A scoping review of the literature, its impact and challenges in healthcare, and a personal experience of its application in practice, teaching, and research.
Ahmedabad Call Girls CG Road đ9907093804 Short 1500 đ Night 6000
Â
Generative AI in Health Care a scoping review and a persoanl experience.
1. Vaikunthan Rajaratnam
Senior Consultant Hand Surgeon,
KTPH, Singapore,
Adjunct Professor & UNESCO Chair Partner,
Asia Pacific University of Technology and
Innovation, Malaysia.
Next-Gen Healthcare: Transforming
Practice and Processes with
Generative AI
Key Findings of a Review and a
Personal Experience
2. Disclaimer
â I am not an AI expert, nor do I possess coding knowledge specific to the
underlying mechanisms of AI models;
â My expertise lies in utilising these models, such as ChatGPT, based on my
extensive experience as a user in healthcare, medical education, and
related research, rather than their technical development or underlying
algorithms.
â This workshop is intended solely for educational and informational purposes in AI
and healthcare.
â The views expressed herein are my own, borne from extensive experience in
surgery, medical education, and instructional design, and do not necessarily reflect
those of any associated institutions.
â While I endeavour to provide accurate and up-to-date information, no guarantee is
given regarding its applicability.
â Participants acknowledge and assume responsibility for using the information
provided by engaging in this workshop.
Vaikunthan Rajaratnam
5. ⢠Tools for Effective Academic Courses and Holistic
Teaching
⢠MOE Malaysia
AI TEACH
⢠For students in middle school
⢠Indigenous School, Malaysia
AI LEARN
⢠Gerontological Optimization through Learning and
Digital Assistance
AI GOLD
⢠Learning Designs
⢠APU, Malaysia, NHG, Singapore
AI LD
⢠Health Professional
⢠Perdana University , Malaysia, BDSSH, Bangladesh
⢠NHG, Singapore, Sengkang, Singapore
AI HP
⢠Research
⢠Perdana University, Malaysia, Sengkang , Singapore
⢠University of Eswatini (Africa)
AI RE
â˘Academic Writing
⢠APU, Perdana University, Malaysia
⢠University of Eswatini (Africa)
AI AW
⢠Leveraging Efficiency in Administrative
Proficiency
⢠MOE, Dubai
AI LEAP
14. ⢠Ambient clinical documentation as a
transformative technology
The Future is
Now:
⢠Artificial intelligence seamlessly captures
and transcribes patient conversations
⢠Generating medical notes
⢠Reducing doctors' administrative workload.
AI-Powered
Solution:
⢠Burden of paperwork and documentation
⢠Major cause of physician burnout;
⢠Ambient clinical documentation offers a
potential solution.
Tackling
Burnout:
⢠Microsoft Nuance DAX Copilot
⢠Abridge, and Suki
Widespread
Adoption:
⢠The integration of ambient clinical
documentation with EHR systems (EPIC)
⢠Expansion into other languages and
medical specialties
Looking
Ahead:
15. AI Reshaping
Healthcare:
Clinical
documentation
Electronic health
records (EHRs).
DAX Copilot:
AI-powered tool by
Nuance and
Microsoft
Automates clinical
note-taking
Reducing physician
workload
Improving patient
interactions.
EPIC's AI
Features:
Summarize
encounters
Highlight
important
information
Predict risks
Optimizing
workflows
Decision-making.
Importance
of Evaluation:
Continuous
research and
evaluation
Ensure the safe,
ethical, and
effective use of AI
in healthcare.
16. Predictive
medicine
Early Disease Detection
Personalized Treatment Plans
Chronic Disease Management
Genomic Medicine and Genetic Risk Prediction
Drug Response Prediction
Epidemic Outbreak Prediction
Hospital Readmission Prediction
19. Challenges
Golhar, S. P., & Kekapure, S. S. (2022). Artificial Intelligence in HealthcareâA Review. International Journal of Scientific
Research in Science and Technology, 9(4), 381â387. https://doi.org/10.32628/IJSRST229454
20. Governance
Model for AI
S. Reddy, S. Allan, S. Coghlan, and P. Cooper, âA governance model for the application of AI in health careâ, J. Am. Med. Inform. Assoc., vol. 27, no.
