Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,176 datasets
This dataset supports the DICE-RL framework for refining robot policies via reinforcement learning. It contains pretraining data for behavior cloning and finetuning data across various Robomimic environments. The dataset was created by author 'wintermelontree' and was last updated in March 2026.
Heart disease patient data originally sourced from the UCI Machine Learning Repository. The dataset is hosted on Kaggle, but specific details on the number of records, features, and time period are not provided in the available metadata. Its origin from a canonical academic repository suggests it is intended for predictive modeling tasks.
Brazilian data from March to December 2020 describes sociodemographic and clinical variables for patients with COVID-19. The dataset is a 9.5 KB XLS file. It was created by Natalia L. Freitas and is licensed under CC BY 4.0.
A healthcare dataset designed for early risk detection using artificial intelligence. The dataset is sourced from Kaggle, but the author, organization, and specific collection details are unknown. Its intended application is for building real-time predictive systems for cardiovascular health.
X-ray images of the cervical spine, sourced from Kaggle. The dataset's size, collection method, and specific annotations are unknown. It likely contains medical images intended for analysis.
A dataset for predicting symptoms and treatments for multiple diseases, sourced from Kaggle. The specific number of records, features, and data collection period are unknown. The dataset likely contains columns related to symptoms and treatment options.
FCT LGA Health & Socio-Economic Pan is a dataset published on Kaggle. The title suggests it contains health and socioeconomic metrics, likely at the Local Government Area level within Nigeria's Federal Capital Territory. The dataset's specific content, size, and origin are not detailed in the provided metadata.
Covid-chest-xray is a collection of chest X-ray images related to COVID-19, hosted on Kaggle. The dataset's size, specific collection methodology, and provenance are not detailed in the available metadata. Its content and structure require verification after download.
SyntheaTM synthetic patient generator data models the complete medical history of synthetic patients. The dataset is provided in the OMOP Common Data Model format at three scales: 1,000, 100,000, and 2,800,000 synthetic persons. Amazon Web Services hosts this data, which is free from cost, privacy, and security restrictions for secondary use.
POP Version 1.4.3 code from Los Alamos National Laboratory was modified to create the CCSM3.0 climate model component. Output data is distributed via the Earth System Grid for community access. The model incorporates numerous modifications for improved physics and diagnostics while maintaining the original code structure where possible.
EXIS instrument data measures solar soft X-ray irradiance and solar extreme ultraviolet spectral irradiance in the 5-127 nm range. The dataset is produced by NOAA's National Centers for Environmental Information (NCEI) for the GOES-R series satellites. The information is used to monitor solar flares and variations affecting space weather and Earth's atmosphere.
August 2004 to present data from the EOS Aura Microwave Limb Sounder (MLS) instrument, containing diagnostic quantities for standard geophysical products. The dataset provides near-global coverage from -82 to +82 degrees latitude with profiles spaced approximately 165 km along the orbit track. It is produced by the MLS science team and distributed by the GES DISC.
North American regulatory limits for volatile organic compounds (VOCs) in healthcare facility cleaning. Dataset A contains 650 limit records from 26 jurisdictions, including EPA, CARB, OTC, and Canada SOR/2021-268. Dataset B includes 5,000 healthcare cleaning products with VOC content, certifications, and compliance flags, authored by Dave Cook and hosted on Harvard Dataverse.
2021 data from patients hospitalized in the intensive care unit, including information on vasopressor requirements. The dataset is structured as a tabular Excel file and is openly licensed for reuse. It provides a specific snapshot of ICU care and medication use for a single year.
Over 90,000 bibliographic references on teratology and developmental and reproductive toxicology published since 1965. The DART/ETIC database is maintained on the National Library of Medicine's TOXNET and funded by U.S. EPA, NIEHS, FDA, and NLM.
Approximately 18 million unweighted hospital discharges annually provide a nationally representative view of readmission rates for all payers and uninsured patients. Developed by the Agency for Healthcare Research and Quality, the database contains over 100 clinical and non-clinical data elements from discharge abstracts. It is designed to analyze national trends in readmissions, reasons for return, and associated hospital costs.
Kidney risk records from repeated patient visits, likely sourced from electronic health records. The dataset appears to track the progression of Chronic Kidney Disease over time. It is hosted on Kaggle, but specific details about its size, origin, and update frequency are not provided.
Medical reports likely contain textual clinical information. The dataset is published on Kaggle, but its specific source, size, and creation date are unknown. Columns, sample data, and other metadata are unavailable.
Annual incidence data for peptic ulcer disease from 2020 to 2024. The dataset is a 5.5 KB XLS file, created by Abdulrahman Al-Dawoudi and last updated on March 18, 2026. Platform tags suggest the data originates from a retrospective cohort study assessing seasonal patterns and independent predictors in the broader Baltic region.
552.1 KB XLSX file contains quality of life data for bladder cancer patients and their caregivers. The dataset, authored by Ficky Ficky and last updated in March 2026, is licensed under CC BY 4.0. Row and column counts are unspecified.