‹ Back

Generative AI Transforming Medical Education

 

ELHS NEWSLETTER 2023-10-1

Paving the Way for Global Health Equity with GenAI, ML, and LHS (Learning Health Systems)

| Subscribe | All Issues |

 

MAIN TOPIC:

GENERATIVE AI IN MEDICAL EDUCATION AND TRAINING

• The Stanford University AI+Education Summit showcased research in AI and education.

• PCORI and AHRQ are investing $50M to create LHS Training and Research Centers.

• The National Academy of Medicine has called for action: Health Professional Education must incorporate AI training to prepare the workforce.

• AI is a force behind the evolution of medical education in recent years.

 ~

 

 

(Source: Stanford University)

 

From Page Mill

^{Published papers, recent news, and significant events in a coherent narrative for the main topic.} 

 

AI+Education Summit: AI in the Service of Teaching and Learning 

[2023/2] “This summit showcased the latest research in AI & education from Stanford faculty and researchers, examined how AI can be used to advance human learning through new pedagogies, new modalities of assessment, new foundation models, and more. In doing so, the summit asked the question of how AI can transform teaching and learning in an ethical, equitable, and safe manner.” (Video recordings available on the event website)

 

PCORI and the Agency for Healthcare Research and Quality Collaborate to Train a New Generation of Learning Health System Scientists

[2023/2] “PCORI and the Agency for Healthcare Research and Quality (AHRQ) are pleased to invite qualified applicants to join a new initiative that will invest up to $50 million over five years to train a new class of learning health system scientists through the creation of Learning Health System Embedded Scientist Training and Research (LHS E-StaR) Centers. PCORI and AHRQ recognize the need for health systems to employ people with the right skills to explore the relevant evidence and produce insights that can be implemented to improve patient care.“

 

Lomis K, Jeffries P, Palatta A, et al. Artificial Intelligence for Health Professions Educators.

NAM Perspectives. 2021 Sep 8;2021:10.31478/202109a. doi: 10.31478/202109a.

[2021/9] This discussion paper from NAM is intended to complement the prior titled “Artificial Intelligence in Health Care: The Hope, the Hype, the Promise, the Peril” and serve as a call to action to the health professional education (HPE) community. Educators must act now to incorporate training in AI across health professions or risk creating a health workforce unprepared to leverage the promise of AI or navigate its potential perils.

~

 

 

 

In the Eyes of GPTs

^{GPTs are becoming an integral part of our society. AJ talks with GenAI to understand how machines view healthcare.}

 

 I'd like to chat about medical education and AI. First, I’d like to understand the history of changes in medical education. What have been the major development up to year 2023?

 

 Medical education has undergone significant changes over the years, evolving to meet the demands of a continually changing healthcare landscape. Here's a brief overview of some major changes in medical education up until 2023:

 

1. Flexner Report (1910):

This was a landmark in medical education. Commissioned by the Carnegie Foundation, Abraham Flexner assessed the state of medical education in the U.S. His report criticized many existing programs and called for standardized curriculum and admissions criteria. As a result, many medical schools were closed, and the ones that remained adopted the rigorous standards that Flexner proposed.

 

2. Problem-Based Learning (PBL) (1960s):

First introduced at McMaster University in Canada, PBL marked a shift away from traditional lecture-based teaching. Students work in small groups and use clinical scenarios to learn the basic sciences.

 

3. Expansion of Clinical Skills Education (1980s-1990s):

There was a growing emphasis on teaching communication skills, professionalism, and ethics, recognizing that being a good doctor is not just about scientific knowledge but also about understanding and interacting with patients.

 

4. Competency-Based Medical Education (2000s):

Rather than focusing on the duration of training, the emphasis shifted to the achievement of specific competencies. This approach is more learner-centered and ensures that graduates meet a defined standard of knowledge and skill.

 

5. Technology and Simulation (2000s-2020s):

The advent of advanced simulation techniques, from basic manikins to high-fidelity patient simulators and virtual reality, allowed students to practice clinical skills in a risk-free environment. This has become especially important for mastering procedural skills.

 

6. Digital & E-Learning Platforms (2010s-2020s):

With the growth of the internet and digital technology, there has been a surge in online courses, platforms, and resources for medical education, enabling more flexible and diverse learning opportunities.

 

7. Integration of AI and Machine Learning (2010s-2023):

AI began to play a role in diagnostics, treatment planning, and personalized medicine. As a result, medical education had to evolve to ensure that doctors could effectively work alongside these technologies. This includes understanding the basics of AI, its potential biases, and its limitations.

