Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,197 datasets
HemOncKB provides standardized data and metadata for systemic anticancer drugs and regimens, maintained by Jeremy Warner MD since May 2019. The dataset utilizes the OMOP Common Data Model (CDM) format for core tables and includes ancillary tables for complex oncological data structures. Updates are released approximately quarterly to reflect current clinical knowledge and administrative metadata.
A cross-sectional study of 916 infants under six months old in Ribeirao Preto, Brazil, in 2011. Data on breastfeeding and outpatient care location were collected during the National Vaccination Campaign. The study was authored by Adriana Passanha and analyzes the association between healthcare facility accreditation by the Brazilian Breastfeeding Network and exclusive breastfeeding rates.
Marcos Cezar Pomini surveyed 427 pregnant women receiving prenatal care at a school hospital in southern Brazil from May to December 2017. The dataset contains responses on sociodemographic profiles, gestational characteristics, and knowledge about the neonatal tongue screening test (TL). Results showed 7.7% of women knew the test and 10.5% had misinformation.
A catalog of radio and X-ray observations for Galactic X-ray binaries, compiled from the literature by Arash Bahramian of Curtin University. The collection focuses on the correlation between radio and X-ray emissions in accretion-powered neutron stars and black holes. New measurements are actively added as new publications are noticed.
A dataset exploring the impact of AI tools on student productivity, academic performance, and mental health. The data was collected via a survey, likely from Kaggle. The specific time range and number of respondents are unknown.
The dataset contains images of Personal Protective Equipment (PPE), corresponding ground truth annotations, and predictions generated by the Gemma 4 E4B model. It appears to be designed for evaluating the performance of the Pehra model or similar computer vision systems on PPE detection tasks. The author, organization, and specific data volume are unknown.
ECG_processing likely contains electrocardiogram signals for computational analysis. The dataset is hosted on Kaggle, but its specific size, origin, and update history are not detailed. Columns and sample data are unavailable, so the exact structure and content require verification after download.
A test dataset for medical image segmentation, likely containing MRI scans of the head and neck region. It is published on Kaggle and appears designed for developing or evaluating U-Net models for tumor segmentation. The specific source, collection date, and dataset size are not provided in the available metadata.
A dataset of histopathology images for the classification of osteosarcoma, a type of bone cancer. It was published on Kaggle, a platform for data science competitions and projects. The specific scale, collection method, and time range are not detailed in the available metadata.
A curated collection of fundus photography images for detecting retinal diseases. The dataset is intended for classifying images into categories including Age-related Macular Degeneration (AMD), Cataracts, Diabetic Retinopathy (DR), and Normal. It originates from the Kaggle platform, but specific author, organization, and temporal coverage details are unknown.
Medical LLM safety demonstrations, splits, and harmfulness prompts. The dataset appears designed for evaluating the safety of large language models in medical contexts. Details on its size, creator, and update frequency are not provided in the input.
Chronic Kidney Disease 200K Dataset is a medical dataset hosted on Kaggle. Its title suggests it contains data related to chronic kidney disease, likely for diagnostic or research purposes. The dataset's specific content, size, and origin are unknown from the provided metadata.
Electrocardiogram signal data sourced from NASA. The dataset likely contains physiological recordings from astronauts or related subjects. Its exact size, collection period, and specific features are unknown.
A collection of chest X-ray images hosted on Kaggle. The dataset's size, source, and temporal coverage are unspecified. Metadata is minimal; actual content requires verification after download.
ECG Grouped NASA likely contains electrocardiogram signals, a common medical time-series data. The dataset is hosted on Kaggle, a platform for sharing data for machine learning. Its specific source, size, and collection details are unknown from the provided metadata.
ECG signals comprise 744 fragments of electrocardiogram data. The dataset is hosted on Kaggle, but its author, collection method, and specific time range are unknown. The raw description, columns, and sample data are unavailable.
Approximately 800,000 diagnostic electrocardiograms from nearly 160,000 unique patients, matched to the MIMIC-IV Clinical Database. The ECGs are 10 seconds in length, sampled at 500 Hz, and use 12 leads. This subset is hosted on AWS Open Data and is provided by PhysioNet under the Open Database License.
Between 1984 and 2002, 1,523 H&E-stained whole slide images of lymph nodes were collected from 177 breast cancer patients at Guy's Hospital in London. The cohort includes 122 lymph node-positive and 55 lymph node-negative patients. The slides were digitized at 40x magnification using a Hamamatsu NanoZoomer scanner and are stored in .ndpi format.
RSNA assembled this dataset in 2019 for the RSNA Intracranial Hemorrhage Detection AI Challenge. It consists of de-identified head CT studies provided by four research institutions. Over 60 volunteer expert radiologists labeled more than 25,000 exams for the presence and subtype of acute intracranial hemorrhage.
Active NYC Health Code Regulated Child Care Programs is an official dataset from the New York City Health Department. It lists active group day care and school-based child care programs regulated under Health Code Articles 47 and 43. The data was last updated on March 22, 2026.