Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,208 datasets
2025 research data from a study published in Food and Chemical Toxicology investigates the effects of cadmium and a high fructose diet on metabolic and reproductive health in female CD-1 mice. The dataset is associated with a publication by the U.S. Environmental Protection Agency and other researchers. It contains experimental data supporting the analysis of contaminant and dietary impacts.
Comprising data from a pragmatic randomized controlled trial with 308 participants comparing Treat-to-Target and Treat-to-Avoid-Symptoms strategies for early gout. Participants were followed for 24 months across seven centers in the Netherlands. Data include baseline characteristics, laboratory measurements, medication use, gout flares, adverse events, and patient-reported outcomes collected every three months.
A list of U.S. Medicare providers and suppliers whose billing privileges have been revoked and who are under a current re-enrollment bar. It includes provider names, NPIs, revocation authorities, revocation effective dates, and re-enrollment bar expiration dates. The data is maintained by the U.S. Department of Health & Human Services.
A dataset hosted on Kaggle containing physiological signals related to electrocardiography (ECG) and polysomnography (PSG). The specific time range, collection method, and author are not provided in the available metadata. Its content likely includes time-series data for modeling or analysis.
Kaggle hosts a dataset titled 'Work Place Mental Health Risk Predictor'. The dataset's columns suggest it likely contains variables for assessing mental health risks in occupational settings. Metadata is minimal; actual content requires verification after download.
A_Multi-Class_Bone_Fracture_X-Ray is a Kaggle-hosted dataset. Its title suggests it contains medical X-ray images categorized by different types of bone fractures. The dataset's specific size, origin, and update date are unknown.
Clinical Severity and Lipid Risk Analysis suggests this dataset links lipid profiles to acute pancreatitis outcomes. Published on Kaggle, it likely contains clinical and biochemical measurements for patients. The specific data volume, collection period, and originating institution are not provided.
Kaggle hosts a dataset of retinal fundus images. The title suggests the collection is likely split into subsets, potentially for tasks like training and validation. The dataset's specific size, origin, and collection date are unknown.
A medical dataset titled 'Medical Dataset Ct Rate Tar Sharded Fine 20260323' was published on the Hugging Face platform by author JiaMao. The dataset is tagged as 'Healthcare' and was last updated on April 5, 2026. Its specific content and structure are not detailed in the available metadata.
A medical dataset hosted on HuggingFace by JiaMao, last updated on April 5, 2026. The title suggests it contains CT (Computed Tomography) scan images, likely related to rate or tariff analysis. The specific content, scale, and collection methodology require verification after download.
A sequential mixed-methods study dataset explores factors influencing interprofessional collaboration within surgical teams in Indonesia. The data was authored by Imanullah Putra and is hosted by Harvard Dataverse. Row and column counts are not specified in the available metadata.
14 attributes describe patient data for predicting the presence of heart disease. The target field is an integer indicating the presence (1) or absence (0) of heart disease. This database was created by the Cleveland Clinical Foundation.
A dataset titled 'Healthcare Inequality Analytics Dataset' is hosted on Kaggle. The raw description suggests it contains AI-driven healthcare equity records. The author, organization, and specific temporal or geographic coverage are unknown.
The mcr package provides regression methods for quantifying the relationship between two measurement methods, as implemented by Sergej Potapov. It addresses regression problems with errors in both variables and without repeated measurements. The package implements algorithms for Theil-Sen and equivariant Passing-Bablok estimators, following CLSI recommendations for analytical method comparison.
A German-language text titled 'Individuum und Gemeinschaft' (Individual and Community) authored by Peter Weibel. The description references a discussion on networked individualism and its relation to society, specifically mentioning Karlsruhe as a central hub. The dataset is sourced from the paperswithcode platform.
10,000 to 100,000 synthetic records modeling stroke recovery and rehabilitation access in Sub-Saharan Africa, created by electricsheepafrica in 2026. The data simulates stroke types, acute care interventions, and functional recovery outcomes across three distinct care tiers. It specifically addresses the high disability rates and low rehabilitation access characteristic of the region.
1942-1949 analysis of Britain's role in forming NATO, authored by John Baylis. The work argues for a 'depolarization' approach, emphasizing the roles of countries beyond the U.S. and Soviet Union. It examines the pragmatic diplomacy of Foreign Secretary Ernest Bevin and the coordination of Western European states.
2,494 synthetic text-only clinical cases formatted for instruction tuning, designed for fine-tuning the MedGemma 1.5 4B IT model on dental diagnosis and treatment planning. The dataset covers 98 unique dental conditions and is split into 2,246 training and 248 validation samples. It was created by naazimsnh02 and last updated on February 23, 2026.
Kaggle hosts a dataset containing symptom, antecedent, and diagnosis information intended for medical artificial intelligence development. The author, organization, and specific scale of the data are not provided in the available metadata. The last update date for this dataset is also unknown.
A realistic healthcare dataset for predicting missed patient appointments using machine learning. The dataset is hosted on Kaggle, but specific details about its size, origin, and creation date are not provided. Its description indicates it is designed for building predictive models related to patient attendance.