| Title: | Predict multiple systemic diseases using retinal imaging, risk factors and multi-omics |
| Lead Institution: | The Hong Kong Polytechnic University |
| Principal investigator: |
Application 101032
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 and validate machine learning models to predict multiple systemic diseases through eye imaging, risk factors and multi-omics. Specific aims are: 1. To explore the associations between retinal biomarkers and a wide range of systemic diseases, and identify those correlated well with retinal imaging. 2. To build machine learning models to predict the onset of systemic diseases using biomarkers derived from retinal imaging, risk factors and multi-omics (metabolites and genetics). 3. To investigate the interplay between retinal structures, risk factors, multi-omics and systemic diseases. Scientific rationale: The retina is a known indicator of systemic microvascular health. Over the years, fundus photography has been an accessible, inexpensive, and even automatic method amiable for wide-range screening. With the increasing incidence of chronic diseases, accurate prediction of an individual is crucial for targeting preventive treatment for those at high risk. The retina shows the end-organ changes of the body in response to multiple insults, therefore has the potential to further stratify participants previously unidentified. Besides, the interplay between genetics, behaviour, retinal biomarkers and systemic diseases is not fully understood. Duration of the project: 36 months. Public health impact: The heavy public burden of systemic diseases calls for accurate and accessible prediction models to identify high-risk individuals. Our proposed project, to develop and validate machine learning models for predicting systemic diseases based on retinal imaging and other risk factors, aims to further improve disease stratification and benefit those previously unidentified with common risk factors. Furthermore, our project will interpret the contribution, interplay, and causal relationship of predictors has great potential to uncover the underlying mechanisms and build robust prediction models. Last but not least, with fundus photography becoming more inexpensive and automatic, the accessibility of the screening tool has the potential for large-scale population screening, thus reducing the burden of multiple systemic diseases.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 13993 | Association of metabolomic aging acceleration and body mass index phenotypes with mortality and obesity-related morbidities | Xiaomin Zeng (+9) | 2024 | Aging Cell |
Enabling scientific discoveries that improve human health