| Title: | Artificial intelligence for using multi-modal data to improve the identification and prediction of diseases in the UK Biobank |
| Lead Institution: | Sun Yat-sen Memorial Hospital, Sun Yat-sen University |
| Principal investigator: |
Application 100739
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
Scientific rationale: Cardiovascular diseases (CVDs) remain the leading cause of death worldwide accounting for ~32% of all global deaths, with the expectation that this number will rise to > 23.6 million deaths annually by 2030. Also, the morbidity and mortality of cancers and other chronic diseases, and severe or acute diseases are rapidly growing and becoming prominent obstacles to increasing life expectancy. These diseases are a growing concern, and new techniques are needed to promote healthcare centers worldwide to appropriately manage them. In our research project, artificial intelligence (AI) will be used to provide key technological support to address clinical problems. Based on deep learning on the comprehensive data, AI algorithms with well-performed accuracy will play an important role in the early prevention, identification, treatment and prognosis on diseases. Furthermore, with the assistance of AI, the individualized diagnosis and treatment process will be achieved, and clinical problems encountered in the medical process could be settled. Aims: In this research, we seek to: (1) Incorporate multiple levels of omics data (genomics, transcriptomics, proteomics, metabolomics, etc.) to improve the identification and prediction of diseases. (2) Develop artificial intelligence models for early detection and prognosis prediction of diseases using Biobank imaging data. (3) Investigate the influence of genetic information and environment risk factors to the occurrence and development of diseases based on Biobank comprehensive individualized data. (4) Develop artificial intelligence models to identify disease risks using multi-modal data across different levels of biology. Project duration: The duration of the project will be for 36 months. Public health impact: Our AI systems are ultimately designed for clinical application and to settle unmet clinical demands comprising early prevention, diagnosis and treatment of CVDs, cancers or other chronic diseases, and severe or acute diseases. Our AI systems based on UK Biobank cohort study have the potential to achieve global generalization and then benefit the patients. Furthermore, our research will provide a favorable opportunity for drug discovery and development process, which will eventually contribute to the rapid development of effective drugs.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 14426 | Machine learning-based plasma metabolomics for improved cirrhosis risk stratification | Jingru Song (+10) | 2025 | BMC Gastroenterology |
Enabling scientific discoveries that improve human health