directions. ArXiv. Preprint posted online on February 9, 2023. [FREE Full text]
    73. Sakib SK, Das AB. Challenging fairness: a comprehensive exploration of bias in LLM-based recommendations. In: Proceedings of the IEEE International Conference on Big Data. 2024. Presented at: BigData 2024; December 15-18, 2024; Washington, DC. URL: https://doi.org/10.1109/BigData62323.2024.10825082 [CrossRef]
    74. Rajput RS, Shah S, Neema S. Content moderation framework for the LLM-based recommendation systems. Int J Comput Eng Technol. 2023;14(3):104-117. [FREE Full text]
    75. Cook DA, Levinson AJ, Garside S, Dupras DM, Erwin PJ, Montori VM. Internet-based learning in the health professions: a meta-analysis. JAMA. Sep 10, 2008;300(10):1181-1196. [FREE Full text] [CrossRef] [Medline]
    76. Maloney S, Chamberlain M, Morrison S, Kotsanas G, Keating JL, Ilic D. Health professional learner attitudes and use of digital learning resources. J Med Internet Res. Jan 16, 2013;15(1):e7. [FREE Full text] [CrossRef] [Medline]
    77. Andreassen HK, Bujnowska-Fedak MM, Chronaki CE, Dumitru RC, Pudule I, Santana S, et al. European citizens' use of e-health services: a study of seven countries. BMC Public Health. Apr 10, 2007;7:53. [FREE Full text] [CrossRef] [Medline]
    78. Atkinson NL, Saperstein SL, Pleis J. Using the internet for health-related activities: findings from a national probability sample. J Med Internet Res. Mar 20, 2009;11(1):e4. [FREE Full text] [CrossRef] [Medline]
    79. de Boer MJ, Versteegen GJ, van Wijhe M. Patients' use of the internet for pain-related medical information. Patient Educ Couns. Sep 2007;68(1):86-97. [FREE Full text] [CrossRef] [Medline]
    80. McMullan M. Patients using the internet to obtain health information: how this affects the patient-health professional relationship. Patient Educ Couns. Oct 2006;63(1-2):24-28. [FREE Full text] [CrossRef] [Medline]
    81. Tan SS, Goonawardene N. Internet health information seeking and the patient-physician relationship: a systematic review. J Med Internet Res. Jan 19, 2017;19(1):e9. [FREE Full text] [CrossRef] [Medline]
    82. Burns L, Abbassi E, Qian X, Mecham A, Simeteys P, Mays KA. YouTube use among dental students for learning clinical procedures: a multi-institutional study. J Dent Educ. Oct 2020;84(10):1151-1158. [FREE Full text] [CrossRef] [Medline]
    83. Curran V, Simmons K, Matthews L, Fleet L, Gustafson DL, Fairbridge NA, et al. YouTube as an educational resource in medical education: a scoping review. Med Sci Educ. Dec 2020;30(4):1775-1782. [FREE Full text] [CrossRef] [Medline]
    84. Helming AG, Adler DS, Keltner C, Igelman AD, Woodworth GE. The content quality of YouTube videos for professional medical education: a systematic review. Acad Med. Oct 01, 2021;96(10):1484-1493. [FREE Full text] [CrossRef] [Medline]
    85. Mueller SM, Hongler VN, Jungo P, Cajacob L, Schwegler S, Steveling EH, et al. Fiction, falsehoods, and few facts: cross-sectional study on the content-related quality of atopic eczema-related videos on YouTube. J Med Internet Res. Apr 24, 2020;22(4):e15599. [FREE Full text] [CrossRef] [Medline]
    86. Camm CF, Sunderland N, Camm AJ. A quality assessment of cardiac auscultation material on YouTube. Clin Cardiol. Mar 2013;36(2):77-81. [FREE Full text] [CrossRef] [Medline]
    87. Aucancela MA, Briones AG, Chamoso P. Educational recommender systems: a systematic literature review. In: Proceedings of the Barcelona Conference on Education 2023. 2023. Presented at: BCE2023; September 19-23, 2023; Online. URL: https://doi.org/10.22492/issn.2435-9467.2023.74 [CrossRef]
    88. Al-Badarenah A, Alsakran J. An automated recommender system for course selection. Int J Adv Comput Sci Appl. 2016;7(3). [FREE Full text] [CrossRef]
    89. Kamal N, Sarker F, Rahman A, Hossain S, Mamun KA. Recommender system in academic choices of higher education: a systematic review. IEEE Access. 2024;12:35475-35501. [CrossRef]
