Synthetic data Using Population Profiles for cardiOvascular Risk facTors (SUPPORT) dataset

The SUPPORT (Synthetic data Using Population Profiles for cardiOvascular Risk facTors) dataset is a large-scale resource comprising 777,358,492 synthetic individuals aged 35–84 across seven geographic regions of Mainland China (Central, East, North, Northeast, Northwest, South, and Southwest) for 2020. Each individual has a detailed profile of sociodemographic attributes and major cardiovascular disease (CVD) risk factors, including blood pressure, cholesterol, body mass index, and diabetes history. The population was constructed using iterative proportional fitting and multivariate normal distribution sampling, integrating data from China's Seventh National Population Census, the Global Burden of Disease (GBD) study, and numerous health surveys. Technical validation against census statistics and independent cohorts, including the China Kadoorie Biobank, confirmed the high fidelity of the dataset to real-world population data. The R scripts used to generate and validate the synthetic dataset are publicly available on GitHub (https://github.com/pkuepi/SUPPORT). The SUPPORT is open-source and can be extended with additional attributes. This resource enables individual-level modeling of CVD and is publicly available at https://doi.org/10.5281/zenodo.17406896 .

Lists of provinces/autonomous region/municipality in seven regions of Mainland China*:

Central: Henan, Hubei, Hunan

East: Shanghai, Jiangsu, Zhejiang, Anhui, Fujian, Jiangxi, Shandong

North: Beijing, Tianjin, Hebei, Shanxi, Inner Mongolia

Northeast: Liaoning, Jilin, Heilongjiang

Northwest: Shaanxi, Gansu, Qinghai, Ningxia, Xinjiang

South: Guangdong, Guangxi, Hainan

Southwest: Chongqing, Sichuan, Guizhou, Yunnan, Xizang (Tibet)

* Note: The synthetic population refers to the population of the 31 provinces, autonomous regions and municipalities of the Chinese mainland, excluding residents in Hong Kong SAR, Macao SAR and Taiwan region.