AI Integration in the Fight Against Age-Related Macular Degeneration
Sponsored Content by ELRIG (UK) Ltd. Jan 3 2024 Reviewed by Danielle Ellis, B.Sc.
Thought Leaders Wen Hwa Lee CEO and Chief Scientist Action Against Age-Related Macular Degeneration
In this interview conducted at ELRIG UK Drug Discovery 2023, Wen Hwa Lee, CEO, and Chief Scientist at Action Against Age-Related Macular Degeneration (AAAMD), offers an enlightening perspective on merging AI with ophthalmology to forge new paths in healthcare and drug discovery. Please introduce yourself and briefly overview your career and how you became the CEO and Chief Scientist at Action Against AMD?
My name is Wen Hwa Lee. I'm the CEO of Action Against AMD (AAAMD), a research charity. I started my career as a molecular biologist and geneticist, then moved into structural biology and computational biology in the early 2000s. I joined the Structural Genomics Consortium in 2004, which led me to focus on big data space and drug discovery. When the AAAMD charity was founded, they were looking for someone with my profile to develop new approaches and therapies to avoid or slow AMD as early as possible. Can you provide an overview of the main challenges in utilizing AI for healthcare, specifically in ophthalmology, and how your organization addresses these challenges?
The challenges lie in data fragmentation, standardization, and integration, especially in ophthalmology. We tackle this by focusing on participant -centric data aggregation and a common data framework. Our approach involves integrating ophthalmic scans with other omics and creating a grassroots movement to encourage public participation in research programs. In your talk, you mention the existence of gaps in healthcare data for training AI algorithms. Could you elaborate on these gaps and their significance in the context of AI-driven drug discovery?
Healthcare data is often skewed towards disease rather than health, leading to gaps in predictive and preventive healthcare. We aim to capture any data covering pre-disease, pre-diagnostic, and pre-hospitalization stages to enable early intervention and targeted drug discovery – therefore, our focus is on public participation in addition to patient participation . Our objective is to understand and utilize the data that goes beyond the immediate disease manifestation.
Image Credit: LALAKA/Shutterstock.com Collaboration across sectors is a key theme in your presentation. Could you share some examples of successful multi-sector collaborations that have improved data availability for AI-driven research in ophthalmology and healthcare more broadly?
We are currently working on implementing the Foresight project, which will act as an honest-broker data aggregator, ensuring ethical and secure data usage and access. Additionally, we aim to collaborate with as many scientists as possible – from academia, industry, and equipment manufacturers – to streamline data collection and analysis. Our approach aims to create a shared, standardized data repository while ensuring data privacy and security. How do you envision the future of healthcare data aggregation, especially in terms of making missing data more accessible for research purposes? Are there specific technologies or strategies you believe will be instrumental in achieving this goal?
We are exploring the use of existing technologies for redeployment in multisystemic data aggregation. Our goal is to make data collection and aggregation cost-effective and accessible. We aim to develop a distributed network approach, akin to the "Uber of healthcare," to ensure the efficient and affordable acquisition of diverse healthcare data. Ophthalmic data is highlighted as a valuable resource for disease-agnostic drug discovery with AI. Could you provide some examples of how ophthalmic data has been successfully leveraged in this manner and what potential benefits it offers to drug discovery R&D?
Ophthalmic data has been effectively utilized in identifying early biomarkers for neurodegenerative diseases like Parkinson's. By analyzing retinal thickness and other eye scan data, researchers can predict disease progression and optimize drug dosing strategies. This approach can significantly improve the success rates of clinical trials by identifying at-risk populations and early disease stages.
Image Credit: CGN089/Shutterstock.com Given the rapid evolution of AI and healthcare, what ethical considerations and data privacy concerns should researchers and organizations be mindful of when working with healthcare data and AI algorithms?
Researchers must adhere to ethical standards and understand the legal constraints associated with data usage. Collaborating with regulatory bodies and charities can help establish standardized protocols for data access and consent. It's crucial to build direct relationships between researchers and patients to ensure transparent and ethical data usage. Can you share some insights into the practical implementation of AI-driven drug discovery in the field of ophthalmology? Are there any specific projects or initiatives that have yielded promising results?
In addition to Foresight, our ongoing pharmacoepidemiology repurposing projects are focusing on identifying novel drugs for AMD. By leveraging AI, we analyze a variety of data sets and aim to develop new biomarkers to track disease progression and patient stratification. Our goal is to integrate this data with clinical trials and accelerate the development of effective treatments within the next five years. In closing, what advice or key takeaways would you offer to researchers, industry professionals, and organizations looking to harness the power of AI in healthcare and drug discovery, based on your experiences and insights?
Emphasize innovative thinking and interdisciplinary collaboration to harness the full potential of AI in healthcare. Look beyond the conventional data sources and leverage existing technologies to develop cost-effective solutions. Foster direct engagement with patients to build trust and ensure ethical data practices. Stay open-minded and proactive in exploring new avenues for research and collaboration. Where can readers find more information? https://www.actionagainstamd.org/ https://elrig.org/ About Wen Hwa Lee
Dr Wen Hwa Lee (Lee) is CEO and Chief Scientist at Action Against Age-Related Macular Degeneration (AAAMD), a research charity focused on tackling the leading cause of legal blindness in developed world at its earliest stages with maximum affordability and accessibility. Lee is a molecular and structural biologist with a wide international network in drug discovery, including charities, academia, industry, and government agencies. Previously at the University of Oxford, Lee is an experienced leader in setting up partnerships and alliances with multiple stakeholders to accelerate discoveries for drug discovery. He designed and implemented several strategies in two of the largest and most successful international public-private partnerships for drug discovery – the Structural Genomics Consortium and the European Lead Factory. Along with his scientific endeavours, Lee also advised high-level government representatives from different countries and charitable institutions on policy and strategy to integrate scientific, societal, and economic impact. Presently Lee also chairs the INSIGHT Hub’s Data Trust Advisory Board (DataTAB), jointly developed with the Open Data Institute to bring in public and patients at Governance level for a transparent, fair, and accountable use of health data.
Sponsored Content Policy: News-Medical.net publishes articles and related content that may be derived from sources where we have existing commercial relationships, provided such content adds value to the core editorial ethos of News-Medical.Net which is to educate and inform site visitors interested in medical research, science, medical devices and treatments.
