Artificial intelligence and clinical anatomical education: Promises and perils

Challenge, integration, and change: ChatGPT and future anatomical education

With the vigorous development of ChatGPT and its application in the field of education, a new era of the collaborative development of human and artificial intelligence and the symbiosis of education has come. Integrating artificial intelligence (AI) into medical education has the potential to revolutionize it. Large language models, such as ChatGPT, can be used as virtual teaching aids to provide students with individualized and immediate medical knowledge, and conduct interactive simulation learning and detection. In this paper, we discuss the application of ChatGPT in anatomy teaching and its various application levels based on our own teaching experiences, and discuss the advantages and disadvantages of ChatGPT in anatomy teaching. ChatGPT increases student engagement and strengthens students' ability to learn independently. At the same time, ChatGPT faces many challenges and limitations in medical education. Medical educators must keep pace with the rapid changes in technology, taking into account ChatGPT's impact on curriculum design, assessment strategies and teaching methods. Discussing the application of ChatGPT in medical education, especially anatomy teaching, is helpful to the effective integration and application of artificial intelligence tools in medical education.

ChatGPT versus a customized AI chatbot (Anatbuddy) for anatomy education: A comparative pilot study

Large Language Models (LLMs) have the potential to improve education by personalizing learning. However, ChatGPT-generated content has been criticized for sometimes producing false, biased, and/or hallucinatory information. To evaluate AI's ability to return clear and accurate anatomy information, this study generated a custom interactive and intelligent chatbot (Anatbuddy) through an Open AI Application Programming Interface (API) that enables seamless AI-driven interactions within a secured cloud infrastructure. Anatbuddy was programmed through a Retrieval Augmented Generation (RAG) method to provide context-aware responses to user queries based on a predetermined knowledge base. To compare their outputs, various queries (i.e., prompts) on thoracic anatomy (n = 18) were fed into Anatbuddy and ChatGPT 3.5. A panel comprising three experienced anatomists evaluated both tools' responses for factual accuracy, relevance, completeness, coherence, and fluency on a 5-point Likert scale. These ratings were reviewed by a third party blinded to the study, who revised and finalized scores as needed. Anatbuddy's factual accuracy (mean ± SD = 4.78/5.00 ± 0.43; median = 5.00) was rated significantly higher (U = 84, p = 0.01) than ChatGPT's accuracy (4.11 ± 0.83; median = 4.00). No statistically significant differences were detected between the chatbots for the other variables. Given ChatGPT's current content knowledge limitations, we strongly recommend the anatomy profession develop a custom AI chatbot for anatomy education utilizing a carefully curated knowledge base to ensure accuracy. Further research is needed to determine students' acceptance of custom chatbots for anatomy education and their influence on learning experiences and outcomes.

Generative artificial intelligence and the personalization of health professional education: A narrative review

This narrative review examined the intersection of generative artificial intelligence (GAI) and the personalization of health professional education (PHE). This review aims to the elucidate the current condition of GAI technologies and their particular uses in the field of PHE. Data were extracted and analyzed from studies focusing on the demographics and professional development preferences of healthcare workers, the competencies required for personalized precision medicine, and the current and potential applications of artificial intelligence (AI) in PHE. The review also addressed the ethical implications of AI implementation in this context. Findings indicated a gender-balanced healthcare workforce with a predisposition toward continuous professional development and digital tool utilization. A need for a comprehensive educational framework was identified to include a spectrum of skills crucial for precision medicine, emphasizing the importance of patient involvement and bioethics. AI was found to enhance educational experiences and research in PHE, with an increasing trend in AI applications, particularly in surgical education since 2018. Ethical challenges associated with AI integration in PHE were highlighted, with an emphasis on the need for ethical design and diverse development teams. Core concepts in AI research were established, with a spotlight on emerging areas such as data science and learning analytics. The application of AI in PHE was recognized for its current benefits and potential for future advancements, with a call for ethical vigilance. GAI holds significant promise for personalizing PHE, with an identified need for ethical frameworks and diverse developer teams to address bias and equity in educational AI applications.

Twelve tips for developing healthcare learners' uncertainty tolerance

BACKGROUND

Uncertainty is pervasive throughout healthcare practice. Uncertainty tolerance (i.e. adaptively responding to perceived uncertainty) is considered to benefit practitioner wellbeing, encourage person-centred care, and support judicious healthcare resource utilisation. Accordingly, uncertainty tolerance development is increasingly referenced within training frameworks. Practical approaches to support healthcare learners' uncertainty tolerance development, however, are lacking.

