Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Chua, National University of Singapore

Blending AI and IoT for Smarter Health
Matthew Chua, Assistant Professor, Biomedical Informatives - National University of Singapore

Apidays Singapore 2024: Connecting Customers, Business and Technology (April 17 & 18, 2024)

------

Check out our conferences at https://www.apidays.global/

Do you want to sponsor or talk at one of our conferences?
https://apidays.typeform.com/to/ILJeAaV8

Learn more on APIscene, the global media made by the community for the community:
https://www.apiscene.io

Explore the API ecosystem with the API Landscape:
https://apilandscape.apiscene.io/

1. Blending ai and iot for smarter health Asst Prof ( dr ) Matthew chua © Copyright National University of Singapore. All Rights Reserved 1

2. About Me Prof. (Dr). Matthew CHUA PhD (Engineering), NUS Assistant Professor of Biomedical Informatics, NUS School of Medicine Research Interests: Data Science, AI and Robotics. Over S$1 million grant as PI Professional Opera Singer © Copyright National University of Singapore. All Rights Reserved 2

3. Introduction IoT and AI are power tools of innovation in health Their transformative potential affects processes in hospitals, homes and more. Global IoMT (Internet of Medical Things) market was valued at $44.5 billion in 2018 and is expected to grow to $254.2 billion in 2026 (Health Tech Magazine, 2020) © Copyright National University of Singapore. All Rights Reserved 4

4. Introduction © Copyright National University of Singapore. All Rights Reserved 5 Hospital of the Future – limitless possibilities with technology and analytics! https://www.youtube.com/watch?v=iQ3zZ6FV-_Q https://www.theonlinecitizen.com/2016/10/21/moh-manpower-plan-for-ageing-population-in-need-of-30000-more-healthcare-workers-by-2020/moh-ward-of-the-future-data/

5. Examples © Copyright National University of Singapore. All Rights Reserved 6 Medical Imaging and Diagnosis Automatic Robotic Pharmacy Mobile Nurse Stations Telemedicine Electronic Health Records Systems Decision Support Systems

6. Consumer Health Informatics (CHI) Definition: Any electronic technology or application that is designed to interact directly with consumers and uses personal data to customize the services provided to the user to manage their health. © Copyright National University of Singapore. All Rights Reserved 7

7. CHI Applications © Copyright National University of Singapore. All Rights Reserved 8 https://www.mii.ucla.edu/research/areas/consumer-health-informatics/

8. Rise of Mobile Health (mHealth) m-Health is the practice of health and medicine using mobile devices Has manage advantages in terms of speed, accessibility, availability and portability Foreseeable that the future of health and healthcare services will be in mobile devices © Copyright National University of Singapore. All Rights Reserved 9 https://www.youtube.com/watch?v=jnEdaslPtEg

9. Mobile Phone Sensing Phone sensors: Camera: Vital signs detection, teledermatology Iris scanner: diagnostics Accelerometer: activity detection Microphone: Sleep Apnea, Stress monitoring GPS: Daily route/activity External sensors: Activity Monitoring BP and Heart Rate Monitoring Medication Adherence (Smart Pill Box) © Copyright National University of Singapore. All Rights Reserved 10

10. Wearables © Copyright National University of Singapore. All Rights Reserved 11 Security and battery life key issues in wearable User data can be harvested for health and business analytics to bring good outcomes Event triggers – heart attack during workout Needs to be fashionable and integrated with daily wearable

11. My NUS Research Projects © Copyright National University of Singapore. All Rights Reserved 12

12. m-Health Fine-motor Skills Rehabilitation for Stroke Problem Statements The first 6 months post-stroke is critical for stroke survivors to regain their motor skills Most patients cannot afford time or money for daily rehabilitation at centres Recovery of fine-motor skills of hands cannot yet be tracked and quantified in most stroke rehabilitation systems © Copyright National University of Singapore. All Rights Reserved 13 Funded by Supported by A Collaboration Between

