Browse every dataset in the Hub

State-based prevalence estimates from the CDC’s Behavioral Risk Factor Surveillance System on modifiable risk factors for chronic disease and leading causes of death, 2011 to present.

A synthetic patient dataset covering 2 million patients from 2008–2010, structured in the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) v5.2.

This dataset presents hospital-level performance ratings for Coronary Artery Bypass Graft (CABG) surgery in California, spanning the years 2011 to 2023.

This dataset provides hospital-level results for CMS complication, patient safety, and mortality quality measures.

This dataset provides global daily reports on the COVID-19 pandemic, including aggregated confirmed cases, deaths, and recoveries, tracked by the Johns Hopkins University Center for Systems Science and Engineering (JHU CSSE).

This dataset comprises 101,766 hospital encounter records for diabetic patients across 130 US hospitals and integrated delivery networks, collected between 1999 and 2008.

This dataset provides daily ambient (outdoor) concentrations of key air pollutants measured across more than 4000 monitoring stations primarily operated by state environmental agencies across the United States and its territories.

This dataset combines two resources from the Centers for Medicare & Medicaid Services (CMS) describing hospice care quality and caregiver experience in the United States.

The INSPIRE dataset is a comprehensive research resource in perioperative medicine, comprising approximately 130,000 surgical cases (representing 50% of all surgical cases) from a single academic institution in South Korea.

This dataset provides state- and county-level measures of Medicare Fee-for-Service market saturation and service utilization across selected healthcare service categories.

This dataset integrates publicly available information from the Centers for Medicare & Medicaid Services (CMS) National Plan and Provider Enumeration System (NPPES) and the National Uniform Claim Committee (NUCC).

The PMC Patient Notes dataset comprises 167,000 patient summaries extracted from case reports within PubMed Central (PMC), supplemented by 3.1 million patient-article relevance annotations and 293,000 patient-patient similarity annotations derived from the PubMed citation graph.

This dataset provides six calculated social deprivation and vulnerability indices (SVI, SDI, NSS7, FDep, ICE) derived from the US Census 2020 5-year American Community Survey data.

This dataset comprises synthetic Medicare Fee-For-Service (FFS) claims, provided by the Stanford Center for Population Health Sciences.

A sampler of 26 public US health tables from CDC, FDA, CMS and AHRQ covering providers, drugs, demographics and disease, useful for exploration and teaching.

Rural–Urban Continuum Codes (RUCC) and Rural–Urban Commuting Area (RUCA) codes from USDA ERS for US counties, census tracts and ZIP codes.

This dataset provides quarterly provisional estimates of death rates for selected indicators of mortality across the United States.

Records for 2,139 participants in AIDS Clinical Trials Group Study 175 (published 1996), a classic benchmark for predicting patient survival.