Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,569 datasets
5,500 GitHub repositories are documented across 29 distinct features covering both popularity and operational metadata. The data tracks specific engagement metrics such as stars and forks alongside technical indicators like CI/CD implementation and community health scores.
Simulated lifestyle, behavioral, and clinical health indicators organized into three primary research categories. The data maps neurobehavioral patterns against physiological risk factors to support synthetic health outcome modeling.
Multiple categories of patient-reported adverse event reports and medication errors including drug names and side effects. These records facilitate post-market safety monitoring of pharmaceutical performance based on real-world incidents submitted to the FDA.
This synthetic dataset provides ICU monitoring data designed for mortality risk modeling and time-series analysis. It focuses on binary classification tasks within the healthcare domain to predict patient outcomes, though specific record counts and authorship details are not documented.
This dataset explores the relationship between personal, lifestyle, and regional factors and their influence on medical insurance charges. It serves as a resource for understanding the determinants of healthcare costs across different demographics and locations.
The Hospital Patient Readmission Dataset is a synthetic healthcare collection hosted on Kaggle, specifically designed for readmission prediction tasks. It provides a simulated environment for data scientists to develop and test models within the medical domain without the privacy concerns associated with real patient data. The dataset is primarily focused on binary classification challenges related to hospital and treatment center efficiency.
A balanced dataset of chest X-ray images for pneumonia detection, sourced from Kaggle. The dataset's size, collection methodology, and specific source institution are not detailed in the provided metadata. Further verification after download is required to confirm the exact number of images and their provenance.
Pathology Report Span Infilling is a dataset hosted on Kaggle. The dataset likely contains pathology reports with spans of text removed for infilling tasks. Its specific size, origin, and update date are not provided in the available metadata.
Kaggle dataset on coronary heart disease in New Zealand. The dataset likely contains clinical or epidemiological information, but specific details on rows, columns, and time range are unavailable from the provided metadata. Its origin and creation date are not specified.
State of Washington Office of the Insurance Commissioner collects annual reports from health carriers covering at least one percent of the state's market share. The dataset includes aggregated data on prior authorization requests, approval rates, appeal outcomes, and average response times for six categories of health services. Data is reported for individual and group health plans.
A dataset of chest X-ray images, likely sourced from the National Institutes of Health (NIH). The dataset is hosted on Kaggle and its title suggests it contains 384 images. Specific details on collection dates, patient demographics, and annotation scope require verification after download.
Chest X-ray images from the National Institutes of Health (NIH). The dataset is hosted on Kaggle and appears to be a processed or standardized version of the original NIH Chest X-ray dataset, likely with images resized to 224x224 pixels. The exact number of images, collection timeframe, and specific labels are not detailed in the provided metadata.
California Children's Services (CCS) maintains a list of providers approved to render services to CCS enrollees. The dataset is published by the State of California's Department of Health Care Services and was last updated in January 2026.
The PICNIC Study provides data on myopia-related aberrations, submitted for publication in November 2024. It was authored by Fuensanta Vera-Diaz and last updated in January 2026. Specific details on rows, columns, and file formats are not provided.
A collection of survey data on gaming habits and mental health indicators. The specific row count, column count, and data collection details are unknown.
The Breast Cancer Wisconsin (Diagnostic) Data Set is a well-known dataset published on Kaggle. It likely contains features computed from digitized images of breast mass cell nuclei to aid in classifying tumors as benign or malignant. The specific number of rows, columns, and collection details are not provided in the available metadata.
1700 records for predicting liver disease, sourced from Kaggle. The dataset's specific features, collection method, and origin are not detailed in the provided metadata. Its content and structure require verification after download.
SPARCS data from New York State provides a detailed breakdown of emergency department treat-and-release encounters, including charge statistics, from 2018 onward. The dataset, published by health.data.ny.gov, summarizes visits by facility and payer type. It includes metrics such as median charges, visit counts, and comparisons to statewide averages.
Chest X-ray images compiled for a Kaggle competition. The dataset's specific size, origin, and collection period are not detailed in the provided metadata. Further details on the competition's objectives and data characteristics require verification after download.
Kaggle hosts a pre-trained model named 'xray-trained-weights'. The dataset's specific content, size, and origin are not detailed in the provided metadata. Users must download the dataset to verify the model architecture, training data, and intended application.