Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,759 datasets
The BRIDGE-Open dataset, released by YLab-Open in August 2025, is an open-access subset of the datasets used in the BRIDGE benchmark. It comprises 55 tasks from datasets that can be publicly released, while other tasks involving clinical data remain under regulated access. The original sources and licenses for each included dataset are detailed in the associated research paper.
WMS service provides the urban development plan for the 'Gewann Eisengehrn' area in Ettlingen, Germany. The data is transformed according to the INSPIRE directive and is based on an XPlanung dataset in version 5.0. The service was last updated by the Bundesamt für Kartographie und Geodäsie on August 15, 2025.
A central database tracks prosthetic device provision and associated costs for patients within the Veterans Health Administration. Data is updated quarterly and used for financial and clinical oversight of the national Prosthetics and Sensory Aids program. The system provides detailed and summary reports by station and Veterans Integrated Service Network (VISN).
A Web Map Service (WMS) layer provides the development plan 'Hospital - Etzweide, 1st Amendment' for the city of Öhringen, Germany. The service originates from the XPlanung 5.0 standard and is published by the Bundesamt für Kartographie und Geodäsie. It was last updated on August 13, 2025.
My HealtheVet (MHV) is the Department of Veterans Affairs' online Personal Health Record system for veterans. It provides access to health and military service information, including prescription refills, lab results, and secure messaging with care teams. The dataset's specific row count, column count, and file format are unknown.
Veterans Affairs Central Cancer Registry (VACCR) collects cancer diagnosis and treatment data from 132 VA Medical Centers. Information includes demographics, cancer identification, disease staging, treatment, and outcomes, compiled according to standards from oversight bodies like NAACCR and the Commission on Cancer. Data extraction is available to researchers with approved VA Institutional Review Board studies and Data Use Agreements.
GMAI-Reasoning10K is a high-quality medical image reasoning dataset containing 10,000 carefully selected samples. The data was collected from 95 medical datasets from sources such as Kaggle, GrandChallenge, and Open-Release, covering 12 imaging modalities including X-ray, CT, and MRI. It was created by General-Medical-AI and last updated on July 21, III.
Over 2 million medical studies pair brain MRI scans with radiologists' reports, including descriptions, conclusions, and recommendations. The imaging data features high-quality 1 mm slice thickness and an average of 30 slices per scan. This dataset, created by ud-medical and last updated in August 2025, is designed for detection, classification, and segmentation tasks across more than 50 pathologies.
The Veterans Equitable Resource Allocation (VERA) database integrates patient-specific care and cost data from over 10 clinical and financial source systems, including the Patient Treatment File and Decision Support System. Operated by the Department of Veterans Affairs, it serves as the basis for resource allocation across the Veterans Health Administration. The data is aggregated from monthly extracts for reporting and analysis.
The Remote Order Entry System (ROES) database supports order fulfillment for the Denver Acquisition & Logistics Center, primarily handling hearing aids and related medical products. It integrates contracting, order fulfillment, distribution, and finance functions for the Department of Veterans Affairs and Department of Defense. The dataset includes features for order tracking, serialized device registration, and patient/device history.
Over 2.4 million medical studies contain MRI images of the lumbar spine paired with corresponding text reports from radiologists. The reports include detailed descriptions, conclusions, and recommendations. The dataset is hosted by ud-medical on Hugging Face and was last updated in August 2025.
Monthly hospital utilization data derived from the HCUP State Inpatient Databases and State Emergency Department Databases. The tables detail trends in inpatient stays and emergency department visits, segmented by encounter type, service line, and priority conditions like COVID-19 and influenza.
The Healthcare Cost and Utilization Project State Inpatient Databases contain the universe of hospital inpatient discharge abstracts from participating U.S. states. Developed by the Agency for Healthcare Research and Quality, the data are translated into a uniform format to facilitate multi-state comparisons and include clinical and resource-use information from short-term, acute care, nonfederal hospitals.
A text dataset for medical reasoning tasks in the Arabic language, created by Gheras and hosted on Hugging Face. The dataset was last updated on September 9, 2025. Its specific size, structure, and content require verification after download.
RadLex is a controlled terminology containing more than 30,000 terms for radiology practice, education, and research. It serves as a unified source to standardize indexing and retrieval of radiology information, unifying and supplementing other lexicons like SNOMED-CT, LOINC, and DICOM. The initiative also includes RadReport, a library of report templates to improve clinical reporting practices.
124 handcrafted, multi-turn conversations simulate supportive interactions in mental health contexts. The dataset is bifurcated into dialogues from a clinical therapy setting and a crisis hotline setting. It was created by Locutusque and last updated on July 28, 2025.
ProteinGym V1 is a benchmark suite for evaluating protein fitness prediction and design models, created by OATML-Markslab and last updated on July 21, 2025. It includes nearly 3 million different mutations, covering both substitution and indel types. The dataset incorporates a wide variety of experimentally assayed proteins and clinically annotated mutations relevant to human disease.
50 patient profiles diagnosed with Lateral Lymph Node Metastasis (LLNM) are paired with 263 ultrasound images and 50 radiology reports. The collection includes both original ultrasound scans and processed versions where hospital and equipment metadata have been removed for privacy.
HealthBench provides the evaluation data for OpenAI's medical benchmarking suite, updated as of August 2025. It is designed to work with the simple-evals reference implementation to measure model performance in health-related domains.
As of June 2010, the Master Veteran Index database contained over 17 million patient entries from all VHA facilities nationwide. It serves as the authoritative identity service for VA clients, establishing and synchronizing identities to enable an enterprise-wide view of patient information.