Eric J. Warm

The concurrent uptake of both artificial intelligence (AI) and competency-based health professions education (CBHPE) represents a watershed opportunity to improve and streamline educational processes and enhance educational effectiveness. Members of the International Competency-based Health Professions Educators Collaborative (ICBHPE) explored the potential of AI to strengthen CBHPE implementation by addressing persistent challenges in meeting its five core components: defined outcome competencies; progressive sequencing; tailored learning experiences; competency-focused instruction; and programmatic assessment. Effective integration of AI tools can be guided by socio-technical systems theory (STST), which highlights the significant interdependence of technical systems and social systems. Successful application of AI in HPE will hinge on addressing the complex interactions among people and roles; goals and incentives; workflows and processes; technology; infrastructure; and organizational culture. Health professions educators should enhance their fundamental knowledge of how AI tools are developed and deployed to understand both its potential and its limitations. The HPE community must rigorously evaluate AI applications to ensure responsible and equitable integration that complements human relationships and judgment.

Purpose: Visual analytics is a nascent and underexplored area in the medical education literature that can assist in synthesizing large volumes of data and information to provide actionable insight. This scoping review aims to identify: 1) the characteristics of the studies that have applied visual analytics in medical education, 2) how visual analytics are being used to support medical education efforts. Method: This study followed the Joanna Briggs Institute (JBI) scoping review guidelines to search four databases in mid-April 2026: PubMed, IEEE Xplore, Scopus, ACM Digital, along with Google Scholar. Key search terms included “medical education” and “visual analytics”; papers that did not implement visual analytics systems in the medical education context were excluded. Variables of the eligible papers were extracted and further analyzed in terms of study characteristics (publication year, study location, primary focus & level of trainees assessed) and application of visual analytics (type of visualization, framework guidance, hardware/software, evaluation technique). Results: Of the 39 eligible papers from 584 screened, 20 (51.3%) were published in the United States. Using visual analytics for learner competency assessment and quality improvement of training programs were the primary focuses. For trainees, nearly all papers focused on assessing residents and medical students. More than 28 (71.8%) studies utilized an interactive tool/dashboard and/or applied an evaluation technique. Only 14 (35.9%) involved a framework-guided design of the visualization. Conclusions: This review highlights that while visual analytics is maturing in medical education, systemic application requires adopting framework-guided visualization design, expertise-matched tools, and goal-oriented evaluation. Future research should prioritize interoperable frameworks for knowledge sharing, controlled field studies assessing impacts on learner competencies, and patient outcomes, and "cross-continuum" dashboards spanning pre-medical through faculty levels. These strategies allow educators and learners to make sense of complex educational data through visual analytics dashboards, ultimately enhancing assessment and patient care quality.

Purpose: Electronic health records (EHRs) can provide valuable insights into workflow, clinical reasoning, and personal attributes; however, the indicators for how an individual acts within the EHR (EHR use metrics) are not frequently analyzed. This study examines whether EHR use metrics are associated with internal medicine resident clinical performance. Method: In this retrospective cohort study, data on EHR use metrics and achievement of 22 clinical performance measures (CPMs) were collected between November 2021–October 2022 from University of Cincinnati internal medicine residents during a year dedicated to ambulatory care. The CPMs were sorted on an attribution–contribution continuum for subgroup analysis. The EHR use metrics were used for agglomerative hierarchical clustering to group residents with similar EHR behaviors. Results: Thirty residents (11 [37%] male and 19 [63%] female) were included. Clustering with a subset of 10 EHR use metrics resulted in 3 clusters with different clinical performance as indicated by achievement of CPMs. The clusters were characterized as lower-performing (n = 5; mean [SD] CPMs achieved, 11.4 [2.3]; 95% CI, 9.4–13.4), middle-performing (n = 23; mean [SD] CPMs achieved, 15.8 [2.1]; 95% CI, 14.9–16.6), and higher-performing (n = 2; mean [SD] CPMs achieved, 22 [0]; 95% CI, 22–22). After sorting the CPMs on an attribution–contribution continuum, the clusters performed differently in actions (F _2,27 = 7.73, P = .002) and screenings (F _2,27 = 9.60, P < .001) but not lab testing (F _2,27 = 2.88, P = .07) or disease control (F _2,27 = 1.01, P = .38). The lower-performing cluster had longer response times and incomplete work, whereas the higher-performing cluster was most responsive and communicative. Conclusions: Hierarchical cluster analysis of EHR use metrics can identify EHR use patterns associated with resident clinical performance. Clustering provides a framework that will enable programs to apply EHR use metrics to augment resident assessment and feedback.

Entrustable professional activities (EPAs) and entrustment decision-making have become common language in competency-based education in the health professions. Since its introduction, several other related concepts have been introduced, which has made it more complex to get an overview of the domain. This chapter sets out to discuss OPAs (observable practice activities), EPA specifications, nested EPAs, core EPAs versus elective EPAs, transdisciplinary EPAs, Practice Activities as used by the WHO, retrospective versus prospective entrustment–supervision scales, STARs (statements of awarded responsibility), microcredentials, and hospital privileging. The concepts are defined and elaborated with examples.

An abstract is unavailable. This article is available as a PDF only.

The shift to pass/fail grading in undergraduate medical education was designed to reduce medical students’ stress. However, this change has given rise to a “shadow economy of effort,” as students move away from traditional didactic and clinical learning to engage in increasing numbers of research, volunteer, and work experiences to enhance their residency applications. These extracurricular efforts to secure a residency position are subphenomena of the hidden curriculum. Medical schools do not officially require all the activities students need to be most competitive for residency selection; therefore, students, as rational actors, participate in the activities they think will most help them succeed. Here, the authors frame residency application and selection as a complex adaptive system (CAS), which self-organizes without centralized control or hierarchical intent. Individuals in a CAS operate in environments marked by volatility, randomness, and uncertainty—all of which are abundant in the residency selection process. Outcomes in such systems, like the development of a shadow economy, are novel, emergent, and cannot always be anticipated. To address these challenges, the authors suggest the need for deep understanding of the system’s elements, interrelationships, and dynamics, including feedback loops and emergent properties. Optimizing the results of a CAS requires incentivizing outcomes over activities, ensuring open information flow, and engaging in continuous monitoring and evaluation. The current pass/fail era and resultant shadow economy of effort risk creating a triple harm by devaluing clinical excellence, burning out medical students, and potentially producing superficial or, worse, inauthentic academic and community work. Medical educators must optimize residency application and selection for cooperative outcomes and design incentives to ensure the outputs of medical education align student, institutional, patient, and societal goals. Without a set of predictive “answers,” the authors suggest a process of determining actions to advance this ultimate aim and reduce harm.