| Title: | Improving disease risk prediction and prevention |
| Lead Institution: | University of South Australia |
| Principal investigator: |
Application 89630
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
The overall aim of this project is to discover risk factors and to improve ways to predict and prevent chronic diseases with the view of developing precision health approaches to improve health and well-being. For many chronic diseases preventative action is currently taken in midlife, after much damage has already occurred. Indeed, some of the deadliest diseases progress in silence until a stage when treatment options are limited. Using comprehensive information available from the UK Biobank, this project will implement various statistical approaches and use artificial intelligence ('machine learning') to discover risk factors that affect risk of chronic diseases (cancer, cardio-metabolic, respiratory, neurodegenerative, and mood disorders) combined disease risks and mortality. We will fit models which will allow the data to show which risk factors are important for predicting early stages of disease and analyze the data to see which of the associations appear to be true ('causal') and what mechanisms may explain these effects. This approach provides an opportunity to discover truly novel insights into the factors that are important for disease risk. We will also work to identify groups of people who are at high risk of developing disease, and who might benefit from increased screening or monitoring. Importantly, we will conduct analyses to test different approaches, and see which modifiable factors may help to lower the risk of disease in those most affected. This project is expected to contribute towards improved prediction and prevention of disease. Our aim is to contribute to a brighter future, where people will have the ability to engage in pre-emptive disease prevention, stopping the disease before any signs are present.5 Publications
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 11554 | Hypothesis-free discovery of novel cancer predictors using machine learning | Iqbal Madakkatel (+4) | 2023 | European Journal of Clinical Investigation |
| 13198 | LLpowershap: logistic loss-based automated Shapley values feature selection method | Iqbal Madakkatel (+1) | 2024 | BMC Medical Research Methodology |
| 12755 | Large-scale analysis to identify risk factors for ovarian cancer | Iqbal Madakkatel (+5) | 2024 | International Journal of Gynecological Cancer |
| 8815 | Phenome-wide association study of ovarian cancer identifies common comorbidities and reveals shared genetics with complex diseases and biomarkers | Anwar Mulugeta (+7) | 2024 | Cancer Medicine |
| 9984 | Uncovering Predictors of Low Hippocampal Volume: Evidence from a Large-Scale Machine-Learning-Based Study in the UK Biobank | Yigizie Yeshaw (+4) | 2024 | Neuroepidemiology |
Enabling scientific discoveries that improve human health