A presentation at the 2024 Eye Data and AI Summit
By Dr. Stanley Woo, OD, MS, MBA, FAAO
School of Optometry & Vision Science
The Global Vision Crisis
World report on vision by the World Health Organization
The Facts
- Everyone, if they live long enough, will experience at least one eye condition in their lifetime.
- The investment needed globally to treat existing unaddressed cases of refractive error and cataract: US$14.3 billion
- Cataract surgery US$ 6.9 billion
- Refractive error US$ 7.4 billion
- Unaddressed distance vision impairment in many low- and middle-income regions is 4x higher than in high-income regions.
- Eye conditions are projected to increase due to a variety of factors, including ageing population, lifestyle and NCDs.
- Projected number of people estimated to have age-related macular degeneration in 2020: 195.6 million vs. in 2030: 243.4 million
- Projected number of people estimated to have Glaucoma in 2020: 76 million vs. in 2030: 95.4 million
- At least 2.2 billion people live with a vision impairment. In at least 1 billion of these cases, vision impairment could have been prevented or has yet to be addressed.
- Unaddressed refractive error (123.7 million)
- Cataract (65.2 million)
- Glaucoma (6.9 milion)
- Corneal opacities (4.2 million)
- Diabetic Retinopathy (3 million)
- Trachoma (2 million)
- Unaddressed presbyopia (826 million)
World report on vision. Geneva: World Health Organization; 2019. Licence: CC BY-NC-SA 3.0 IGO. p. xiv. Available from: https://www.who.int/publications-detail/world-report-on-vision [accessed February 2020]
World Health Organization - 3 Major Challenges
- Eye care needs will rise sharply due to changes in demographics and lifestyle
- Data are often lacking and health information systems weak, thus hampering planning
- Eye care is frequently poorly integrated into health systems, for example, in national health strategic plans and health information systems; and the eye care workforce is poorly coordinated
Pan-Canadian Health Data Strategy
Identified gaps in health data:
- No systematic, nor systemic principle-based approach to data use in the health sector;
- No clear accountability in the health sector for its fastest growing asset – data;
- No systemic way to understand public and community health data requirements;
- No strong and coherent governance model for data oversight in the health sector;
- No policy that articulates the duty to share data for the public good while also ensuring it is secure; and
- No common health data terminology to enable effective health data literacy initiatives for health leaders, health workforce and the public.
Building the Eye Data Repository
We propose that the University of Waterloo be the trusted host for the ethical development of an eye data repository in Canada for optometry:
- Experience from US: AOA MORE, AAO IRIS
- Good timing – NEI, FDA, ONC promoting ocular imaging standards
- Importance of longitudinal data for predicting disease, optimal treatment pathways, and precision medicine
Optometry plays a key role to the data needed.
- Optometry is a primary health profession focus on eye and vision care.
- It plays a critical role in maintaining overall health, prevention, early detection, diagnosis, and treatment of eye diseases.
- It contributes to the eye data repository through its widespread reach, clinical insights and commitment to health care.
Canadian Association of Optometrists Membership
- 5,950 OD Members across 10 provinces
- 305 Student members from Canadian and American schools
- 2,037 Canadian Certified Optometric Assistants (CCOA)
- 78 Assistant.e.s optométriques certifié.es canadien.nes (AOCC)
- 13 Council members representing all provinces and students
*As of December 31, 2023 UNIVERSITY OF WATERLOO
Electronic Health Records and Imaging
- EHR clinical data and PHI PLUS diagnostic imaging using the eye as the window to the brain and body.
- GOAL: Leverage partnerships to promote the annotation, curation, archiving and retrieval of large datasets of imaging and clinical data to support machine-learning (ML)/artificial intelligence (AI) research, precision medicine, and population healt
AI in Optometry – Digital Health
In Optometry, big data (large and complex datasets) can helps uncover patterns, predict disease, and improve care across populations. Advanced tools, like AI, has potential to:
- Improve diagnostic/prognostic predictions
- Improve access to care
- Improve business intelligence
- Enhance case-based education for students and CPD
- Provide clinical decision support vs. replacement of OD
- Streamline screening and patient pathway to integrated primary care
What are your priorities for AI in optometry?
Big Data: Key Issues to Address
- Acceptability – Ensuring public and professional trust
- Data ownership, privacy and cybersecurity
- Accountability – Clear roles and responsibilities
- Explainability and trustworthiness of AI models
- De-identification – Protecting patient identity
- Governance – how should this be done?
Partners and Collaborators
The development of the Eye Data Repository is supported by a growing network of collaborators across sectors:
- Fyidoctors, Iris, Eye Recommend….
- Provincial and national associations and colleges
- Industry – EssilorLuxottica
- Government?
- Others?
- UW researchers, grad students, post-docs…
- Dr. Clark Dickerson
- Prof. Jimmy Lin
- Prof. Anita Layton
- Prof. Anindya Sen
- Prof. Helen Chen
- Many grad students and post-docs