13. Summary of System Development of a m-Health Hand Rehabilitation System for Stroke Patient Recovery Integration of Infrared-based camera tracking system, machine learning, gamification elements and virtual instructor-led training Captures every finger joint of the hand and the fine range of motion as data Fun, easy-to-use, and interactive training programmes Adherence to programme and recovery rate can be tracked and reported accurately System was unveiled at during the opening of the Stroke Support Station branch at Jurong Point in May 2019 © Copyright National University of Singapore. All Rights Reserved 14 https://www.youtube.com/watch?v=ogI6IRPEXFU

14. © Copyright National University of Singapore. All Rights Reserved 15 Portable and interactive hand rehab exercises

15. © Copyright National University of Singapore. All Rights Reserved 16 Gamification to motivate stroke survivor to perform more rehabilitation

16. © Copyright National University of Singapore. All Rights Reserved 17 AI and automation reduce the burden of therapist

17. Intelligent Gait-Assistive Device for Elderly with Walking Dysfunctionalities Features Intelligent sensing and learning Biofeedback through stimuli Benefits Free up healthcare work’s time and energy Empower patient and builds confidence Improves mobility More effective than current methods © Copyright National University of Singapore. All Rights Reserved 18 https://www.youtube.com/watch?v=ZbrFH2m0tgA&t=165s CNA Documentary in March 2018

18. Mind Typing Interface for LIS Patients Features Assistive Typing Platform for Locked-in Syndrome Patients Short Training Time due to Assisted ML Specially designed keyboard interface Hands-free typing using just pure brain power https://www.youtube.com/watch?v=e0-nev_pEQs © Copyright National University of Singapore. All Rights Reserved 19

19. Large-Scale Hospital Vitals Monitoring Problem Statement Nurses have to wake patients up every 2 to 4 hours to collect vitals Manpower intensive and redundant task Inaccuracies in entering of data into system Disturbance to patients Patient falls in various parts of the hospitals goes unnoticed (toilets, hallways, kopitiams ) © Copyright National University of Singapore. All Rights Reserved 20 A Collaboration With

20. Overview of System © Copyright National University of Singapore. All Rights Reserved 21 Features and Benefits: Smart disposable patient wrist tag Monitors vitals (heart rate, spO2, temperature), location and falls Readings updated every 10 minutes Sync and push notification to nurse station dashboard Benefits: Faster response to incidences Manpower savings Better quality of hospital stay

21. Integrative Cardiac Rehabilitation Employing Smartphone Technology ( i -CREST) Collaboration with Alice Lee Centre for Nursing Studies Features To develop a home-based cardiac rehabilitation system using IoT technologies Active tracking of vitals while patients perform exercises Education + Monitoring + Active Feedback Currently undergoing clinical trials at NUH Benefits Cost savings for patients and hospitals Faster discharge rate Better tracking of adherence Quantification of patient recovery © Copyright National University of Singapore. All Rights Reserved 22

22. Virtual reality training for assembly of hybrid medical devices Skill training in the medical device manufacturing industry is essential to optimize and expedite the efficiency level of new workers The system integrate Artificial Intelligence (AI), VR and gaming concepts Self-adaptive and autonomous Training to take place in a virtual workcell environment without the supervision of a physical trainer © Copyright National University of Singapore. All Rights Reserved 23 Ho, N., Wong, P. M., Chua, M., & Chui, C. K. (2018). Virtual reality training for assembly of hybrid medical devices.  Multimedia Tools and Applications ,  77 (23), 30651-30682.

23. Smart Health Station Features All-in-one platform to measure and predict health-related issues Image analysis for melanoma detection Stress detection from Heart Rate Variability (HRV) And more functionalities! Benefits To be stationed in the new ISS showcase room Free for staff to use if you suspect something is wrong with you © Copyright National University of Singapore. All Rights Reserved 24

24. Invitation to join me Interested in a collaboration in IoT/AI/Data Science? Or maybe just for a chat on life choices? CONTACT ME @ [email protected] ! © Copyright National University of Singapore. All Rights Reserved 25