Research Areas

Large Models for Disease Risk Prediction


Utilizing real-world multimodal healthcare data to train general-purpose large models for disease risk prediction, capable of forecasting the risks of major chronic diseases such as myocardial infarction and stroke over various future time periods for individuals.

Large Models for Health Intervention


Providing personalized, professional health recommendations and guidance for individuals at high risk of major chronic diseases, aiming to prevent the onset and progression of these conditions.

Big Data and Public Health Policy Evaluation


We conduct a systematic assessment of policy effectiveness by deeply analyzing public policies using real-world data. By employing statistical analysis, we evaluate the impact of relevant policies on public health, including disease risks and the associated economic burden.

Multi-omics Big Data Analysis


Employing deep learning to comprehensively process large-scale omics data, such as transcriptomics, proteomics, and metabolomics, to understand the effects of environmental exposure and other factors on health. We also aim to elucidate the biological mechanisms behind genomic variation, epigenetic landscapes, and changes at transcriptional and translational levels.

Environmental Health Big Data Analysis


Leveraging multidisciplinary strengths, we integrate advanced tools and technologies such as satellite remote sensing, geographic information systems (GIS), neuroimaging, bioinformatics, and machine learning to construct high spatiotemporal resolution environmental datasets. We collect population-level data including EEG, near-infrared spectroscopy, and multi-omics data to conduct epidemiological analysis.