JMIR Medical Education最新文献

Background: Generative large language models (LLMs) have the potential to revolutionize medical education by generating tailored learning materials, enhancing teaching efficiency, and improving learner engagement. However, the application of LLMs in health care settings, particularly for augmenting small datasets in text classification tasks, remains underexplored, particularly for cost- and privacy-conscious applications that do not permit the use of third-party services such as OpenAI's ChatGPT.

Objective: This study aims to explore the use of open-source LLMs, such as Large Language Model Meta AI (LLaMA) and Alpaca models, for data augmentation in a specific text classification task related to hospital staff surveys.

Methods: The surveys were designed to elicit narratives of everyday adaptation by frontline radiology staff during the initial phase of the COVID-19 pandemic. A 2-step process of data augmentation and text classification was conducted. The study generated synthetic data similar to the survey reports using 4 generative LLMs for data augmentation. A different set of 3 classifier LLMs was then used to classify the augmented text for thematic categories. The study evaluated performance on the classification task.

Results: The overall best-performing combination of LLMs, temperature, classifier, and number of synthetic data cases is via augmentation with LLaMA 7B at temperature 0.7 with 100 augments, using Robustly Optimized BERT Pretraining Approach (RoBERTa) for the classification task, achieving an average area under the receiver operating characteristic (AUC) curve of 0.87 (SD 0.02; ie, 1 SD). The results demonstrate that open-source LLMs can enhance text classifiers' performance for small datasets in health care contexts, providing promising pathways for improving medical education processes and patient care practices.

Conclusions: The study demonstrates the value of data augmentation with open-source LLMs, highlights the importance of privacy and ethical considerations when using LLMs, and suggests future directions for research in this field.

Background: Virtual reality (VR) is increasingly being used in higher education for clinical skills training and role-playing among health care students. Using 360° videos in VR headsets, followed by peer debrief and group discussions, may strengthen students' social and emotional learning.

Objective: This study aimed to explore student-perceived usability of VR simulation in three health care education programs in Norway.

Methods: Students from one university participated in a VR simulation program. Of these, students in social education (n=74), nursing (n=45), and occupational therapy (n=27) completed a questionnaire asking about their perceptions of the usability of the VR simulation and the related learning activities. Differences between groups of students were examined with Pearson chi-square tests and with 1-way ANOVA. Qualitative content analysis was used to analyze data from open-ended questions.

Results: The nursing students were most satisfied with the usability of the VR simulation, while the occupational therapy students were least satisfied. The nursing students had more often prior experience from using VR technology (60%), while occupational therapy students less often had prior experience (37%). Nevertheless, high mean scores indicated that the students experienced the VR simulation and the related learning activities as very useful. The results also showed that by using realistic scenarios in VR simulation, health care students can be prepared for complex clinical situations in a safe environment. Also, group debriefing sessions are a vital part of the learning process that enhance active involvement with peers.

Conclusions: VR simulation has promise and potential as a pedagogical tool in health care education, especially for training soft skills relevant for clinical practice, such as communication, decision-making, time management, and critical thinking.

[This corrects the article DOI: 10.2196/64125.].

Background: Competence-based medical education requires robust data to link competence with clinical experiences. The SARS-CoV-2 (COVID-19) pandemic abruptly altered the standard trajectory of clinical exposure in medical training programs. Residency program directors were tasked with identifying and addressing the resultant gaps in each trainee's experiences using existing tools.

Objective: This study aims to demonstrate a feasible and efficient method to capture electronic health record (EHR) data that measure the volume and variety of pediatric resident clinical experiences from a continuity clinic; generate individual-, class-, and graduate-level benchmark data; and create a visualization for learners to quickly identify gaps in clinical experiences.

Methods: This pilot was conducted in a large, urban pediatric residency program from 2016 to 2022. Through consensus, 5 pediatric faculty identified diagnostic groups that pediatric residents should see to be competent in outpatient pediatrics. Information technology consultants used International Classification of Diseases, Tenth Revision (ICD-10) codes corresponding with each diagnostic group to extract EHR patient encounter data as an indicator of exposure to the specific diagnosis. The frequency (volume) and diagnosis types (variety) seen by active residents (classes of 2020-2022) were compared with class and graduated resident (classes of 2016-2019) averages. These data were converted to percentages and translated to a radar chart visualization for residents to quickly compare their current clinical experiences with peers and graduates. Residents were surveyed on the use of these data and the visualization to identify training gaps.