 

8. Emphasis on Wellness and Mental Health (2010s-2023):

With increasing recognition of burnout and mental health challenges in physicians, there's been a growing emphasis on teaching resilience, self-care, and wellness strategies within medical education.

 

9. Response to Global Health Crises (2020s):

The COVID-19 pandemic had a profound impact on medical education. Many medical schools rapidly transitioned to virtual learning, clinical rotations were disrupted, and there was an increased emphasis on public health, infectious diseases, and crisis management in curricula.

 

10. Decentralized and Community-Based Training (2010s-2023):

Recognizing the need to train doctors for various settings, including rural and underserved areas, many medical schools began to emphasize community-based training, where students spend time outside of large academic hospitals.

 

11. Interprofessional Education (2010s-2023):

With the understanding that healthcare is a team effort, there's been a growing emphasis on training medical students alongside other health professionals, like nurses, pharmacists, and social workers, to foster collaborative care.

 

This is a high-level overview, and many of these changes were interrelated and influenced by broader shifts in society, technology, and healthcare demands. Each of these points could be delved into more deeply for a comprehensive understanding of its implications and nuances.

 

  Thank you for the comprehensive list. It seems that AI is one of the driving forces behind these changes. Medical schools have been incorporating AI into medical education. What specific modes of AI integration or applications have been successful in enhancing student learning?

 

 Indeed, AI has become an influential force in reshaping various sectors, including medical education. Its integration into medical curricula and teaching methods has brought about innovative ways to enhance student learning. Here are some specific integration modes and usages of AI that have shown promise:

 

1. Personalized Learning Pathways:

AI can analyze individual students' learning habits, strengths, and areas needing improvement. Based on this analysis, it can customize content delivery, suggesting resources or modules tailored to each student's needs, ensuring more efficient and effective learning.

 

2. Virtual Patients & Simulations:

Advanced simulations powered by AI can recreate complex patient scenarios. These "virtual patients" can provide students with an opportunity to practice clinical reasoning, diagnosis, and even some procedures without risk to real patients.

 

3. Natural Language Processing (NLP) for Assessment:

AI systems using NLP can assess students' open-ended responses, case notes, or even verbal interactions, providing instant feedback on content, clarity, and communication skills.

 

4. Automated Tutoring Systems:

These AI-driven systems can guide students through complex topics, answer questions, and provide feedback in real-time. This is especially valuable for supplementing areas where there may be a shortage of human tutors or for after-hours learning.

 

5. Augmented Reality (AR) and Virtual Reality (VR) Enhancements:

AI can power AR and VR platforms to provide immersive learning experiences, from visualizing complex anatomical structures to simulating surgical procedures.

 

6. Image Analysis and Interpretation:

Particularly in specialties like radiology or pathology, AI tools can assist students in image interpretation, highlighting areas of interest, and providing differential diagnoses.

 

7. Predictive Analytics for Early Intervention:

By analyzing students' performance data, AI can identify those at risk of falling behind or failing. Early interventions can then be put in place to support these students.

 

8. Enhancing Problem-Based Learning (PBL):

AI can be integrated into PBL scenarios to provide real-time data, diagnostic suggestions, or even play the role of a virtual patient, making the learning experience more dynamic.

 

9. Continuous Curriculum Updates:

AI can scan the latest research publications and clinical guidelines to suggest updates or modifications to the curriculum, ensuring that students are always learning the most current and relevant information.

 

10. Chatbots for FAQ and Administrative Tasks:

AI-powered chatbots can assist students with frequently asked questions, administrative tasks, or even basic content queries, freeing up faculty time for more complex interactions.

 

11. Enhancing Clinical Decision Support Systems (CDSS):

While CDSS is more of a clinical tool, integrating it into medical education helps students understand the role of AI in real-world decision-making, the potential biases, and the importance of clinician oversight.

 

12. Virtual Anatomy and Dissection:

AI-driven platforms can simulate anatomy labs, allowing students to "dissect" and explore human anatomy virtually, which can be particularly useful when access to cadavers is limited.

 

While these modes of integration offer significant benefits, it's essential to approach them with a balanced perspective. Human interaction, mentorship, and hands-on clinical experience remain irreplaceable in medical education. AI tools should be viewed as complementary, enhancing traditional methods rather than replacing them.

 

~~~