Applications of Artificial Intelligence in Teaching Diagnostic Interpretation Skills to Health Professions Students: A Scoping Review

Background and Rationale Diagnostic interpretation skills, including the interpretation of electrocardiograms, medical images, laboratory data, and clinical cases, are fundamental competencies for health professions students. Developing these skills is cognitively complex and traditionally relies on supervised clinical exposure and expert feedback, which can be inconsistent and resource intensive. In recent years, artificial intelligence (AI) technologies—such as machine learning, deep learning, intelligent tutoring systems, and adaptive learning platforms—have been increasingly applied in health professions education to support learning, feedback, and assessment. While AI has demonstrated promising applications in clinical diagnostics, its role in teaching diagnostic interpretation skills remains less clearly defined. Existing studies are diverse in terms of diagnostic domains, educational settings, AI technologies, and outcome measures. To date, no comprehensive synthesis has systematically mapped how AI is being used to teach diagnostic interpretation skills across health professions education. A scoping review is therefore warranted to explore the extent, nature, and characteristics of the existing evidence and to identify gaps that may inform future educational research and curriculum development. Purpose of the Review The purpose of this scoping review is to systematically map the literature on applications of artificial intelligence in teaching diagnostic interpretation skills to health professions students. The review aims to provide an overview of how AI technologies are being used in educational contexts, the diagnostic domains addressed, the educational approaches employed, and the outcomes reported. Review Questions The primary research question guiding this scoping review is: What are the applications of artificial intelligence in teaching diagnostic interpretation skills to health professions students? Secondary questions include: What types of AI technologies are used to support the teaching of diagnostic interpretation skills? Which diagnostic domains (e.g., ECG, radiology, pathology, clinical reasoning) are addressed using AI-based educational interventions? In what educational contexts and learning settings are these AI applications implemented? What educational outcomes are reported in relation to AI-supported diagnostic interpretation training? What gaps exist in the current literature? Methods Overview This scoping review will be conducted using the Arksey and O’Malley framework, with methodological enhancements described by Levac et al., and reported in accordance with the PRISMA-ScR guidelines. The review will include the following stages: Identifying the research question Identifying relevant studies Study selection Charting the data Collating, summarising, and reporting the results A comprehensive search will be conducted across multiple electronic databases, including PubMed/MEDLINE, Scopus, Web of Science, ERIC, IEEE Xplore, and Google Scholar. Studies involving health professions students and the use of AI for teaching diagnostic interpretation skills in educational or training contexts will be eligible for inclusion. Data will be charted using a pre-defined extraction framework and synthesised descriptively and narratively. Expected Outcomes This scoping review is expected to: Provide a comprehensive mapping of AI applications used to teach diagnostic interpretation skills in health professions education. Identify patterns and trends in the use of specific AI technologies across different diagnostic domains. Summarise the educational approaches and outcomes associated with AI-supported diagnostic training. Highlight research gaps, including underrepresented disciplines, limited outcome measures, and areas requiring further empirical investigation. Inform educators, curriculum designers, and researchers about current practices and future directions for integrating AI into diagnostic skills training. Significance By synthesising and mapping existing evidence, this review will contribute to a clearer understanding of the role of artificial intelligence in teaching diagnostic interpretation skills. The findings are expected to support evidence-informed curriculum design, guide future educational research, and contribute to discussions on the responsible and effective integration of AI in health professions education. Ethics and Dissemination As this study involves the analysis of published literature only, ethical approval is not required. The findings of the review will be disseminated through academic publication and may also inform educational practice and policy discussions related to AI in health professions education.