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/

Transcript

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
4. 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
5. 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/
6. 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
7. 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
8. CHI Applications © Copyright National University of Singapore. All Rights Reserved 8 https://www.mii.ucla.edu/research/areas/co nsumer-health-informatics/
9. 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
10. 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
11. 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
12. My NUS Research Projects © Copyright National University of Singapore. All Rights Reserved 12
13. 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
14. 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/wat ch?v=ogI6IRPEXFU
15. © Copyright National University of Singapore. All Rights Reserved 15 Portable and interactive hand rehab exercises
16. © Copyright National University of Singapore. All Rights Reserved 16 Gamification to motivate stroke survivor to perform more rehabilitation
17. © Copyright National University of Singapore. All Rights Reserved 17 AI and automation reduce the burden of therapist
18. 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
19. 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/wat ch?v=e0-nev_pEQs © Copyright National University of Singapore. All Rights Reserved 19
20. 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
21. 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
22. 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
23. 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.
24. 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
25. Invitation to join me • Interested in a collaboration in IoT/AI/Data Science? • Or maybe just for a chat on life choices? • CONTACT ME @ cchm87@nus.edu.sg ! © Copyright National University of Singapore. All Rights Reserved 25