Monday 27 November 2023

Basics of AI in Health Professions Education: AI for All - APMEC 2024 Pre-Conference Workshop

Basics of AI in Health Professions Education: AI for All - APMEC 2024 Pre-Conference Workshop (W1A5)

Poh Sun Goh, Elisabeth Schlegel, Mildred Lopez

17 January 2024, from 8.00AM- 12.00PM (GMT+5.30)

UCFM Tower, Faculty of Medicine, Colombo









Basics of AI in Health Professions Education: AI for All 

Workshop Description
This workshop will cover the basic ideas, principles and practices of AI in Health Professions
Education (HPE). There will be short faculty presentations, and opportunities for both interactive
discussions, demonstrations and exploration using AI in HPE. We will start by exploring basic ideas and principles at a working level, to build a foundation for further discussion and exploration. We will then explore how and where AI is embedded in how we practice and the tools and platforms we use, including when we do online search, take advantage of autocomplete and chatbot options, AI tools and extensions within work productivity software, and standalone AI platforms and mobile Apps. The aim of this workshop is to build AI literacy, practise common applications such as developing NBME-style questions, structured clinical case based teaching outlines, AI facilitated short teaching video production, or even write fun class summary poems to elevate the mood on a difficult subject. Further goals include developing a deeper appreciation of the potential and pitfalls of using AI, exploring pedagogy, policies as well as research and scholarship avenues using AI in HPE. At the end of this workshop, participants will have a foundation to actively participate in discussions using AI in HPE, as well as foundational knowledge to actively explore and use AI in HPE.

Background Reading/Curated Online Resources

Workshop Objectives
-To review the basic ideas, principles and practices of AI in Health Professions Education (HPE).
-To build AI literacy, practise common applications
-To build a a foundation to actively participate in discussions using AI in HPE, as well as
foundational knowledge to actively explore and use AI in HPE.

Who Should Attend
Health professions educators who are interested in reviewing the basic ideas, principles and
practices of AI in Health Professions Education (HPE); building AI literacy, practising common
applications, building a foundation to actively participate in discussions using AI in HPE, as well as foundational knowledge to actively explore and use AI in HPE.

https://aiinhpe.blogspot.com/2023/11/fundamentals-of-ai-what-ai-is-what-it.html

I will demonstrate how to work with AI driven search engines and with AI tools (like Chat GPT 3.5 and Bard) as a partner in developing and delivering content for this workshop - https://aiinhpe.blogspot.com/2023/11/fundamentals-of-ai-what-ai-is-what-it.html


--

Lopez, M., Goh, PS. (2024). Catering for the Needs of Diverse Patient Populations: Using ChatGPT to Design Case-Based Learning Scenarios. Med.Sci.Educ. Published online 13 January 2024.  https://doi.org/10.1007/s40670-024-01975-4

Lopez, M. (2024). What AI prompt is the best for…? That is the question. TAPS, 9(1), 64-65. Published online 2 January 2024. https://doi.org/10.29060/TAPS.2024-9-1/LE3109

--



























--

Role of AI in Health Professions Education - https://aiinhpe.blogspot.com/2023/06/role-of-ai-in-health-professions.html


“Artificial intelligence and machine learning, and instructors in their role as trainers and coaches, give feedback and provide dynamic, personalised customisation of learning content and training experiences.”

Goh, PS. (2020). Medical Educator Roles of the Future. Med.Sci.Educ. 30 (Suppl 1), 5–7. https://doi.org/10.1007/s40670-020-01086-w


AI Won’t Replace Humans — But Humans With AI Will Replace Humans Without AI

Harvard Business Review. August 4, 2023

https://hbr.org/2023/08/ai-wont-replace-humans-but-humans-with-ai-will-replace-humans-without-ai


--

What AI is, what it can do, what is available

- including idea that we are already using AI whenever we do an online search, use common software and mobile Apps, and interact with our mobile and computing devices

What is available, how to use AI, examples

- how can we use embedded AI intentionally?

- how can we best blend use of technology, including AI, with learning science, instructional design and sound pedagogy?

Can Chat GPT and Bard provide references for its answers?

"explaining and justifying answers with evidence and literature as indicator of learning"

--

"What is Learning?

How can we promote, encourage and support deep learning rather than superficial surface learning?

How can we, as educators, instructors, guides and coaches facilitate the learning process?

How can we best use AI to support, and facilitate learning? For example by requiring learners to demonstrate understanding, by explaining, justifying and supporting their answers; including providing evidence, literature, theory and logical arguments and explanations."

Poh-Sun Goh, 28 November 2023 @ 0923am, Singapore Time

---

Role of AI in Crafting Effective Case Studies

Use Examples: Prompts and Responses

https://aiinhpe.blogspot.com/2023/11/fundamentals-of-ai-what-ai-is-what-it.html

ChatGPT vs Bard

"One of the key differences between Google Bard and ChatGPT is their access to the internet. Google Bard has real-time access to the internet, which means that it can access the latest information and keep its responses up-to-date. ChatGPT, on the other hand, does not have real-time access to the internet." - https://www.simform.com/blog/google-bard-vs-chatgpt/


Using Chat GPT 3.5, and three prompts, 

- Develop clinical case to manage breathless patient

- With suspected COVID-19 (follow up prompt)

- Develop clinical skills training simulation to manage patient with suspected pneumothorax

the following response from Chat GPT 3.5 was generated (30 December 2023) - https://chat.openai.com/share/7a9e9302-3916-4979-bcfe-fafc6d3a8237


