Public-Health_Epidemiology_Population-Surveys

数据集文件元信息以及数据文件，请浏览“数据集文件”页面获取。 当前数据集卡片使用的是默认模版，数据集的贡献者未提供更加详细的数据集介绍，但是您可以通过如下GIT Clone命令，或者ModelScope SDK来下载数据集 #### 下载方法 :modelscope-code[]{type="sdk"} :modelscope-code[]{type="git"} # MedicalAgent Public Health, Epidemiology and Population Surveys This repository is the **Public Health, Epidemiology and Population Surveys sub-database** of Medical Agent. It collects and organizes public health, epidemiological statistics, population survey datasets, global health indicators, mortality statistics, cancer statistics, and disease burden datasets for population-level health analysis, epidemiological trend analysis, public health reporting, health risk assessment, and global health research. The current data package is stored as: ```text 6.19.zip ``` ## Dataset Summary The current repository contains **6 public health and epidemiology data resources**: | Dataset Resource | Data Type | Typical Task | | ---------------------------------------------- | ----------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ | | National Survey of Children's Health（NSCH） | Child health survey datasets, codebooks, topic guides, and question guides | Child health status analysis, healthcare access analysis, family and social environment analysis | | Youth Risk Assessment Monitoring System（YRAMS） | Adolescent health risk survey datasets and documentation | Youth health risk behavior analysis, school health surveillance, trend analysis | | United States Cancer Statistics（USCS） | Cancer incidence and mortality summary statistics | Cancer burden analysis, state/county comparison, cancer trend analysis | | WHO Global Health Observatory（GHO） | Global health indicators, metadata, dimensions, and representative API records | Global health trend analysis, SDG indicator tracking, cross-country comparison | | WHO Mortality Database | Mortality statistics by country, year, age, sex, and cause of death | Mortality trend analysis, cause-of-death analysis, international mortality comparison | | IHME Global Burden of Disease / GHDx | Disease burden estimates, mortality, DALY, YLD, HALE, risk factor outputs, and supporting files | Global burden of disease analysis, health loss comparison, risk factor analysis | These resources belong to the same high-level category: **Public Health, Epidemiology and Population Surveys**. However, they cover different subtypes of public health data, including survey-based population data, cancer statistics, global health indicators, mortality registration data, and model-based disease burden estimates. ## Format The repository is organized as one compressed archive: ```text 6.19.zip ``` Inside the archive, each data resource is stored as an independent compressed package. The original organization of each dataset is preserved as much as possible. Depending on the dataset, the package may contain ZIP files, CSV files, TXT files, Excel files, PDF codebooks, SAS scripts, SPSS syntax files, DAT files, metadata files, data dictionaries, download records, validation reports, and dataset summaries. ## Structure ```text 6.19.zip └── 6.19 ├── National_Survey_of_Childrens_Health.zip ├── Youth_Risk_Assessment_Monitoring_System.zip ├── United_States_Cancer_Statistics.zip ├── WHO_Global_Health_Observatory.zip ├── WHO_Mortality_Database.zip └── IHME_Global_Burden_of_Disease_GHDx.zip ``` If the exact local filenames contain spaces, apostrophes, Chinese characters, or slightly different punctuation, the dataset meaning remains the same. Each compressed package corresponds to one independent public health data resource. ## Dataset Folders ### National Survey of Children's Health National Survey of Children's Health（NSCH）is a public child health survey resource. It contains survey datasets, codebooks, topic guides, question guides, and supporting dictionary materials. The current collection includes: * **NSCH Codebooks** * **NSCH Dataset** * **NSCH Guide to Topics & Questions** Current coverage: * 82 files * 54 subdirectories * Approximately 872.85 MB * Covers 2001, 2003, 2005, 2007, 2009, 2011, and 2016–2024 * Includes a dictionary file exported on 2026-06-18 The NSCH package is useful for child health status analysis, healthcare access analysis, family and social environment analysis, public health survey research, and long-term child health trend comparison. ### Youth Risk Assessment Monitoring System Youth Risk Assessment Monitoring System（YRAMS）is a public adolescent health risk survey resource. It contains national datasets, combined high school data, combined middle school data, and related documentation. The current collection includes: * **Combined high school** * **Combined middle school** * **National datasets & documentation** Current coverage: * 196 files * 127 subdirectories * Approximately 7,460.74 MB * National datasets cover odd-numbered years from 1991 to 2023 * Combined high school and middle school data cover 2019, 2021, and 2023 The YRAMS package is useful for adolescent health risk behavior analysis, school health surveillance, health behavior trend analysis, and public health policy evaluation. ### United States Cancer Statistics United States Cancer Statistics（USCS）is a public cancer statistics resource provided by CDC and NCI. The current package contains pre-analyzed delimited ASCII data tables from the Data Visualizations Tool, rather than patient-level or case-level raw data. The current collection includes: * Original ZIP archive * 9 TXT summary data tables * 1 Excel data dictionary * 1 official SAS input program * Download and validation records Current coverage: * Incidence data years: 1999–2023 * Mortality data years: 1999–2024 * Version: November 2025 submission * Total data records: 4,792,596 rows, excluding headers The USCS package is useful for cancer burden analysis, state-level and county-level comparison, cancer site analysis, demographic disparity analysis, trend analysis, and public health visualization. Because