Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,518 datasets
Physionet Challenge 2020 is a dataset from a medical data science competition hosted on Kaggle. The platform tags suggest it contains clinical time-series data intended for healthcare AI applications. The specific content, size, and origin require verification after download.
The U.S. Environmental Protection Agency's High Production Volume Information System provides health and environmental effect information on chemicals manufactured in large amounts. The dataset is updated regularly, with a last recorded update in February 2026.
Synthetic data likely representing cancer patients in China. The dataset is hosted on Kaggle, but its specific size, features, and creation details are unknown. The synthetic nature suggests it was generated for research or modeling purposes.
Dental OPG X-ray images collected in 2024. The dataset is hosted on Kaggle, but the specific source institution, collection methodology, and exact scale are not detailed in the provided metadata. Further details about the number of images, patient demographics, and annotation specifics require verification after accessing the data.
A medical imaging dataset combining resources from the Vindr and Physionet platforms. The dataset includes 384 items and provides annotations for the images. It is hosted on Kaggle, but the original authors, collection dates, and specific image types are not detailed in the available metadata.
MIMIC-III is a critical care database hosted on Kaggle. The dataset's specific size, columns, and temporal coverage are not detailed in the provided metadata. Its content likely pertains to patient care within intensive care units.
Delivering instruction-style prompts that map patient symptoms to multiple potential disease diagnoses categorized by explicit confidence levels. It establishes a structured reasoning format for medical prediction tasks specifically designed for Large Language Model fine-tuning.
A WMS service provides the urban development plan 'Sondergebiet Feuerwehr' for the municipality of Uttenweiler. The data is transformed according to the INSPIRE directive and is based on an XPlanung dataset in version 5.0. The Bundesamt für Kartographie und Geodäsie is listed as the organization responsible for this service.
A Web Feature Service (WFS) dataset describes the urban development plan for a special fire department area in the municipality of Uttenweiler. The data is transformed according to the INSPIRE interoperability standards and is based on an XPlanung dataset in version 5.0. The dataset was last updated on January 14, 2026.
Galar patient 21-30 is a dataset published on Kaggle. The title suggests it likely contains patient-related information, possibly clinical or medical records. The dataset's specific content, size, and provenance are not detailed in the provided metadata.
Kaggle hosts an X-ray dataset where images likely exceed 1000 pixels in both dimensions. The dataset's specific content, size, and origin are not detailed in the provided metadata. Further details such as the number of images, their source, and the date of collection are unknown.
112 entries comprising 58,090,418 characters of text on Traditional Chinese Medicine, Feng Shui, and I Ching, created by jakeveo05 on 2026-01-11. The dataset includes content in Vietnamese, English, and Chinese, with categories for Vietnamese Đông Y, English TCM textbooks, and divination texts.
A dataset containing time-series recordings of Electrocardiogram (ECG) and Galvanic Skin Response (GSR) signals. It is hosted on the Kaggle platform, but the author, collection method, and specific scale are not detailed in the provided metadata. The dataset's recency and exact temporal coverage are unknown.
AureaMind provides a database structured for a Star Model relational schema, focusing on women's health monitoring. The dataset is hosted on Kaggle, but details on its size, specific variables, and creation date are not provided in the available metadata. Its content likely contains health-related metrics and observations suitable for analytical modeling.
Heart disease data published on Kaggle. The dataset likely contains clinical or diagnostic features relevant to cardiovascular health. Its specific size, origin, and update history are not detailed in the provided metadata.
Richard Dzeng of MGH_VIC released this collection of prostate cancer Tissue Microarrays (TMAs) in early 2026. The data serves as a specialized resource for medical imaging research within the field of oncology, specifically focusing on histopathological samples.
5,000 registry-verified clinical trial records are available for analysis. The dataset is described as NLP-ready and ML-ready, indicating suitability for text mining and machine learning applications. It covers global trials from 2024 to 2026.
NIH Chest X-Ray Data Preprocessing Output is a derived dataset from the original NIH Chest X-ray collection. The data has undergone preprocessing steps, likely including image normalization, resizing, or format conversion. The original source is the National Institutes of Health Clinical Center.
Quarterly updated data from the U.S. Department of Health & Human Services provides provider certification, termination, and ownership details for Medicare and Medicaid facilities. The file supports federal regulatory requirements and CMS-sponsored quality research efforts. Information is organized by CMS Certification Number.
2016-2019 de-identified summary table of prevalence rates for vision and eye health indicators from Medicaid Analytic eXtract (MAX) data. Prevalence estimates are stratified by age group, gender, and state.