Using Bard, and the prompt

- Case Study: Managing Breathlessness in a Patient - For Training Medical Students

the following response from Bard was generated (30 December 2023) - 

https://g.co/bard/share/2387f7ae53dc


Using Bard, and the prompt

- Develop clinical skills training simulation to manage patient with suspected pneumothorax

the following response from Bard was generated (30 December 2023) - 

https://g.co/bard/share/3fdefbcb772e



Selected transcript from TED talk above: Machine Learning, AI, and the Future of Education | Marc Natanagara | TEDxBrookdaleCommunityCollege - https://www.youtube.com/watch?v=gjDPtzJQnyM&t=2s (accessed 31 December 2023)

let's design more lessons and ask more
6:37
questions with these five
6:39
characteristics
6:40
>> first emphasize live Hands-On
6:43
experiences then ask what did you notice
6:45
when this happened how might your
6:47
actions have affected the outcome how
6:49
did your team collaborate on this task
6:51
problem solving through Discovery
6:53
exploration and reflection is part of
6:56
what we call Active Learning which we
6:58
know to be more effective than old
6:59
school models like lectures worksheets
7:01
and book reports
7:04
>> second ask questions about meaning
7:06
encourage students to identify their
7:08
beliefs see the bigger picture
7:10
generalize Concepts from one area to the
7:12
other make learning personal by asking
7:15
what does this information mean to you
7:16
what might it mean to our community or
7:18
another community
7:20
why is this relevant to anyone
7:22
and when children ask us why do I need
7:24
to learn this adults should have a good
7:26
answer
7:28
>> third ask students to make connections
7:31
to the real world to integrate the
7:33
pieces of what they know studies show
7:35
students are more engaged when they
7:36
understand context for example how does
7:39
this relate to last week's lesson or to
7:41
what you're learning in social studies
7:42
or art class
7:44
how do your personal local and Global
7:46
perspectives compare
7:48
how might this give you Insight on the
7:50
past present and future
7:52
>> fourth ask students about their feelings
7:55
imagine that awareness empathy putting
7:58
yourself in someone else's shoes and
8:00
playing nice with others or what we call
8:02
emotional intelligence
8:04
as much as we're putting AI into devices
8:06
that are always listening maybe even
8:08
watching AI still can't read the room
8:11
a one-year-old child even your cat or
8:13
dog can sense your mood better than any
8:16
computer
8:17
now we don't normally ask students to
8:19
flex these four muscles so things may
8:21
not go smoothly at first but let's keep
8:23
in mind
8:24
struggle is a necessary prerequisite for
8:26
learning
8:28
>> finally let's have students direct their
8:30
Knowledge and Skills towards novel
8:32
applications
8:33
ask them to apply their current
8:35
understandings to a new situation or
8:37
create a new way of looking at an old
8:39
problem
8:40
only humans can think divergently like
8:42
that outside the box computers are the
8:45
Box
8:46
artificial intelligence can only follow
8:48
the rules they've been given
8:51
AI can't experience generalize reason
8:54
reflect think abstractly or understand
8:57
relevance and it can't access a
8:59
student's perceptions interpretations
9:01
and feelings
9:03
a good education should do all of these
9:05
things
9:08
this is how we future proof our
9:09
classrooms make AI a co-teacher work
9:12
with the technology strengths and
9:14
weaknesses but most importantly let's
9:16
value human intelligence as more than
9:18
just computer-like processing get
9:21
students to use parts of their brains
9:22
computers don't have ask questions AI
9:25
can answer device problems chat Bots
9:27
can't solve we can do that by
9:30
challenging students with authentic
9:32
experiences that tap into the incredible
9:34
capacity diversity and creativity of
9:37
their human Minds




Using Microsoft Co-pilot AI app and prompt:

Develop clinical skills training simulation to manage patient with suspected pneumothorax

Response below:

To develop a clinical skills training simulation to manage a patient with suspected pneumothorax, you can consider the following steps:
1. Identify the learning objectives: Determine the key concepts and skills that you want the simulation to teach. For example, you may want to focus on identifying the signs and symptoms of pneumothorax, performing a chest examination, and interpreting chest X-rays.
2. Design the simulation: Create a scenario that simulates a patient with suspected pneumothorax. This could include designing a manikin or using a virtual patient simulator. Ensure that the scenario is realistic and includes all the necessary equipment and supplies.
3. Develop the curriculum: Create a curriculum that outlines the learning objectives, simulation scenario, and assessment tools. This should include a detailed description of the simulation scenario, the expected outcomes, and the assessment criteria.
4. Conduct the simulation: Run the simulation with the participants. Ensure that the simulation is conducted in a safe and controlled environment. Provide feedback to the participants and encourage them to reflect on their performance.
5. Evaluate the simulation: Evaluate the effectiveness of the simulation in achieving the learning objectives. This could include assessing the participants’ knowledge, skills, and confidence before and after the simulation.
For more information on nursing care management for patients with pneumothorax, you can refer to the following resource 1:
* Pneumothorax Nursing Care and Management: Study Guide 1
I hope this helps! Let me know if you have any other question



"One of the key takeaways from our workshop is to recommend our participants build experience on one core platform, app or AI tool e.g. chat GPT or Bard; whilst also being open to newer options." - Poh-Sun
(31 December 2023)

No comments:

Post a Comment

Note: only a member of this blog may post a comment.