Principal Investigator: Professor Ching-yu Cheng
Singapore Eye Research Institute
Professor Wynne Hsu, National University of Singapore, Singapore, Singapore
Ms Haein Ju, Medi-Whale Inc., Seoul, South KoreaTags: 45925, artificial intelligence, epidemiology, eye diseases, risk factor, Vision-threatening
Aims: The primary objective of this research is to evaluate biologic, lifestyle factors and biomarkers related to the development of major vision-threatening eye diseases in Asian and western populations, using data from the SEED study and UK Biobank study. We will further utilize the collected clinical data and images to develop a novel artificial intelligence-based system to predict the onset and progression of diabetic retinopathy or other major eye diseases, using the UK Biobank data for validation.
Scientific rationale: The prevalence of vision-threatening eye diseases is projected to increase steadily with an ageing population. The loss of vision is often irreversible, resulting in loss of productivity, inability to perform activities of daily living, and a substantial reduction in quality-of-life. This poses a significant challenge to healthcare professionals of today and tomorrow. Thus, there is an urgent need for healthcare systems in the world to transit from a curative paradigm to one that emphasizes on prevention. This is especially so in eye care as the gap between supply and demand of eye care services widen globally.
This transition in healthcare system needs to be informed by large-scale genomic and detailed clinical data from well-designed population-based prospective cohort studies, and the UK Biobank is an excellent example of such a resource-rich avenue. The UK Biobank will provide us with the data breadth and depth needed to gain a deeper insight into the individual and combined effects of genetic and environmental determinants for a wide range of eye diseases in adult population. These diseases may be caused by many different exposures, each with a modest effect and interact with one another in complex ways. Therefore, a large sample size is needed to study the specific effects of any specific exposure. The extensive dataset from the UK Biobank will allow in-depth analysis and comparison to be made between different populations.
Project duration: 36 months
Public health impact: Findings from this project may provide important information on risk factors of vision-threatening eye diseases, which may improve our understanding of the complex gene-environment mechanism involved in disease development or progression, and accelerate the development of prevention or early detection program for major eye diseases. This project will also provide useful information on the generalizability of risk factors and impact of major eye diseases in genetically different populations.
Project extension – April 2020
As the population ages, visual impairment from eye diseases is increasing worldwide. The major eye diseases threatening vision include age-related macular degeneration, diabetic retinopathy, cataract, glaucoma, and refractive errors. The challenge posed by these conditions highlights the need for accurate data, not only on the epidemiology, but also on specific modifiable risk factors and the complex gene-environment mechanism involved in the development and progression for these conditions in the world.
The primary objective of this research is to evaluate biologic, lifestyle factors and systemic diseases related to the development and progression of major vision-threatening eye diseases, and the impact of these eye diseases on visual function, using data from the Singapore Epidemiology of Eye Diseases (SEED) Study and the UK Biobank. We will further utilize the collected clinical data and images to develop novel artificial intelligence-based systems to predict the progression of major eye diseases and systemic diseases including chronic kidney disease (CKD including end-stage renal disease), and cardiovascular disease (CVD including stroke, acute myocardial infarction and heart failure).
In addition, we would like to investigate the association between brain MRI, retinal images and variable systemic factors (primarily cardiovascular factors and cognitive factors). For preliminary analysis, both development and test sets will be from the UK Biobank data, while searching for external test set where both retinal and brain images are available with clinical information. The first analysis is for the association between variable numeric brain MRI parameters and systemic factors with machine learning based algorithm. The numeric MRI parameters are already available in the dataset, including the diffusion parameters from diffusion-weighted imaging, and volume of each region of the brain. The second analysis is to use convolutional neural network (CNN)-based method to extract more high-dimensional and abstract information from the images, for investigation of the association between brain images and systemic factors. As CNN-based algorithms learn the relevant features directly from the images, without the need for hand-crafted measurement or feature extraction, this method may provide more automated and clinically feasible model. The third step is to integrate both retinal images and brain MRI into the CNN-based model, and assess the performance of models based on brain MRI + retinal images vs. brain MRI alone. If external test set is successfully acquired while conducting the three steps of analysis, the final step is external validation of the model.
Therefore, as brain MRI and retinal images may have synergy other as common modalities of medical check-up that provides information upon systemic cardiovascular risk, these additional analyses may lead to increase in clinical efficacy for systemic disease screening (including cardiovascular disease) and reduction of socioeconomic burden.
Last updated Jun 24, 2020