3, pp. 491â497, Mar. 2020, doi: 10.1093/jamia/ocz192
Rahman, N., Thamotharampillai, T., & Rajaratnam, V. (2023). Ethics, guidelines, and policy for technology in healthcare. In
Medical Equipment Engineering: Design, Manufacture and Applications (pp. 119â147). IET Digital Library.
https://doi.org/10.1049/PBHE054E_ch9
21. Scoping Review
⢠âGenerative AIâ & âhealthcareâ
Search terms
⢠SCISPACE (typeset.io)
Database
⢠92 Papers selected
Title and Abstract
Screening
⢠Main Findings and Implications
Data extraction
⢠Analysed to NINE theme
Text data
Synthesised
22. 59.AI revolution in healthcare and medicine and the (re-)emergence of inequalities and
disadvantages for ageing population
60.AI in healthcare: A narrative review
61.Generative Adversarial Networks Enhanced Pre-training for Insufficient Electronic Health
Records Modeling
62.A Methodology for A Scalable, Collaborative, And Resource-Efficient Platform, MERLIN, to
Facilitate Healthcare AI Research
63.The Emerging Role of Artificial Intelligence in Healthcare.
64.Synthetic Data Generator for Adaptive Interventions in Global Health
65.Embedded AI-Based Digi-Healthcare
66.AI- and IoT-Based Architecture in Healthcare 92 PAPERS
67. Artificial Intelligence in Healthcare
68.Generating synthetic mixed-type longitudinal electronic health records for artificial
intelligent applications
69.Survey of Explainable AI Techniques in Healthcare
70.Artificial Intelligence (AI) in Medicine and Modern Healthcare Systems
71.Development of new ai in healthcare
72.Ai Consulting Healthcare Chatbot System Using Pattern Matching
73.Software as a Medical Device: Regulating AI in Healthcare via Responsible AI
74.Introducing AI General Practitioners to Improve Healthcare Services
75.Healthcare Applications Using Biomedical AI System
76.The Advent of Generative Language Models in Medical Education
77.Realizing AI in Healthcare: Challenges Appearing in the Wild
23. No. Paper Insight Main Findings
1.
The Disruptive Impacts of
Next Generation Generative
Artificial Intelligence
Highlights the transformative
potential of generative AI in
healthcare, focusing on
diagnostics and personalized
medicine.
Demonstrates how
generative AI can significantly
enhance diagnostic accuracy
and enable more
personalized treatment plans.
2.
Integrating Generative AI in
Healthcare Organisations:
Opportunities, Challenges,
and Deployment Strategies
(Preprint)
Discusses the integration
challenges and strategic
deployment of generative AI
in healthcare settings.
Outlines practical strategies
for overcoming organizational
and technical barriers to
effectively integrate
generative AI in healthcare.
3.
The Rise of Generative
Artificial Intelligence in
Healthcare
Examines the emerging role
of generative AI in
healthcare, particularly in
enhancing patient care and
treatment options.
Identifies key areas where
generative AI is set to
transform healthcare,
including drug discovery,
predictive analytics, and
patient engagement.
4.
The Rise of Generative
Artificial Intelligence in
Healthcare
Emphasizes the role of
generative AI in advancing
healthcare technologies and
its impact on future medical
practices.
Projects future advancements
in AI-driven predictive
models, personalized
medicine, and automated
clinical workflows.
5.
Artificial intelligence in
healthcare: Complementing,
not replacing, doctors and
healthcare providers
Focuses on how generative AI
complements healthcare
professionals, enhancing
rather than replacing human
expertise.
Highlights the supportive role
of AI in decision-making
processes, patient
monitoring, and enhancing
healthcare delivery without
replacing human providers.
