Artificial Intelligence in Medicine - AI Datasets

The Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI) oversees a public repository of imaging data. This collection includes carefully curated and annotated clinical imaging across multiple modalities, including echocardiograms, brain CT scans, MRI, radiographs, and ultrasounds. The data comes from a variety of sources such as Stanford Health Care, Stanford Children's Hospital, the University Healthcare Alliance, and Packard Children's Health Alliance clinics. All datasets in this repository are designated for research purposes and are managed through the Stanford Medicine Research Data Repository (STARR).

HealthData.gov aims to provide entrepreneurs, researchers, and policymakers with easier access to valuable health data, aiming for improved health outcomes for everyone. The website offers a searchable index with over 3,000 datasets covering various areas, some easily accessible with just one click.

A wide range of data collections related to global health and well-being.

The Healthcare Cost and Utilization Project (HCUP) includes the largest collection of longitudinal hospital care data in the United States.

The dataset for a longitudinal study includes neuroimaging, clinical, and genetic data from individuals with Alzheimer's disease, mild cognitive impairment, and healthy controls.

A user-friendly system menu enables access to the Centers for Disease Control and Prevention's (CDC) information resources for both public health professionals and the general public. It offers a broad range of public health information.

Data and statistics covering over 30 subjects, along with tools to aid in analysis.

dbGaP was created to store and share findings from studies exploring how genes and traits interact in humans.

A dataset containing comprehensive cancer genomics, clinical data, and imaging data for various types of cancer enables research on the diagnosis, prognosis, and treatment of cancers.

This benchmark dataset features ten different segmentation tasks across various anatomical structures and imaging modalities, making it ideal for evaluating and comparing medical image segmentation algorithms.

A large, freely-available database of deidentified health-related data associated with over forty thousand patients who stayed in critical care units of the Beth Israel Deaconess Medical Center between 2001 and 2012. The database contains demographics, vital sign measurements taken at the bedside (~1 data point per hour), laboratory test results, procedures, medications, caregiver notes, imaging reports, and mortality (including post-hospital discharge).

A dataset comprising over 100,000 chest X-ray images released by the National Institutes of Health (NIH), annotated for the presence of common thoracic pathologies.

Provides up-to-date state-specific data from all 50 states and national data covering over 700 topics related to demographics, health, and health policies.

A dataset containing comprehensive cancer genomics, clinical data, and imaging data for various types of cancer enables research on the diagnosis, prognosis, and treatment of cancers.