AIMS

Drawing on findings across the literature, and the authors' educational experiences, twelve tips for promoting healthcare learners' uncertainty tolerance were developed.

RESULTS

Tips are divided into 1. Tips for Learners, 2. Tips for Educators and Supervisors, and 3. Tips for Healthcare Education Institutions and Systems. Each tip summarises relevant research findings, alongside applications to educational practice.

CONCLUSIONS

Approaches to developing uncertainty tolerance balance factors supporting learners through uncertain experiences, with introducing challenges for learners to further develop uncertainty tolerance. These tips can reassure healthcare education stakeholders that developing learner uncertainty tolerance, alongside core knowledge, is achievable.

Using artificial intelligence to grade practical laboratory examinations: Sacrificing students' learning experiences for saving time?

The use of artificial intelligence (AI) by students has recently been made a key topic among educators because of the potential to transform students' learning experiences. However, the use of AI-based software by instructors has not received the same level of consideration despite its recent accessibility and prevalence. This contribution discusses the benefits, challenges, and limitations of commercial AI-based software (Gradescope®) for grading summative, short answer practical examinations in an undergraduate gross anatomy course. While the integration of Gradescope® in grading practical examinations reduces time and perceived instructor biases, it might erode personal relationships between students and instructors, especially with regard to individual feedback. Future research should assess best practices for incorporating AI technology into course grading considering the challenges and trade-offs to students and instructors.

Evaluating AI-powered text-to-image generators for anatomical illustration: A comparative study

Medical illustration, which involves the creation of visual representations of anatomy, has long been an essential tool for medical professionals and educators. The integration of AI and medical illustration has the potential to revolutionize the field of anatomy education, providing highly accurate, customizable images. The authors evaluated three AI-powered text-to-image generators in producing anatomical illustrations of the human skulls, heart, and brain. The generators were assessed for their accurate depiction of foramina, suture lines, coronary arteries, aortic and pulmonary trunk branching, gyri, sulci, and the relationship between the cerebellum and temporal lobes. None of the generators produced illustrations with comprehensive anatomical details. Foramina, such as the mental and supraorbital foramina, were frequently omitted, and suture lines were inaccurately represented. The illustrations of the heart failed to indicate proper coronary artery origins, and the branching of the aorta and pulmonary trunk was often incorrect. Brain illustrations lacked accurate gyri and sulci depiction, and the relationship between the cerebellum and temporal lobes remained unclear. Although AI generators tended toward esoteric imagery, they exhibited significant speed and cost advantages over human illustrators. However, improving their accuracy necessitates augmenting the training databases with anatomically correct images. The study emphasizes the ongoing role of human medical illustrators, especially in ensuring the provision of accurate and accessible illustrations.

Ethical concerns surrounding artificial intelligence in anatomy education: Should AI human body simulations replace donors in the dissection room?

The potential effects of artificial intelligence (AI) on the teaching of anatomy are unclear. We explore the hypothetical situation of human body donors being replaced by AI human body simulations and reflect on two separate ethical concerns: first, whether it is permissible to replace donors with AI human body simulations in the dissection room when the consequences of doing so are unclear, and second, the overarching ethical significance of AI use in anatomy education. To do this, we highlight the key benefits of student exposure to the dissection room and body donors, including nontechnical, discipline-independent skills, awareness and interaction with applied bioethics, and professional identity formation. We suggest that the uniqueness of the dissection room experience and the importance of the key benefits accompanying this exposure outweigh the potential and so far unknown benefits of AI technology in this space. Further, the lack of engagement with bioethical principles that are intimately intertwined with the dissection room experience may have repercussions for future healthcare professional development. We argue that interaction with body donors must be protected and maintained and not replaced with AI human body donor simulations. Any move away from this foundation of anatomy education requires scrutiny. In light of the possible adoption of AI technologies into anatomy teaching, it is necessary that medical educators reflect on the dictum that the practice of healthcare, and anatomy, is a uniquely human endeavor.