24. Theme Implication Summary
AI-Enhanced Diagnosis and Treatment
Improves diagnostic accuracy, personalizes
treatment plans, and enhances clinical decision-
making.
Synthetic Data and Privacy
Mitigates privacy concerns with synthetic data,
revolutionizing medical training and research.
AI and Healthcare Efficiency
Increases healthcare efficiency, streamlines
management, and reduces medical professionals'
burden.
Human-AI Collaboration
Assists healthcare professionals, improves
healthcare accessibility and educational initiatives.
Generative AI in Medical Education and Research
Impacts medical imaging, drug development, and
healthcare interventions, enhancing nursing
education.
Challenges and Ethical Considerations
Addresses ethical, legal, and social implications,
emphasizing responsible AI utilization.
AI in Healthcare Management and Operations
Improves healthcare management, diagnostics,
patient care, and integrates AI with IoT for enhanced
care.
Policy, Regulatory, and Governance Frameworks
Necessitates comprehensive governance
frameworks, regulatory considerations, and policy
implications.
Innovation and Future Directions
Drives innovation, development of new AI models,
and explores AI's potential to transform healthcare.
25. Impact on
Healthcare
Employment
Disruption of job
markets
Job automation
New job
opportunities - AI
management and
ethical oversight.
Importance of
professional
engagement
Professionalsâ
Insights
Continuous
learning
Develop ethical
AI guidelines
Proactive
adaptation
26. Synthetic Data Generation
Generative Adversarial Networks (GANs)
Enhancing
Patient
Outcomes
⢠Extensive and
diverse
training
datasets
⢠Train AI
systems
without the
risk of
exposing
sensitive
information.
⢠Assist in
diagnosis and
treatment
planning
Balancing Data
Access with
Privacy:
⢠Expand data
access for
research and
development
⢠Maintaining
individual
privacy
⢠Contains no
real patient
data.
Clinical Trials
and Research:
⢠Simulate
controlled
environments
for clinical
trials
⢠Without the
need for real
patient
involvement
⢠Speeding up
research
⢠Maintaining
ethical
standards.
Training and
Education:
⢠Synthetic
scenarios for
training
purposes
⢠Larger
portfolio of
scenarios
⢠No
confidentialit
y concerns.
Regulatory
Compliance:
⢠Adhering to
PDPA
regulations
⢠Avoids the
use of actual
patient
27. Ethical Use
and Education
Guidelines for Ethical use
Standards for patient rights
Transparency / Accountability
Training programs for
healthcare professionals.
Multidisciplinary collaborative
research.
Stakeholder engagement
Dynamic ethical reviews
Enhance NOT replace human
expertise.
Prioritize patient autonomy
Institutional Ethical
responsibility
28. Visual Explanations and Trust
⢠foster trust and accelerate clinical
adoption.
Transparent AI
models
⢠aids healthcare professionals in
accurate diagnostics.
Interpretability of AI
⢠enhances patient and provider
confidence in AI tools.
Clear AI decision-
making
⢠ensures better risk management.
Understanding AI's
capabilities and limits
⢠contributes to continuous learning in
the healthcare sector.
Informed use of AI
30. Revolutionizing Research and Training
Synthetic data mimics
accurate patient data
⢠Enabling safe AI training
⢠Medical research
⢠Diverse medical
scenarios
⢠Rare disease research
⢠Accelerates healthcare
innovation
⢠No privacy risks.
Health Professional
Education
⢠Realistic simulations
⢠Personalised Learning
⢠Real time feedback
⢠Authentic Assessment
31. Overcoming Disruptive Impacts
Transformation
of Healthcare
Delivery:
New ways of
Delivery
Technology
empowered
Shift in Skill
Demands:
Shift in the job
skills
Reskilling and
upskilling
Capacity
building
Innovation in
Service
Offerings:
On Demand
Anytime
Anywhere
Value for
Money
Nurses as AI
Integration
Leaders:
Front lines of
care - AI into
clinical practice
Effectively and
empathetic
Patient
advocates
Focus on
patient-
centered care.