the data are pre-aggregated summary statistics, they are not suitable for patient-level prediction, individual outcome modeling, or patient-level train/validation/test splitting. ### WHO Global Health Observatory WHO Global Health Observatory（GHO）is a global health indicator resource provided by the World Health Organization. The current package contains metadata, dimensions, country and region dimension values, and representative indicator records downloaded through the WHO GHO API. The current collection includes: * Indicator metadata * Dimension metadata * COUNTRY dimension values * REGION dimension values * OData metadata XML * 5 representative indicator datasets Current coverage: * 3,063 indicators * 195 dimensions * 234 COUNTRY dimension value records * 43 REGION dimension value records * 117,394 representative indicator records The representative indicators include life expectancy at birth, maternal mortality ratio, under-five mortality rate, UHC service coverage index, and adult obesity age-standardized estimates. The GHO package is useful for global health trend analysis, cross-country comparison, regional comparison, SDG health indicator tracking, UHC and health system comparison, and public health risk factor analysis. This package is not a complete mirror of all WHO GHO indicators. GHO is continuously updated, and different indicators may have different country coverage, year coverage, estimation methods, and metadata definitions. ### WHO Mortality Database WHO Mortality Database is a mortality statistics resource focused on deaths by country, year, age, sex, and cause of death. The current package is included as an independent data resource under the public health and epidemiology category. It is separate from WHO Global Health Observatory, although both are provided by WHO-related data systems. The WHO Mortality Database package is useful for mortality trend analysis, cause-of-death analysis, international mortality comparison, age-specific mortality analysis, sex-specific mortality analysis, and public health burden reporting. Users should check the included documentation, metadata, variable definitions, and official source notes before formal analysis, especially when comparing countries or years, because mortality registration coverage, coding systems, and cause-of-death classifications may vary over time and across countries. ### IHME Global Burden of Disease / GHDx IHME Global Burden of Disease / GHDx is a disease burden data resource provided by IHME. The current package includes GBD 2023 / GHDx-related files downloaded through GHDx access. The current collection includes: * Hierarchies * Disability Weights * ICD Mappings * Mortality 1990–2023 tables * YLD / DALY / HALE / Risk appendices * Results Tool exports * Supporting PDF, XLSX, CSV, ZIP, DOCX, JSON, TXT, and Markdown files * Validation and audit records Current coverage: * 22 official source files manually downloaded * 63 original and supporting files in the package * 167 files inside ZIP archives * 68 extracted ZIP members * Approximately 715.2 MB before compression * Approximately 626.94 MB after compression Important notes: * This package is not a complete mirror of GBD / GHDx. * GBD results are model-based estimates, not patient-level data and not raw observations. * ICD Mappings are recorded as GBD 2021 files. * Sources Tool data were not exported due to collaborator / employee access restrictions. * Lower and upper fields should be interpreted as uncertainty intervals. * Users should follow IHME / GHDx access terms and citation requirements. The IHME GBD / GHDx package is useful for global disease burden analysis, mortality analysis, DALY and YLD comparison, HALE analysis, risk factor analysis, and cross-location health loss comparison. ## Records The current archive focuses on preserving the collected data packages and their internal documentation. Depending on the dataset package, records may include: * Dataset summary files * Download records * File inventories * SHA-256 checksums * Validation reports * Data dictionaries * Codebooks * Official documentation * Source link notes * License and citation notes Recommended future repository-level record files include: * `collection_audit_2026-06-19.md` * `dataset_collection_table.md` * `dataset_inventory.csv` * `file_inventory.csv` * `source_links.md` * `license_notes.md` * `download_notes.md` These files can be added later to improve traceability, version control, source verification, and file-level auditing. ## Notes and Limitations The resources in this repository are public health and epidemiology datasets, but they do not all have the same data granularity. Users should pay attention to the following points: 1. Some resources are survey-based datasets and may require sampling weights or survey design variables. 2. Some resources are pre-aggregated statistics and should not be interpreted as patient-level records. 3. Some resources are model-based estimates and should not be treated as raw observations. 4. Variable names, question wording, coding systems, and file formats may change across years. 5. Cross-year or cross-country comparison should be conducted only after checking official documentation and metadata. 6. Population-level findings should not be directly interpreted as individual-level causal conclusions. 7. For resources requiring registration, agreement, or platform access, users should follow the original access terms. 8. Users should cite the original official data providers when using these materials for research, reports, or publications. ## Citation If you use this repository, please cite the original official datasets and this ModelScope dataset page. ```bibtex @dataset{medicalagent_public_health_epidemiology_population_surveys_2026, title = {MedicalAgent Public Health, Epidemiology and Population Surveys}, author = {Medical Agent Contributors}, year = {2026}, url = {https://www.modelscope.cn/datasets/K217189/Medical_Data1} } ```