Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,756 datasets
EgoExOR is a dataset for comprehensive understanding of surgical activities, featuring both egocentric and exocentric video perspectives. The dataset was created by authors including Ege Özsoy and Arda Mamur, with official code for a paper submitted to the NeurIPS 2025 Datasets & Benchmarks Track. It was last updated on the Hugging Face platform on September 29, 2025.
HISTAI Skin B2 is a dermatological pathology dataset released by Histai in 2025, covering medical data from the United States. It serves as the data foundation for the research findings presented in Arxiv:2505.12120.
Annual facility-level reports from California hospitals detail services capacity, inpatient and outpatient utilization, patient demographics, and financial statements. The data includes revenues and expenses categorized by type and payer, alongside balance sheet information. It is compiled by the State of California's Department of Health Care Access and Information.
HISTAI-breast is a histopathology imaging dataset for breast cancer research released by histai in September 2025. The collection is associated with Arxiv publication 2505.12120 and covers medical samples from the United States. Access is gated and requires manual approval from the authors due to the high resource cost of its assembly.
Replication data and code for a study on minimum wage and supplementary health insurance in Canada. The materials were authored by Zhao and Grignon and are hosted on the Borealis Harvested Dataverse platform. The dataset was last updated on October 13, 2025.
Histai Skin B1 contains an unspecified quantity of skin histopathology images released by the Histai group in September 2025. This collection serves as the foundational data for the Arxiv 2505.12120 publication and focuses on medical samples from the United States.
Four standardized area measurements for England's health administrative units as of April 2023. The data covers Sub Integrated Care Board Locations, Integrated Care Boards, and NHS regions, with measurements provided in hectares to two decimal places. This dataset is provided by the Government Digital Service and was last updated on the platform in August 2025.
Four standardized area measurements for England's health administrative boundaries as of April 2018. The data includes Clinical Commissioning Groups, NHS England Region Local Offices, and NHS England Regions. Measurements are provided in hectares to two decimal places and follow the Eurostat-recommended approach for calculating population density.
Histai Hematologic is a US-based medical dataset released by Histai in September 2025, linked to Arxiv publication 2505.12120. It provides hematologic data for research purposes, though specific record counts and column schemas are not publicly disclosed. Access is managed through a manual approval process under a CC BY-NC 4.0 license.
UniqueData's Spinal Cord Dataset contains MRI scans of the spine in DICOM format, labeled by doctors and accompanied by PDF reports. The collection includes 9 studies with images captured from different angles. The dataset was last updated on Hugging Face in September 2025.
Histai Thorax is a medical dataset focused on thoracic pathology, released by the Histai organization in 2025. It is associated with the research publication Arxiv 2505.12120 and covers medical data within the United States region.
A lightweight dataset of (anchor, positive, negative) triplets for training Vietnamese medical text embeddings. Anchors are short section headers, positives are answer snippets from the same article, and negatives are semantically related snippets from other articles in the same category. The dataset was created by mtue29 and last updated on September 25, 2025.
MedRedQA is a dataset of 50,991 medical questions and responses sourced from qualified medical professionals. The dataset was uploaded to HuggingFace by user bagga005 and was last updated on September 25, 2025. It contains 40,792 training, 5,099 test, and 5,100 validation question-answer pairs.
Prevalence estimates for select chronic conditions derived from the National Health and Nutrition Examination Survey (NHANES). The dataset is curated for the NCHS Data Query System (DQS) and was last updated in August 2025. It includes columns for ESTIMATE, STANDARD_ERROR, and confidence intervals across various demographic SUBGROUPS.
The University of Texas High-Resolution X-ray CT Facility (UTCT) provides X-ray CT scans of a phantom containing 208 19-mm glass spheres arranged in a hexagonal pattern. Data is intended for evaluating 3D data processing, with variable voxel size and provided with varying degrees of down-sampling. The dataset was last updated on October 15, 2025.
New York State hospital emergency department encounters are summarized by facility and quarter from 2018 onward. The data categorizes visits into treat and release, those requiring ambulatory surgery, and those resulting in inpatient admission. It is published by health.data.ny.gov based on SPARCS (Statewide Planning and Research Cooperative System) data.
The City of New York provides data on incidents handled by FDNY Fire units, collected via the New York Fire Incident Reporting System (NYFIRS). This dataset includes fire, medical, and non-fire emergencies, with information structured to report to the national NFIRS system. It captures details on incident types, locations, and resources used for mitigation.
17,600 professionally annotated veterinary electronic health records (EHRs) from UK first-opinion practices are partitioned into training, evaluation, and test sets. The dataset features free-text clinical narratives mapped to International Classification of Disease 11 (ICD-11) syndromic categories.
Japanese medical incident reports compiled from the Japan Council for Quality Health Care. The dataset summarizes specific incident details, background factors, and proposed improvements. It was created by Sakaji-Lab and last updated in September 2025.
Search strategies for six major databases including MEDLINE, EMBASE, and Web of Science, focusing on randomized controlled trials for blood transfusion thresholds. The dataset was created by Daniela Ziegler, with an initial search conducted on March 27, 2024, and last updated on May 28, 2026. It was harvested from the Borealis Dataverse platform.