32. Data Privacy and Ethics
Data Privacy:
⢠PDPA
Compliances
⢠HIPAA
Compliances.
Ethical
Considerations:
⢠Context-
specific Ethical
Framework
⢠Consent,
transparency,
and
accountability.
Compliance with
Regulations:
⢠Evolving
regulatory
frameworks
⢠Region/culture
and value
specific
Synthetic Data
as a Solution:
⢠Train AI
without
compromising
individual
privacy
Maintaining
Trust:
⢠Leveraging
synthetic data
⢠Transparency
⢠Minimizing the
risk of data
breaches and
unauthorized
access.
33. Reliability and Authorship Concerns
â˘Accuracy
â˘Relevance
â˘Validity
Content
Accuracy:
â˘Citation
â˘Evidence based Validation
Source
Verification:
â˘Plagiarism
â˘Clear guidelines on use and disclosures
Authorship
Clarity:
â˘Use and Cite
â˘Copy Right vs Copy Left
Ethical Use:
â˘Authors accountability
â˘Rigorous review by domain experts
Oversight and
Review:
34. Implementation Challenges
⢠EPIC
⢠Complex and resource-intensive.
Integration with
Existing Systems:
⢠High-quality, comprehensive datasets
Data Quality and
Availability:
⢠Use case
⢠Government support
User Acceptance
and Trust:
⢠Legislation
⢠Stakeholder engagement
Ethical and Legal
Concerns:
⢠Training healthcare professionals
⢠Educating Public
Training and
Education:
44. References
⢠Aryan Jadon & Shashank Kumar. (2023). Leveraging Generative AI Models for Synthetic Data Generation
in Healthcare: Balancing Research and Privacy. arXiv.Org, abs/2305.05247.
https://doi.org/10.48550/arXiv.2305.05247
⢠Integrating Generative AI in Healthcare Organisations: Opportunities, Challenges, and Deployment
Strategies (Preprint). (2023). https://doi.org/10.2196/preprints.50082
⢠JosĂŠ DarĂo MartĂnez-Ezquerro. (2023). AI healthcare applications beyond ChatGPT.
https://doi.org/10.31219/osf.io/mez2a
⢠Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and
Privacy. (2023). https://doi.org/10.48550/arxiv.2305.05247
⢠Mohammadali Mohajel Shoja, J M Monica van de Ridder, & Vijay Rajput. (2023). The Emerging Role of
Generative Artificial Intelligence in Medical Education, Research, and Practice. Cureus.
https://doi.org/10.7759/cureus.40883
⢠Murat Kuzlu, Zhenxin Xiao, Salih Sarp, F. Ozgur Catak, Necip Gurler, & Ozgur Guler. (2023). The Rise of
Generative Artificial Intelligence in Healthcare. 1â4. https://doi.org/10.1109/MECO58584.2023.10155107
⢠Oran Lang, Ilana Traynis, Heather Cole-Lewis, Courtney R. Lyles, Charles Lau, Christopher Semturs, Dale R.
Webster, Greg S. Corrado, Avinatan Hassidim, Y. Matias, Yun Liu, Naama Hammel, & Boris Babenko.
(2023). Using generative AI to investigate medical imagery models and datasets. arXiv.Org,
abs/2306.00985. https://doi.org/10.48550/arXiv.2306.00985
⢠The Disruptive Impacts of Next Generation Generative Artificial Intelligence. (2023). Cin-Computers
Informatics Nursing, 41, 479â481. https://doi.org/10.1097/CIN.0000000000001044
⢠The Rise of Generative Artificial Intelligence in Healthcare. (2023).
https://doi.org/10.1109/meco58584.2023.10155107
⢠Using generative AI to investigate medical imagery models and datasets. (2023).
https://doi.org/10.48550/arxiv.2306.00985