Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,852 datasets
1,500 question-answer pairs related to dermatology, compiled by Mreeb and last updated in November 2023. The dataset likely contains inquiries about skin diseases, symptoms, medications, and treatment modalities, intended for fine-tuning language models.
Images of human tissue slides, some containing cancer, sourced from the NCT biobank and the UMM pathology archive. The dataset includes tissues from different parts of the body, organized into 9 classes. The dataset was created by Owkin and last updated on October 26, 2023.
National data from the CDC's National ART Surveillance System (NASS) provides a snapshot of services, patient characteristics, and success rates for assisted reproductive technology across U.S. fertility clinics for the year 2020. The dataset includes clinic profiles, patient demographics, and cycle outcomes, linked by a unique ClinicID. It was published by data.cdc.gov and last updated in August 2023.
yfyeung's dataset comprises 272 simulated medical conversation audio files in mp3 format and their corresponding text transcripts. The dataset focuses on respiratory cases and was published in a Nature Scientific Data paper in 2022. The dataset was last updated on the Hugging Face platform on 2023-11-10.
2002-2010 county-level prevalence data for behavioral risk factors from the CDC's Behavioral Risk Factor Surveillance System (BRFSS). The dataset includes estimates for selected metropolitan area counties with at least 500 survey respondents, compiled by the Centers for Disease Control and Prevention (CDC). It covers topics like modifiable risk factors for chronic diseases and leading causes of death.
The Behavioral Risk Factor Surveillance System (BRFSS) SMART project provides county-level prevalence data for selected metropolitan areas from 2011 to 2012. Data is collected via a continuous state-based surveillance system combining landline and cell phone surveys, focusing on modifiable risk factors for chronic diseases. The dataset is hosted by data.cdc.gov and was last updated in August 2023.
2020 final success rates for Assisted Reproductive Technology cycles are reported by the National ART Surveillance System. Data includes cumulative success rates for patients using their own eggs and non-cumulative rates for donor egg cycles, linked across four datasets by a unique ClinicID. The data was published by data.cdc.gov and last updated in August 2023.
2020 data from the National ART Surveillance System provides an overview of clinic services, contact information, and summary statistics for fertility clinics across the United States. The dataset includes four linked components covering services, patient characteristics, success rates, and annual summaries, all connectable by a unique ClinicID. It is published by data.cdc.gov and was last updated in August 2023.
Daily records from the beginning of the pandemic through at least June 2022 provide COVID-19 metrics for Connecticut. The dataset includes confirmed and probable cases and deaths, hospitalizations, and tests, broken down by age group and date. It is published by the Connecticut Department of Public Health on data.ct.gov.
25 columns of data track COVID-19 metrics at the county level in Connecticut, including Confirmed cases, Probable cases, Hospitalized cases, Total deaths, Confirmed deaths, and Probable deaths. The dataset is published by data.ct.gov and was last updated on August 2, 2023. It contains information starting from June 16, 2022, and is updated daily.
COVID-19 Cases, Hospitalizations, and Deaths (By County) - ARCHIVE contains daily counts of confirmed and probable cases, hospitalizations, and deaths for Connecticut counties. The data is published by data.ct.gov and was last updated on August 2, 2023. It includes metrics such as total case rate and county codes, with data sourced from the Connecticut Department of Public Health and the Connecticut Hospital Association.
Patient Doctor dataset was published by Postzeun on the HuggingFace platform and last updated on December 2, 2023. The dataset's content likely relates to interactions between patients and healthcare providers. Column names and specific data details are unavailable.
A dataset of 400 records listing diseases, their symptoms, and treatments. The data was sourced from various medical websites accessible through Google search and uploaded by QuyenAnhDE in November 2023. It contains four columns for disease code, name, symptoms, and treatments.
2020 data from the National ART Surveillance System (NASS) summarizes patient demographics and ART service types performed at fertility clinics across the United States. The dataset is published by data.cdc.gov and was last updated in August 2023. Patient characteristics are presented per treatment cycle, meaning individuals with multiple cycles in the reporting year are represented multiple times.
Know Medical Dialogue V2 is a dataset of medical conversations published on HuggingFace by mlabonne. The title suggests it likely contains doctor-patient dialogue transcripts. Its specific content, size, and structure require verification after download.
100,000 non-overlapping image patches from hematoxylin & eosin (H&E) stained histological images of human colorectal cancer and normal tissue. All images are 224x224 pixels at 0.5 microns per pixel and are color-normalized using Macenko's method. The dataset was manually extracted from 86 H&E stained slides from the NCT Biobank and UMM pathology archive, and last updated on HuggingFace in October 2023.
2014 funding recommendations from the CDC's Best Practices for Comprehensive Tobacco Control Programs guide. The data include recommended and minimum total funding levels for state programs, with breakdowns by intervention areas such as State and Community Interventions and Cessation Interventions. These data update a previous 2007 report and are reported at total and per capita levels.
AeroPath is a benchmark dataset for airway segmentation that includes challenging pathology cases. The dataset was created by author andreped and was last updated on Hugging Face in November 2023. Its specific size, format, and license details are not provided in the available metadata.
2007 funding recommendations from the CDC's evidence-based guide for state tobacco control programs. Data include total and per capita funding levels, with breakdowns by intervention areas such as State and Community Interventions and Cessation Interventions. The dataset is hosted on data.cdc.gov and was last updated in August 2023.
Healthy People 2020 provides a framework for action to reduce tobacco use as a public health problem. The dataset includes objectives, operational definitions, baselines, and targets for tobacco use indicators from the U.S. Centers for Disease Control and Prevention. Baseline years vary by objective, with targets set for the year 2020.