    90. O'Mahony MP, Smyth B. A recommender system for on-line course enrolment: an initial study. In: Proceedings of the 2007 ACM conference on Recommender Systems. 2007. Presented at: RecSys '07; October 19-20, 2007; Minneapolis, MN. URL: https://doi.org/10.1145/1297231.1297254 [CrossRef]
    91. Bulut O, Cormier DC, Shin J. An intelligent recommender system for personalized test administration scheduling with computerized formative assessments. Front Educ. Sep 23, 2020;5:572612. [FREE Full text] [CrossRef]
    92. Meryem G, Douzi K, Chantit S. Toward an e-orientation platform: using hybrid recommendation systems. In: Proceedings of the 11th International Conference on Intelligent Systems: Theories and Applications. 2016. Presented at: SITA 2016; October 19-20, 2016; Mohammedia, Morocco. URL: https://doi.org/10.1109/SITA.2016.7772305 [CrossRef]
    93. Xu J, Xing T, van der Schaar M. Personalized course sequence recommendations. IEEE Trans Signal Process. Oct 15, 2016;64(20):5340-5352. [FREE Full text] [CrossRef]
    94. Ansari MH, Moradi M, NikRah O, Kambakhsh KM. CodERS: a hybrid recommender system for an e-learning system. In: Proceedings of the 2nd International Conference of Signal Processing and Intelligent Systems. 2016. Presented at: ICSPIS 2016; December 14-15, 2016; Tehran, Iran. URL: https://doi.org/10.1109/ICSPIS.2016.7869884 [CrossRef]
    95. Bauman K, Tuzhilin A. Recommending remedial learning materials to students by filling their knowledge gaps. MIS Q. Jan 1, 2018;42(1):313-332. [CrossRef]
    96. Lu J. A personalized e-learning material recommender system. In: Proceedings of the 2nd International Conference on Information Technology for Application. 2004. Presented at: ICITA 2004; October 20-22, 2004; Sydney, Australia.
    97. Tembo S, Chen J. Personalised material and course recommendation system for high school students. In: Wang W, Wang G, Ding X, Zhang B, editors. Artificial Intelligence in Education and Teaching Assessment. Singapore, Singapore. Springer; 2021:175-184.
    98. Pinto FM, Estefania M, Cerón N, Andrade R, Campaña M. iRecomendYou: a design proposal for the development of a pervasive recommendation system based on student’s profile for Ecuador’s students’ candidature to a scholarship. In: Rocha Á, Correia A, Adeli H, Reis L, Mendonça Teixeira M, editors. New Advances in Information Systems and Technologies. Cham, Switzerland. Springer; 2016.
    99. Rismanto R, Syulistyo AR, Agusta BP. Research supervisor recommendation system based on topic conformity. Int J Modern Educ Comput Sci. 2020;12(1):26-34. [FREE Full text] [CrossRef]
    100. Patel B, Kakuste V, Eirinaki M. CaPaR: a career path recommendation framework. In: Proceedings of the IEEE Third International Conference on Big Data Computing Service and Applications. 2017. Presented at: BigDataService 2017; April 6-9, 2017; Redwood City, CA. [CrossRef]
    101. de Schipper E, Feskens R, Keuning J. Personalized and automated feedback in summative assessment using recommender systems. Front Educ. Mar 22, 2021;6:652070. [FREE Full text] [CrossRef]
    102. Cheung SK, Wang FL, Kwok LF, Poulova P. In search of the good practices of personalized learning. Interact Learn Environ. Apr 02, 2021;29(2):179-181. [FREE Full text] [CrossRef]
    103. Koestner R, Lekes N, Powers TA, Chicoine E. Attaining personal goals: self-concordance plus implementation intentions equals success. J Pers Soc Psychol. 2002;83(1):231-244. [FREE Full text] [CrossRef]
    104. Bandura A. Social cognitive theory: an agentic perspective. Annu Rev Psychol. 2001;52:1-26. [FREE Full text] [CrossRef] [Medline]
    105. Gupta N, Ali K, Jiang D, Fink T, Du X. Beyond autonomy: unpacking self-regulated and self-directed learning through the lens of learner agency- a scoping review. BMC Med Educ. Dec 23, 2024;24(1):1519. [FREE Full text] [CrossRef] [Medline]
    106. Olivier J, du Toit-Brits C, Bunt BJ, Dhakulkar A. Contextualised Open Educational Practices: Towards Student Agency and Self-Directed Learning. Cape Town, South Africa. AOSIS; 2022.