Results: Patient encounter data about clinical experiences for 102 residents (N=52 graduates) were extracted. Active residents (n=50) received data reports with radar graphs biannually: 3 for the classes of 2020 and 2021 and 2 for the class of 2022. Radar charts distinctly demonstrated gaps in diagnoses exposure compared with classmates and graduates. Residents found the visualization useful in setting clinical and learning goals.

Conclusions: This pilot describes an innovative method of capturing and presenting data about resident clinical experiences, compared with peer and graduate benchmarks, to identify learning gaps that may result from disruptions or modifications in medical training. This methodology can be aggregated across specialties and institutions and potentially inform competence-based medical education.

Background: Recent studies, including those by the National Board of Medical Examiners, have highlighted the remarkable capabilities of recent large language models (LLMs) such as ChatGPT in passing the United States Medical Licensing Examination (USMLE). However, there is a gap in detailed analysis of LLM performance in specific medical content areas, thus limiting an assessment of their potential utility in medical education.

Objective: This study aimed to assess and compare the accuracy of successive ChatGPT versions (GPT-3.5, GPT-4, and GPT-4 Omni) in USMLE disciplines, clinical clerkships, and the clinical skills of diagnostics and management.

Methods: This study used 750 clinical vignette-based multiple-choice questions to characterize the performance of successive ChatGPT versions (ChatGPT 3.5 [GPT-3.5], ChatGPT 4 [GPT-4], and ChatGPT 4 Omni [GPT-4o]) across USMLE disciplines, clinical clerkships, and in clinical skills (diagnostics and management). Accuracy was assessed using a standardized protocol, with statistical analyses conducted to compare the models' performances.

Results: GPT-4o achieved the highest accuracy across 750 multiple-choice questions at 90.4%, outperforming GPT-4 and GPT-3.5, which scored 81.1% and 60.0%, respectively. GPT-4o's highest performances were in social sciences (95.5%), behavioral and neuroscience (94.2%), and pharmacology (93.2%). In clinical skills, GPT-4o's diagnostic accuracy was 92.7% and management accuracy was 88.8%, significantly higher than its predecessors. Notably, both GPT-4o and GPT-4 significantly outperformed the medical student average accuracy of 59.3% (95% CI 58.3-60.3).

Conclusions: GPT-4o's performance in USMLE disciplines, clinical clerkships, and clinical skills indicates substantial improvements over its predecessors, suggesting significant potential for the use of this technology as an educational aid for medical students. These findings underscore the need for careful consideration when integrating LLMs into medical education, emphasizing the importance of structured curricula to guide their appropriate use and the need for ongoing critical analyses to ensure their reliability and effectiveness.

Unlabelled: In the field of medicine, uncertainty is inherent. Physicians are asked to make decisions on a daily basis without complete certainty, whether it is in understanding the patient's problem, performing the physical examination, interpreting the findings of diagnostic tests, or proposing a management plan. The reasons for this uncertainty are widespread, including the lack of knowledge about the patient, individual physician limitations, and the limited predictive power of objective diagnostic tools. This uncertainty poses significant problems in providing competent patient care. Research efforts and teaching are attempts to reduce uncertainty that have now become inherent to medicine. Despite this, uncertainty is rampant. Artificial intelligence (AI) tools, which are being rapidly developed and integrated into practice, may change the way we navigate uncertainty. In their strongest forms, AI tools may have the ability to improve data collection on diseases, patient beliefs, values, and preferences, thereby allowing more time for physician-patient communication. By using methods not previously considered, these tools hold the potential to reduce the uncertainty in medicine, such as those arising due to the lack of clinical information and provider skill and bias. Despite this possibility, there has been considerable resistance to the implementation of AI tools in medical practice. In this viewpoint article, we discuss the impact of AI on medical uncertainty and discuss practical approaches to teaching the use of AI tools in medical schools and residency training programs, including AI ethics, real-world skills, and technological aptitude.

