What do medical students actually need to know about artificial intelligence?

Abstract

With emerging innovations in artificial intelligence (AI) poised to substantially impact medical practice, interest in training current and future physicians about the technology is growing. Alongside comes the question of what, precisely, should medical students be taught. While competencies for the clinical usage of AI are broadly similar to those for any other novel technology, there are qualitative differences of critical importance to concerns regarding explainability, health equity, and data security. Drawing on experiences at the University of Toronto Faculty of Medicine and MIT Critical Data's "datathons", the authors advocate for a dualfocused approach: combining robust data science-focused additions to baseline health research curricula and extracurricular programs to cultivate leadership in this space.

Undergraduate Medical Competencies in Digital Health and Curricular Module Development: Mixed Methods Study

“…Brunner et al [ 38 ] classified the digital health capabilities expected of medical graduates into 4 domains: (1) digital technologies, systems, and policies , covering digital literacy and ELSI; (2) c linical practice and applications , including the ability to integrate digital health into clinical routine; (3) data analysis and knowledge creation, including the ability to apply basic data analytics to unstructured digital data sets; and (4) and system and technology implementation, suggesting that medical professionals should participate in the development and implementation of digital health. The latter aspect is also stressed by our results and a recent publication that demands physicians with dual competencies in clinical and data science expertise [ 49 ]. A medical graduate should be able to use digital health technology, interpret its results, and explain those to the patients.…”

“…This process is driven by individual pilot projects rather than by validated and coordinated guidelines or national regulations [ 16 , 38 , 40 - 48 ]. Pilot projects, adapted to the individual curricular conditions of medical faculties, can be the first step toward realizing a longitudinal interdisciplinary approach to implement digital health in the overall curriculum [ 13 , 16 , 49 - 51 ].…”

“…A focus on students’ engagement (eg, own creation in hackathons, peer teaching) and linking knowledge transfer to practical experiences (eg, bedside teaching with available digital technology) is desirable and effective. Students should be given the opportunity to deepen their knowledge and skills in special fields (eg, clinical data science, design thinking) in extracurricular activities or in the form of an elective module [ 49 ]. The exchange with other disciplines in workshops or hackathons can be the seed for future health innovations and entrepreneurial ventures.…”

Why educating for clinical machine learning still requires attention to history: a rejoinder to Gauld et al

“…While this is no new demand (Shorter, 2008), it may not have received enough attention in the context of psychiatric ML yet. Of course, we are aware that curricula run the danger of being overburdened in the context of ML, and agree with Gauld et al (2020) and McCoy et al (2020) that training should focus on fundamental concepts. However, education about the historical development and employment of psychiatric classifications should be considered part of these fundamental issues and will remain crucial to counter potential ethical, clinical and conceptual pitfalls of ML in psychiatry.…”

Knowledge of and Attitudes on Artificial Intelligence in Healthcare: A Provincial Survey Study of Medical Students

“…A survey was conducted rather than interviews or focus groups as our goal was increased representation (number of students), and to capture standardized data on individual student knowledge and perceptions on a wide variety of aspects on AI in medicine, and as opposed to an in-depth exploration of student perspectives with a limited number of questions (Kelley et al ., 2003). Survey questions were developed following a review of articles proposing to integrate AI competencies into UME (Masters, 2019; Davenport and Kalakota, 2019; Paranjape et al ., 2019; Kolachalama and Garg, 2018; Wartman and Combs, 2019; McCoy et al ., 2020), previous surveys of physician and medical student attitudes on AI in medicine (Laï, Brian and Mamzer, 2020; Blease et al ., 2019; Oh et al ., 2019; Blease et al ., 2018), and consultation with educators involved in developing AI in medicine curricula at the University of Toronto Medical School. The complete survey questionnaire is included in Supplementary Figure 1.…”