    107. Bernacki ML, Greene MJ, Lobczowski NG. A systematic review of research on personalized learning: personalized by whom, to what, how, and for what purpose(s)? Educ Psychol Rev. Apr 27, 2021;33(4):1675-1715. [FREE Full text] [CrossRef]
    108. Solari M, Vizquerra MI, Engel A. Students’ interests for personalized learning: an analysis guide. Eur J Psychol Educ. Dec 02, 2022;38(3):1073-1109. [FREE Full text] [CrossRef]
    109. DeLong C, Desikan P, Srivastava J. USER: user-sensitive expert recommendations for knowledge-dense environments. In: Proceedings of the 7th International Workshop on Knowledge Discovery on the Web. 2005. Presented at: WEBKDD 2005; August 21, 2005; Chicago, IL. URL: https://doi.org/10.1007/11891321_5 [CrossRef]
    110. Deschênes M. Recommender systems to support learners’ agency in a learning context: a systematic review. Int J Educ Technol High Educ. Oct 21, 2020;17(1):50. [FREE Full text] [CrossRef]
    111. Tran TN, Felfernig A, Trattner C, Holzinger A. Recommender systems in the healthcare domain: state-of-the-art and research issues. J Intell Inf Syst. Dec 17, 2020;57(1):171-201. [FREE Full text] [CrossRef]
    112. Etemadi M, Bazzaz Abkenar S, Ahmadzadeh A, Haghi Kashani M, Asghari P, Akbari M, et al. A systematic review of healthcare recommender systems: open issues, challenges, and techniques. Expert Syst Appl. Mar 2023;213:118823. [FREE Full text] [CrossRef]
    113. Drachsler H, Verbert K, Santos OC, Manouselis N. Panorama of recommender systems to support learning. In: Ricci F, Rokach L, Shapira B, editors. Recommender Systems Handbook. Boston, MA. Springer; 2015.
    114. Lampropoulos G. Recommender systems in education: a literature review and bibliometric analysis. Adv Mobile Learn Educ Res. 2023;3(2):829-850. [FREE Full text] [CrossRef]
    115. da Silva FL, Slodkowski BK, da Silva KK, Cazella SC. A systematic literature review on educational recommender systems for teaching and learning: research trends, limitations and opportunities. Educ Inf Technol (Dordr). 2023;28(3):3289-3328. [FREE Full text] [CrossRef] [Medline]
    116. Clemente J, Yago H, de Pedro-Carracedo J, Bueno J. A proposal for an adaptive recommender system based on competences and ontologies. Expert Syst Appl. Dec 2022;208:118171. [FREE Full text] [CrossRef]
    117. Khobreh M, Ansari F, Dornhöfer M, Fathi M. An ontology-based recommender system to support nursing education and training. In: Proceedings of the German Conference on Learning, Knowledge, Adaptation. 2013. Presented at: LWA 2013; October 7-9, 2013; Bamberg, Germany. URL: https://minf.uni-bamberg.de/lwa2013/FinalPapers/lwa2013_submission_10.pdf
    118. Liou CH, Chen HS. CAR-based personalized learning activity recommendations for medical interns. In: Proceedings of the Sixteenth International Conference on Electronic Commerce. 2014. Presented at: ICEC '14; August 5-6, 2014; Philadelphia, PA. URL: https://doi.org/10.1145/2617848.2617854 [CrossRef]
    119. Hsu MH. Proposing a charting recommender system for second-language nurses. Expert Syst Appl. Aug 2011;38(8):9281-9286. [FREE Full text] [CrossRef]
    120. Liou CH. Personalized article recommendation based on student's rating mechanism in an online discussion forum. In: Proceedings of the 49th Hawaii International Conference on System Sciences. 2016. Presented at: HICSS 2016; January 5-8, 2016; Koloa, HI. URL: https://doi.org/10.1109/HICSS.2016.16 [CrossRef]
    121. Peters MD, Marnie C, Tricco AC, Pollock D, Munn Z, Alexander L, et al. Updated methodological guidance for the conduct of scoping reviews. JBI Evid Synth. Oct 2020;18(10):2119-2126. [FREE Full text] [CrossRef] [Medline]
