| Title: | Retinal features and age-related diseases |
| Lead Institution: | Centre for Eye Research Australia |
| Principal investigator: |
Application 94372
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
Aims: The overall goal of this project is to develop new risk prediction models and detection and management systems for age-related diseases. Specific aims are: 1) To explore the relationship between age-related eye disease and associated genes. 2) To explore the causality of previously reported risk factors in age related diseases and mortality. 3)To build a deep learning system for age-related outcome prediction and risk assessment. 4) To develop eyecare clinical tools for age-related disease detection and management based on models developed from retinal features. Recent developments in deep learning have revealed that many health-related outcomes, such as aging, cardiovascular events, mortality, cognitive dysfunction could be predicted using imaging techniques with or without a series of combined risk factors. It is promising to build an artificial intelligence (AI) system using different imaging techniques, along with other demographic information, biological variables and behavioural data to decompose genetic and environmental influences on age related outcomes, and to develop clinical tools that can help disease detection and management. Since vision has significant impact on the quality of life, and examinations of the eyes could be easily obtained, we will pay special attention on the eyes. The project duration is expected to be 36 months. Our proposed project has the potential to predict the onset and progression of age-related diseases such as cardiovascular events, macular degeneration, and glaucoma, which can then be translated into useful clinical tools for disease detection and management. Potential impact of this AI project includes 1) improving quality of life in people especially the elderly people, 2) developing more effective and efficient detection and management models, and 3) inform health policy.2 Publications
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 9490 | Deep neural network-estimated age using optical coherence tomography predicts mortality | Ruiye Chen (+10) | 2023 | GeroScience |
| 9017 | Retinal Vascular Measurements and Mortality Risk: Evidence From the UK Biobank Study | Mayinuer Yusufu (+9) | 2024 | Translational Vision Science & Technology |
Enabling scientific discoveries that improve human health