Using design thinking to create and implement a 3D digital library of anatomical specimens

Design thinking (DT) is a five-stage process (empathize, define, ideate, prototype, and test) that guides the creation of user-centered solutions to complex problems. DT is in common use outside of science but has rarely been applied to anatomical education. The use of DT in this study identified the need for flexible access to anatomical specimens outside of the anatomy laboratory and guided the creation of a digital library of three-dimensional (3D) anatomical specimens (3D Anatomy Viewer). To test whether the resource was fit for purpose, a mixed-methods student evaluation was undertaken. Student surveys (n = 46) were employed using the system usability scale (SUS) and an unvalidated acceptability questionnaire. These verified that 3D Anatomy Viewer was usable (SUS of 72%) and acceptable (agreement range of 77%-93% on all Likert-type survey statements, Cronbach's alpha = 0.929). Supplementary interviews (n = 5) were analyzed through content analysis and revealed three main themes: (1) a credible online supplementary learning resource; (2) learning anatomy with 3D realism and interactivity; (3) user recommendations for expanding the number of anatomical models, test questions, and gamification elements. These data demonstrate that a DT framework can be successfully applied to anatomical education for creation of a practical learning resource. Anatomy educators should consider employing a DT framework where student-centered solutions to learner needs are required.

Responding to the healthcare workforce shortage: A scoping review exploring anatomical pathologists' professional identities over time

Anatomical pathology (AP) is an anatomy-centric medical specialty devoted to tissue-based diagnosis of disease. The field faces a current and predicted workforce shortage, likely increasing diagnostic wait times and delaying patient access to urgent treatment. A lack of AP exposure is proposed to preclude recruitment to the field, as medical students are afforded only a limited understanding of who a pathologist is and what they do (their professional identity/PI and role). Anatomical sciences educators may be well placed to increase student understanding of anatomical pathologists' PI features, but until features of anatomical pathologists' PI are understood, recommendations for anatomy educators are premature. Thus, this scoping review asked: "What are the professional identity features of anatomical pathologists reported in the literature, and how have these changed over time?" A six-stage scoping review was performed. Medline and PubMed, Global Health, and Embase were used to identify relevant studies (n = 74). Team-based framework analysis identified that features of anatomical pathologists' professional identity encompass five overarching themes: professional practice, views about the role, training and education, personal implications, and technology. Technology was identified as an important theme of anatomical pathologists' PI, as it intersected with many other PI feature themes, including diagnosis and collaboration. This review found that pathologists may sometimes perceive professional competition with technology, such as artificial intelligence. These findings suggest unique opportunities for integrating AP-specific PI features into anatomy teaching, which may foster student interest in AP, and potentially increase recruitment into the field.

Transfer of learning in histology: Insights from a longitudinal study

All anatomical educators hope that students apply past training to both similar and new tasks. This two-group longitudinal study investigated the development of such transfer of learning in a histology course. After 0, 10, and 20 sessions of the 10-week-long course, medical students completed theoretical tasks, examined histological slides trained in the course (retention task), and unfamiliar histological slides (transfer task). The results showed that students in the histology group gradually outperformed the control group in all tasks, especially in the second half of the course, η2  = 0.268 (p < 0.001). The best predictor of final transfer performance was students' retention performance after 10 sessions, β = 0.32 (p = 0.028), and theoretical knowledge after 20 sessions, β = 0.46 (p = 0.003). Results of eye tracking methodology further revealed that the histology group engaged in greater "visual activity" when solving transfer tasks, as indicated by an increase in the total fixation count, η2  = 0.103 (p = 0.014). This longitudinal study provides evidence that medical students can use what they learn in histology courses to solve unfamiliar problems but cautions that positive transfer effects develop relatively late in the course. Thus, course time and the complex relationship between theory, retention, and transfer holds critical implications for anatomical curricula seeking to foster the transfer of learning.

Evaluation of ChatGPT's Real-Life Implementation in Undergraduate Dental Education: Mixed Methods Study

BACKGROUND

The recent artificial intelligence tool ChatGPT seems to offer a range of benefits in academic education while also raising concerns. Relevant literature encompasses issues of plagiarism and academic dishonesty, as well as pedagogy and educational affordances; yet, no real-life implementation of ChatGPT in the educational process has been reported to our knowledge so far.

OBJECTIVE

This mixed methods study aimed to evaluate the implementation of ChatGPT in the educational process, both quantitatively and qualitatively.

METHODS

In March 2023, a total of 77 second-year dental students of the European University Cyprus were divided into 2 groups and asked to compose a learning assignment on "Radiation Biology and Radiation Protection in the Dental Office," working collaboratively in small subgroups, as part of the educational semester program of the Dentomaxillofacial Radiology module. Careful planning ensured a seamless integration of ChatGPT, addressing potential challenges. One group searched the internet for scientific resources to perform the task and the other group used ChatGPT for this purpose. Both groups developed a PowerPoint (Microsoft Corp) presentation based on their research and presented it in class. The ChatGPT group students additionally registered all interactions with the language model during the prompting process and evaluated the final outcome; they also answered an open-ended evaluation questionnaire, including questions on their learning experience. Finally, all students undertook a knowledge examination on the topic, and the grades between the 2 groups were compared statistically, whereas the free-text comments of the questionnaires were thematically analyzed.