    122. Arksey H, O'Malley L. Scoping studies: towards a methodological framework. Int J Soc Res Methodol. Feb 2005;8(1):19-32. [FREE Full text] [CrossRef]
    123. Munn Z, Peters MD, Stern C, Tufanaru C, McArthur A, Aromataris E. Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Med Res Methodol. Nov 19, 2018;18(1):143-147. [FREE Full text] [CrossRef] [Medline]
    124. Colquhoun H. Current best practices for the conduct of scoping reviews. EQUATOR Network. 2016. URL: https:/​/www.​equator-network.org/​wp-content/​uploads/​2016/​06/​Gerstein-Library-scoping-reviews_May-12.​pdf [accessed 2024-02-28]
    125. Shamseer L, Moher D, Clarke M, Ghersi D, Liberati A, Petticrew M, et al. Preferred reporting items for systematic review and meta-analysis protocols (PRISMA-P) 2015: elaboration and explanation. BMJ. Jan 02, 2015;350:g7647. [FREE Full text] [CrossRef] [Medline]
    126. Tricco AC, Lillie E, Zarin W, O'Brien KK, Colquhoun H, Levac D, et al. PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation. Ann Intern Med. Oct 02, 2018;169(7):467-473. [FREE Full text] [CrossRef] [Medline]
    127. Haddaway NR, Collins AM, Coughlin D, Kirk S. The role of Google Scholar in evidence reviews and its applicability to grey literature searching. PLoS One. 2015;10(9):e0138237. [FREE Full text] [CrossRef] [Medline]
    128. Aromataris E, Riitano D. Constructing a search strategy and searching for evidence. A guide to the literature search for a systematic review. Am J Nurs. May 2014;114(5):49-56. [FREE Full text] [CrossRef] [Medline]
    129. Urdaneta-Ponte MC, Mendez-Zorrilla A, Oleagordia-Ruiz I. Recommendation systems for education: systematic review. Electronics. Jul 06, 2021;10(14):1611. [FREE Full text] [CrossRef]
    130. EndNote 21. Clarivate. URL: https://support.clarivate.com/Endnote/s/article/EndNote-21-key-features?language=en_US [accessed 2025-07-31]
    131. Covidence homepage. Covidence. URL: https://www.covidence.org/ [accessed 2025-07-31]
    132. Pawliuk C, Brown HL, Widger K, Dewan T, Hermansen AM, Grégoire MC, et al. Optimising the process for conducting scoping reviews. BMJ Evid Based Med. Dec 2021;26(6):312. [FREE Full text] [CrossRef] [Medline]
    133. Aali G, Shokraneh F. No limitations to language, date, publication type, and publication status in search step of systematic reviews. J Clin Epidemiol. May 2021;133:165-167. [FREE Full text] [CrossRef] [Medline]
    134. Tricco AC, Lillie E, Zarin W, O'Brien K, Colquhoun H, Kastner M, et al. A scoping review on the conduct and reporting of scoping reviews. BMC Med Res Methodol. Mar 09, 2016;16:15. [FREE Full text] [CrossRef] [Medline]
    135. Dickersin K. The existence of publication bias and risk factors for its occurrence. JAMA. Mar 09, 1990;263(10):1385-1389. [CrossRef]

    ‎
    HPE: health professions education
    LLM: large language model
    MeSH: Medical Subject Headings
    PRISMA-ScR: Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews

    Edited by A Schwartz; submitted 12.12.24; peer-reviewed by P Makmee; comments to author 11.03.25; revised version received 06.05.25; accepted 06.06.25; published 21.08.25.

    Copyright

    ©Padraig Mark Healy, Colm O'Tuathaigh, Ciara Heavin, Nora McCarthy, Syed Latifi. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 21.08.2025.

    This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Research Protocols, is properly cited. The complete bibliographic information, a link to the original publication on https://www.researchprotocols.org, as well as this copyright and license information must be included.