Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,812 datasets
SkinCAP is a multi-modal dataset of 4,000 dermatology images annotated with medical descriptions. The dataset was created by author joshuachou and last updated in July 2024. Images were sourced from the Fitzpatrick 17k and Diverse Dermatology Images datasets.
A subset of Korean medical questions sampled from the AIHUB super-large healthcare Q&A dataset. Responses were generated using the GPT-4o and GPT-4o-mini models in August 2024. The dataset was created by ChuGyouk and last updated on Hugging Face on 2024-08 21.
The CoD dataset was created by FreedomIntelligence as part of research on interpretable medical agents using a chain of diagnosis approach. It is associated with the 2024 arXiv paper 'CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis'. The dataset was last updated on the Hugging Face platform on August 23, 2024.
omi-health's Medical Dialogue To Soap Summary dataset contains 10,000 synthetic dialogues between patients and clinicians, generated using GPT-4 based on PubMed Central case reports. Each dialogue is paired with a corresponding SOAP summary, also generated by GPT-4. The dataset is split into 9,250 training, 500 validation, and 250 test entries.
The PSST Challenge dataset focuses on high-accuracy automatic phoneme recognition of disordered speech in a diagnostic context. It was created by jimregan and last updated in September 2024.
The Dxbench dataset is associated with the 2024 arXiv paper 'CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis'. It was uploaded to Hugging Face by FreedomIntelligence on 2024-08-23. The platform tags indicate it contains clinical text in English and Chinese, formatted in JSON, and is intended for token classification tasks.
Financial plan and reports on its implementation, additions and changes to them for the Central City Hospital. The dataset was last updated on August 15, 2024, and originates from the States site of Ukraine. The data is available in multiple file formats including Excel and PDF.
Historical data from the State of Maryland provides hospitalization rates related to Alzheimer's or other dementias per 100,000 population. The dataset covers the period from 2008 to 2017 and was last updated in August 2024. It is part of the State Health Improvement Process (SHIP) initiative.
CheXpert is a large dataset of chest X-rays for automated interpretation, featuring uncertainty labels and radiologist-labeled reference standard evaluation sets. The dataset was created by the Stanford ML Group and uploaded to Hugging Face by 'danjacobellis'. The Hugging Face record was last updated on July 18, 2024.
WORD provides abdominal organ segmentation labels for CT images, developed by HiLab-git and published in Medical Image Analysis (MedIA) in 2022. It functions as a benchmark for clinical applicability and annotation-efficient learning in deep learning workflows.
Russian-language dataset of 2,282 patient conversations with a medical bot. The training sample includes 2,053 conversations, and the test sample includes 229 conversations. It was authored by Mykes and last updated on July 15, 2024.
Trier, Germany contains points of interest for cemeteries within the city's urban area. The data is provided by the Bundesamt für Kartographie und Geodäsie and was last updated on July 18, 2024. It is accessible through an OGC Web Feature Service (WFS) interface as part of an INSPIRE download service.
Geospatial data from 2019 shows hospital treatment cases per 10,000 inhabitants for the 45-64 age group at the district level in Europe. The data is provided by the Bundesamt für Kartographie und Geodäsie and was last updated in June 2024. It is part of a broader collection of thematic health maps that includes metrics on doctors, dentists, and pharmacies.
European Union open data provides a 2019 thematic map visualizing hospital treatment cases for diseases of the musculoskeletal system. The data is aggregated at the association level and normalized per 10,000 inhabitants. It was published by the Bundesamt für Kartographie und Geodäsie and last updated on June 30, 2024.
Mimicgen Stack D4 Ep100 is a dataset published on Hugging Face by dusty-nv. The title suggests it contains data related to robotic manipulation, likely involving stacking tasks. The dataset was last updated on August 26, 2024.
A collection of chest X-ray images for the task of pneumonia classification, published on the Hugging Face platform by author Ewakaa. The dataset was last updated on August 22, 2024. The specific number of images, file formats, and licensing details are not provided in the available metadata.
Tsomaros published a dataset titled 'Medical Dataset' on the Hugging Face platform. The dataset was last updated on August 21,我们发现了一个错误，请重试。
Obesity rate for adults 20+ years old from the US Diabetes Surveillance System, maintained by the Division of Diabetes Translation at the Centers for Disease Control and Prevention. The dataset includes county-level obesity percentages with confidence intervals and geographic identifiers. It was last updated on 2024-06-11.
Health service metrics and indicators from Nova Scotia Health, aggregated from multiple sources including hospital inpatient, emergency, surgical, and long-term care systems. The dataset is anonymized and used for public reporting on the Action for Health platform. It was last updated in May 2024 by data.novascotia.ca.
32,120 axial computed tomography slices from 10,594 CT scans of 4,427 patients. The dataset includes 1-3 lesions per image with bounding boxes and size measurements, totaling 32,735 annotated lesions. It was created by farrell236 from NIH PACS data and last updated on Hugging Face in June 2024.