RESULTS

Out of the 77 students, 39 were assigned to the ChatGPT group and 38 to the literature research group. Seventy students undertook the multiple choice question knowledge examination, and examination grades ranged from 5 to 10 on the 0-10 grading scale. The Mann-Whitney U test showed that students of the ChatGPT group performed significantly better (P=.045) than students of the literature research group. The evaluation questionnaires revealed the benefits (human-like interface, immediate response, and wide knowledge base), the limitations (need for rephrasing the prompts to get a relevant answer, general content, false citations, and incapability to provide images or videos), and the prospects (in education, clinical practice, continuing education, and research) of ChatGPT.

CONCLUSIONS

Students using ChatGPT for their learning assignments performed significantly better in the knowledge examination than their fellow students who used the literature research methodology. Students adapted quickly to the technological environment of the language model, recognized its opportunities and limitations, and used it creatively and efficiently. Implications for practice: the study underscores the adaptability of students to technological innovations including ChatGPT and its potential to enhance educational outcomes. Educators should consider integrating ChatGPT into curriculum design; awareness programs are warranted to educate both students and educators about the limitations of ChatGPT, encouraging critical engagement and responsible use.

Automatization of CT Annotation: Combining AI Efficiency with Expert Precision

The integration of artificial intelligence (AI), particularly through machine learning (ML) and deep learning (DL) algorithms, marks a transformative progression in medical imaging diagnostics. This technical note elucidates a novel methodology for semantic segmentation of the vertebral column in CT scans, exemplified by a dataset of 250 patients from Riga East Clinical University Hospital. Our approach centers on the accurate identification and labeling of individual vertebrae, ranging from C1 to the sacrum-coccyx complex. Patient selection was meticulously conducted, ensuring demographic balance in age and sex, and excluding scans with significant vertebral abnormalities to reduce confounding variables. This strategic selection bolstered the representativeness of our sample, thereby enhancing the external validity of our findings. Our workflow streamlined the segmentation process by eliminating the need for volume stitching, aligning seamlessly with the methodology we present. By leveraging AI, we have introduced a semi-automated annotation system that enables initial data labeling even by individuals without medical expertise. This phase is complemented by thorough manual validation against established anatomical standards, significantly reducing the time traditionally required for segmentation. This dual approach not only conserves resources but also expedites project timelines. While this method significantly advances radiological data annotation, it is not devoid of challenges, such as the necessity for manual validation by anatomically skilled personnel and reliance on specialized GPU hardware. Nonetheless, our methodology represents a substantial leap forward in medical data semantic segmentation, highlighting the potential of AI-driven approaches to revolutionize clinical and research practices in radiology.

Enhancing Anatomy Education Throu€gh Flipped Classroom and Adaptive Learning A Pilot Project on Liver Anatomy

OBJECTIVES

Anatomy education plays a critical role in medical practice, and the level of anatomical knowledge among students and physicians significantly impacts patient care. This article presents a pilot project aimed at exploring the effectiveness of the Area9's Rhapsode platform, an intelligent tutoring system that uses artificial intelligence (AI) to personalize learning and collect data on mastery acquisition.

METHODS

The study focused on liver anatomy (microscopic and macroscopic anatomy, embryology, clinical anatomy) and employed a flipped classroom approach, incorporating adaptive learning modules and an interactive in-class session. A total of 123 first-year medicine students (55 M/68F) participated to the study. Content and resources of the module were adaptable to various digital devices. Statistics were compiled based, on the one hand, on the measurement of mastery for every single learning objective provided automatically by the platform via the student interactions with the system probes (questions); on the other hand, metacognition data were worked out by crossing mastery data with the self-awareness declared in every question and learning resource by each learner.

RESULTS AND CONCLUSIONS

At the outset of the study, students displayed a 18.11% level of conscious incompetence and a 19.43% level of unconscious incompetence. Additionally, 50.86% of students demonstrated conscious competence. By the conclusion of the learning module, the level of conscious incompetence had decreased to 1.87%, and 98.73% of students exhibited conscious mastery of the materials. The results demonstrated improved learning quality, positive repurposing of study time, enhanced metacognitive awareness among students, with most students demonstrating conscious mastery of the materials and a clear understanding of their level of competence. This approach, by providing valuable insights into the potential of AI-based adaptive learning systems in anatomy education, could address the challenges posed by limited teaching hours, shortage of anatomist, and the need for individualized instruction.

