Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,196 datasets
A preprocessed version of the classic Pima Indians diabetes dataset claims to enable a Random Forest Classifier to achieve 92.86% accuracy, a significant increase over the 78.57% reported on the original data. It originates from the National Institute of Diabetes and Digestive and Kidney Diseases and was used in a published 1988 study on forecasting diabetes onset. The dataset's objective is to predict whether a patient has diabetes based on diagnostic measurements like glucose and blood pressure.
Echocardiogram reports related to heart disease, published on Kaggle. The dataset likely contains structured or semi-structured data from medical reports. Specific details on volume, origin, and collection date are not provided in the metadata.
Healthcare Claim Denials is a dataset published on Kaggle. It likely contains records related to medical billing and insurance claim processing. The specific source, size, and time period of the data are not detailed in the available metadata.
Patient Health is a dataset hosted on the Kaggle platform. The dataset's specific content, scale, and origin are not detailed in the available metadata. Further verification after download is required to understand its composition and potential applications.
Paul Johnson's rockchalk package provides functions for interpreting and presenting regression analysis results. The collection includes tools for regression diagnostics, regression tables, and plots of interactions and moderator variables. It is used to produce statistics lectures hosted at https://pj.freefaculty.org/guides/.
100,000 non-overlapping image patches from hematoxylin & eosin stained histological slides of human colorectal cancer and normal tissue, each 224x224 pixels at 0.5 microns per pixel. The dataset includes nine manually annotated tissue classes and was created by Jakob Nikolas Kather from the National Center for Tumor Diseases using samples from the NCT Biobank and UMM pathology archive. A separate validation set of 7,180 image patches from 50 non-overlapping patients is also provided.
A dataset comparing patient data for Amyotrophic Lateral Sclerosis (ALS) and normal subjects. It is hosted on Kaggle, but the specific source organization and collection date are unknown. The dataset's size, specific features, and row count are not detailed in the provided metadata.
234 home health agencies in the Detroit metropolitan area are listed. The data includes $204 million in Medicare billing for the 2023 calendar year. The dataset's author and specific source are not provided.
A mixed-methods study collected quantitative survey data from 272 Saudi nurses and qualitative interview data from 17 nurses in three public hospitals in Saudi Arabia's Makkah region. The research was conducted by Mohammed Alshmemri of RMIT University to identify factors influencing job satisfaction and dissatisfaction. Quantitative data were analyzed with SPSS and qualitative data with NVivo software.
The NEOSTAR trial (NCT03158129) was a phase 2 randomized study of 44 patients with operable non-small cell lung cancer. It compares neoadjuvant nivolumab monotherapy to nivolumab plus ipilimumab, with major pathologic response as the primary endpoint. The dataset, from paperswithcode, includes results on response rates, tumor viability, and immune cell frequencies.
Owkin's HER2 data challenge dataset for a 2026 Spring medical imaging internship. The repository contains data and a baseline script, hosted on HuggingFace and last updated on March 23, 2026.
Kaggle hosts a dataset titled 'Patients Cleaned Contact'. The dataset likely contains processed contact information for patients. Its specific size, origin, and update history are not provided in the available metadata.
A collection of chest X-ray images from the MIMIC-CXR database. The dataset is hosted on Kaggle, but specific details about its size, creation date, and exact content are not provided in the available metadata. The title suggests it is a subset or specific version of the larger MIMIC-CXR resource.
A dataset for predicting healthcare insurance costs likely contains variables related to lifestyle choices and medical risk factors. It is hosted on Kaggle, but the author, organization, and specific data volume are unknown. The last update date is also unknown.
A restructured dataset of skin disease images, likely for machine learning tasks. The dataset appears to be prepared for custom stratified splits and K-Fold cross-validation. The original author, organization, and specific collection details are unknown.
18 real people in Boston, MA, USA contributed normal, healthy electrocardiogram recordings. The dataset likely contains time-series data of cardiac electrical activity. Its origin is associated with the MIT-BIH arrhythmia database project.
X-radiographs of sediment cores from Florida Bay were used to examine internal sediment structure and assess mixing. The data supports ecosystem management by defining rates of ecological, physical, and chemical change, where historical records are lacking. A common method for dating change involves measuring the decay of naturally occurring radioactive nuclides.
NOAA NCEI archives this tree ring dataset from the Spitalgasse site in Bavaria, Germany. The chronology covers 118 years from 337 to 219 calendar years before present. The National Centers for Environmental Information (NCEI) under the World Data Service for Paleoclimatology provides this data.
Finland hosts this tree ring chronology from the Rantasalmi Old Hospital site, specifically for Scots pine (PISY). The NOAA National Centers for Environmental Information provides the data, which covers a 443-year period from 569 to 127 calendar years before present. It is part of the NOAA/WDS Paleoclimatology archive and the International Tree-Ring Data Bank.
X-ray mutation data likely contains medical imaging information paired with genetic mutation details. The dataset is hosted on Kaggle, but its specific source, collection method, and size are not provided. Details such as the number of records, column descriptions, and creation date are unknown.