Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,157 datasets
NeuroCycle+ is a dense-sampling structural MRI dataset examining brain structural changes across a five-week period. The dataset was created by xenificity and involves four participants scanned intensively, with approximately 25 sessions each. It was last updated on Hugging Face in April 2026.
Anonymized raw data from a case–control study evaluating the association between the DEFB1 rs11362 polymorphism and periodontitis. The dataset also contains clinical outcomes following non-surgical periodontal therapy. The data was contributed by Huynh, Linh to Harvard Dataverse and last updated on April 22, -2026.
ACT Government data provides admitted patient care performance metrics for public hospitals in the Australian Capital Territory. The dataset is published by DAB-ReportingandAnalysis and was last updated in March 2026.
A 9.5 KB Excel file containing Gelman-Rubin diagnostic values and 95% upper credible intervals for model parameters. The data was authored by George Bamwebaze and last updated on March 19, 2026. It appears to be derived from a spatiotemporal model, likely using a Kalman filtering technique, related to neonatal mortality in Uganda.
MIMIC-IV is a large, publicly available database of de-identified health data related to patients admitted to intensive care units. The dataset is published on Kaggle, though the specific scale, time range, and contributing institution are not detailed in the provided metadata. Its content likely contains detailed clinical records, which are a cornerstone resource for medical informatics research.
A collection of chest X-ray images, likely from the National Institutes of Health. The dataset is hosted on Kaggle, but specific details on size, collection dates, and annotation are not provided in the metadata. The title suggests it may be a version of a known NIH chest X-ray dataset, possibly containing 224-pixel images.
Tooth X-Rays is a dataset of dental radiographs hosted on Kaggle. The dataset likely contains images of teeth for analysis. Specific details regarding the number of images, collection methodology, and licensing are not provided in the available metadata.
Potentially Preventable Visit (PPV) rates for emergency department discharges in New York State, calculated by 3M Health Information Systems software. Data includes observed, expected, and risk-adjusted rates per 100 people, aggregated by patient zip code and discharge year beginning in 2011. The dataset is published by health.data.ny.gov.
3,000 HIV-infected patients participated in this Phase III clinical trial conducted by the ACTG Statistical and Data Analysis Center to compare short-course and long-course tuberculosis preventive therapies. The study followed participants for a median of 3.3 years to track tuberculosis incidence, treatment completion rates, and safety outcomes.
A collection of fundus images annotated to a gold standard for detecting glaucoma. The dataset is hosted on Kaggle, though specific details on size, collection dates, and authorship are not provided in the available metadata. Its primary purpose is to serve as a benchmark for developing and evaluating automated glaucoma detection algorithms.
The Health Evidence Review Commission (HERC) Prioritized List dataset contains administrative records related to healthcare funding decisions in Oregon. Columns such as FileDate, ListEffectiveDate, and FundingLine suggest it tracks the versioning and financial categorization of medical services. This dataset appears on multiple government data platforms, indicating its use in public health policy and administration.
Front desk triage at a medical clinic. This dataset likely contains simulation data for practicing skills and diplomacy in handling competing demands at a healthcare facility. The dataset was authored by David Topps and last updated on April 25, 2026.
A dataset from Borealis Harvested Dataverse illustrating the distinction between steps and decisions in OLab case design. The dataset, created by David Topps, contains no clinical content and was last updated on April 25, 2026.
A clinical case from the CCases series designed for medical clerks. The case focuses on a patient presenting with fatigue, challenging learners to handle diagnostic uncertainty. The case was authored by David Topps and is hosted on the Borealis Harvested Dataverse platform, with a record last updated on April 25, 2026.
A 2026 study assessed the implementation of a "7-1-7" timeliness metric for tuberculosis (TB) screening and TB preventive therapy (TPT) under routine programmatic conditions. The data was collected from 12 health facilities in Kenya, focusing on household contacts of index patients with bacteriologically confirmed pulmonary TB. The dataset supports analysis of programmatic efficiency and adherence to timeliness targets.
California hospital data on central line-associated bloodstream infections (CLABSI) reported to the state's public health department. It includes metrics such as observed and predicted infection counts, central line-days, and Standardized Infection Ratios (SIR) for facilities including acute care and critical access hospitals. The data is used to compare hospital performance against a national baseline.
Kaggle hosts this dataset titled 'memristorkan_kaggle_sdc4dopant'. The dataset likely contains information related to memristor devices and dopant characteristics, as suggested by its name. Its specific contents, size, and creation details are not provided in the available metadata.
A synthetic dataset designed to resemble the MIMIC-III clinical database. It is published on Kaggle, though the specific author and creation date are unknown. The dataset likely contains simulated patient records for research purposes.
A register of current contracts valued over $10,000 held by the Gold Coast Hospital and Health Service. The data was published by Queensland Health and last updated on March 19, 2026.
The Allen Ivy Glioblastoma Atlas contains images of human glioblastoma brain tumor tissue sections. Each section is probed for specific gene expression and paired with an adjacent histologically stained section. All images have been annotated for tumor features by a machine learning process trained by expert medical doctors.