The Significance of Artificial Intelligence Platforms in Anatomy Education: An Experience With ChatGPT and Google Bard

This study evaluated the use of two large language models (LLMs), ChatGPT and Google Bard, in anatomy education. The models were asked to answer questions, generate multiple-choice questions, and write articles on anatomy topics. The results showed that the models were able to perform these tasks with varying degrees of accuracy. ChatGPT and Google Bard did not differ significantly in terms of answering questions. Both models were able to generate multiple-choice questions with a high degree of accuracy. However, the performance of the models in article writing was not yet at a sufficient level. The study also found that the use of LLMs in medical education requires caution. This is because LLMs are still under development and they can sometimes generate inaccurate or misleading information. It is important to carefully evaluate the output of LLMs before using them in educational settings. Overall, the study found that LLMs have the potential to be valuable tools for anatomy education. However, more research is needed to improve the accuracy of the models and to better understand how they can be used effectively in educational settings.

Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide No. 158

Health Professions Education (HPE) has benefitted from the advances in Artificial Intelligence (AI) and is set to benefit more in the future. Just as any technological advance opens discussions about ethics, so the implications of AI for HPE ethics need to be identified, anticipated, and accommodated so that HPE can utilise AI without compromising crucial ethical principles. Rather than focussing on AI technology, this Guide focuses on the ethical issues likely to face HPE teachers and administrators as they encounter and use AI systems in their teaching environment. While many of the ethical principles may be familiar to readers in other contexts, they will be viewed in light of AI, and some unfamiliar issues will be introduced. They include data gathering, anonymity, privacy, consent, data ownership, security, bias, transparency, responsibility, autonomy, and beneficence. In the Guide, each topic explains the concept and its importance and gives some indication of how to cope with its complexities. Ideas are drawn from personal experience and the relevant literature. In most topics, further reading is suggested so that readers may further explore the concepts at their leisure. The aim is for HPE teachers and decision-makers at all levels to be alert to these issues and to take proactive action to be prepared to deal with the ethical problems and opportunities that AI usage presents to HPE.

Teaching, Learning and Assessing Anatomy with Artificial Intelligence: The Road to a Better Future

Anatomy is taught in the early years of an undergraduate medical curriculum. The subject is volatile and of voluminous content, given the complex nature of the human body. Students frequently face learning constraints in these fledgling years of medical education, often resulting in a spiraling dwindling academic performance. Hence, there have been continued efforts directed at developing new curricula and incorporating new methods of teaching, learning and assessment that are aimed at logical learning and long-term retention of anatomical knowledge, which is a mainstay of all medical practice. In recent years, artificial intelligence (AI) has gained in popularity. AI uses machine learning models to store, compute, analyze and even augment huge amounts of data to be retrieved when needed, while simultaneously the machine itself can be programmed for deep learning, improving its own efficiency through complex neural networks. There are numerous specific benefits to incorporating AI in education, which include in-depth learning, storage of large electronic data, teaching from remote locations, engagement of fewer personnel in teaching, quick feedback from responders, innovative assessment methods and user-friendly alternatives. AI has long been a part of medical diagnostics and treatment planning. Extensive literature is available on uses of AI in clinical settings, e.g., in Radiology, but to the best of our knowledge there is a paucity of published data on AI used for teaching, learning and assessment in anatomy. In the present review, we highlight recent novel and advanced AI techniques such as Artificial Neural Networks (ANN), or more complex Convoluted Neural Networks (CNN) and Bayesian U-Net, which are used for teaching anatomy. We also address the main advantages and limitations of the use of AI in medical education and lessons learnt from AI application during the COVID-19 pandemic. In the future, studies with AI in anatomy education could be advantageous for both students to develop professional expertise and for instructors to develop improved teaching methods for this vast and complex subject, especially with the increasing paucity of cadavers in many medical schools. We also suggest some novel examples of how AI could be incorporated to deliver augmented reality experiences, especially with reference to complex regions in the human body, such as neural pathways in the brain, complex developmental processes in the embryo or in complicated miniature regions such as the middle and inner ear. AI can change the face of assessment techniques and broaden their dimensions to suit individual learners.