Unlabelled: Digital transformation has disrupted many industries but is yet to revolutionize health care. Educational programs must be aligned with the reality that goes beyond developing individuals in their own professions, professionals wishing to make an impact in digital health will need a multidisciplinary understanding of how business models, organizational processes, stakeholder relationships, and workforce dynamics across the health care ecosystem may be disrupted by digital health technology. This paper describes the redesign of an existing postgraduate program, ensuring that core digital health content is relevant, pedagogically sound, and evidence-based, and that the program provides learning and practical application of concepts of the digital transformation of health. Existing subjects were mapped to the American Medical Informatics Association Clinical Informatics Core Competencies, followed by consultation with leadership to further identify gaps or opportunities to revise the course structure. New additions of core and elective subjects were proposed to align with the competencies. Suitable electives were chosen based on stakeholder feedback and a review of subjects in fields relevant to digital transformation of health. The program was revised with a new title, course overview, course intended learning outcomes, reorganizing of core subjects, and approval of new electives, adding to a suite of professional development offerings and forming a structured pathway to further qualification. Programs in digital health must move beyond purely informatics-based competencies toward enabling transformational change. Postgraduate program development in this field is possible within a short time frame with the use of established competency frameworks and expert and student consultation.

Background: Undergraduate medical students often lack hands-on research experience and fundamental scientific research skills, limiting their exposure to the practical aspects of scientific investigation. The Cerrahpasa Neuroscience Society introduced a program to address this deficiency and facilitate student-led research.

Objective: The primary goal of this initiative was to enhance medical students' research output by enabling them to generate and publish peer-reviewed papers within the framework of this pilot project. The project aimed to provide an accessible, global model for research training through structured journal clubs, mentorship from experienced peers, and resource access.

Methods: In January 2022, a total of 30 volunteer students from various Turkish medical schools participated in this course-based undergraduate research experience program. Students self-organized into 2 groups according to their preferred study type: original research or systematic review. Two final-year students with prior research experience led the project, developing training modules using selected materials. The project was implemented entirely online, with participants completing training modules before using their newly acquired theoretical knowledge to perform assigned tasks.

Results: Based on student feedback, the project timeline was adjusted to allow for greater flexibility in meeting deadlines. Despite these adjustments, participants successfully completed their tasks, applying the theoretical knowledge they had gained to their respective assignments. As of April 2024, the initiative has culminated in 3 published papers and 3 more under peer review. The project has also seen an increase in student interest in further involvement and self-paced learning.

Conclusions: This initiative leverages globally accessible resources for research training, effectively fostering research competency among participants. It has successfully demonstrated the potential for undergraduates to contribute to medical research output and paved the way for a self-sustaining, student-led research program. Despite some logistical challenges, the project provided valuable insights for future implementations, showcasing the potential for students to engage in meaningful, publishable research.

Background: Artificial intelligence (AI) chatbots are poised to have a profound impact on medical education. Medical students, as early adopters of technology and future health care providers, play a crucial role in shaping the future of health care. However, little is known about the utilization of, perceptions on, and intention to use AI chatbots among medical students in China.

Objective: This study aims to explore the utilization of, perceptions on, and intention to use generative AI chatbots among medical students in China, using the Unified Theory of Acceptance and Use of Technology (UTAUT) framework. By conducting a national cross-sectional survey, we sought to identify the key determinants that influence medical students' acceptance of AI chatbots, thereby providing a basis for enhancing their integration into medical education. Understanding these factors is crucial for educators, policy makers, and technology developers to design and implement effective AI-driven educational tools that align with the needs and expectations of future health care professionals.

Methods: A web-based electronic survey questionnaire was developed and distributed via social media to medical students across the country. The UTAUT was used as a theoretical framework to design the questionnaire and analyze the data. The relationship between behavioral intention to use AI chatbots and UTAUT predictors was examined using multivariable regression.

Results: A total of 693 participants were from 57 universities covering 21 provinces or municipalities in China. Only a minority (199/693, 28.72%) reported using AI chatbots for studying, with ChatGPT (129/693, 18.61%) being the most commonly used. Most of the participants used AI chatbots for quickly obtaining medical information and knowledge (631/693, 91.05%) and increasing learning efficiency (594/693, 85.71%). Utilization behavior, social influence, facilitating conditions, perceived risk, and personal innovativeness showed significant positive associations with the behavioral intention to use AI chatbots (all P values were <.05).

Conclusions: Chinese medical students hold positive perceptions toward and high intentions to use AI chatbots, but there are gaps between intention and actual adoption. This highlights the need for strategies to improve access, training, and support and provide peer usage examples to fully harness the potential benefits of chatbot technology.