Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
14,812 datasets
157,000 synthetic discharge summaries generated from PMC-Patients case reports using GPT-3.5. The dataset is structured in a Clinical Note - Question - Answer format to build clinical LLMs. It was created by starmpcc and published on Hugging Face in June 2024.
An index lists numerous medical imaging datasets, including CT, MRI, and 4D-lung scans. The collection was compiled by the author 'linhandev' and was last updated in August 2024. Specific datasets referenced include MSD, TCIA, Qin Lung CT, and Qin Prostate Repeatability.
New Jersey's official registry lists all licensed acute care facilities, including hospitals. The dataset includes 23 columns detailing facility locations, ownership, licensing, and contact information. It is maintained by data.nj.gov and was last updated in May 2024.
BreAst Cancer Histology (BACH) Dataset contains Hematoxylin and eosin (H&E) stained breast histology microscopy images. Images are labelled as normal, benign, in situ carcinoma, or invasive carcinoma based on the predominant cancer type. The annotation was performed by two medical experts and images where there was disagreement were discarded.
The ROCO-radiology dataset is a subset of the large-scale Radiology Objects in COntext (ROCO) collection, focusing on medical imaging. It was modified by the author mdwiratathya to select only radiology data and convert images to PIL objects. The dataset was last updated on the Hugging Face platform on June 14, 2024.
A clinical dataset from a Spanish population with subjective adverse food reactions. It correlates symptomatology, body composition, physical activity, and food-specific IgG4 antibody titers for over 40 food antigens. The dataset was authored by Pantoja-Arévalo and last updated in May 2024.
Clinical Trials data was uploaded to HuggingFace by pankajrajdeo on June 26, 2024. The dataset's specific content, size, and structure are not detailed in the available metadata. Columns, sample data, and file formats are unknown.
New York City hotels, motels, hostels, and dormitories are listed across the five boroughs. The dataset is maintained by the City of New York and was last updated in July 2024. Specific row and column counts are not provided.
A study investigating the effect of serum exosomes from prostate cancer patients on tumor cell aggressiveness. The dataset likely contains results from experiments on LNCaP-FGC and PC3 cell lines, including measurements of migration, neuroendocrine differentiation, and enzyme secretion. The data was contributed by Jorge Recio Aldavero and was last updated on May 5, '24.
Pixel-level annotations for cancer regions in TCGA-RCC and TCGA-LU whole slide images, saved as PNG files where white, red, and green mark cancer and blue marks background. Patch-level annotations for TCGA-STAD are provided in CSV files. The dataset was authored by zeyugao and last updated on Hugging Face on 2024-05-15.
956 workers provided data for a study investigating how emotions mediate the relationship between stereotypes ascribed to leaders and evaluations of their performance. The dataset, authored by Cristina García-Ael and harvested from e-cienciaDatos, was last updated on May 5, 2024. It analyzes leaders in male- and female-dominated sectors using the Stereotype Content Model and role congruity theory.
Weekly updated hospitalization data from approximately 6,000 U.S. hospitals, aggregated to country, HHS region, and state/territory levels. The dataset tracks hospital admissions, inpatient bed capacity, and ICU occupancy, with pediatric COVID-19 admission fields beginning March 1, 2022. Data updates ceased after May 3, 2024, following the end of federal reporting requirements.
Research data from a study investigating TRAF1 signalling as a therapeutic target to restore cytotoxic T cell response in chronic Hepatitis C virus infection. The dataset was authored by Juan-Ramón Larrubia and harvested from e-cienciaDatos Dataverse, with a last update recorded on 2024-05 05. It likely contains immunological and clinical measurements from patients with varying infection durations and fibrosis progression rates.
A research dataset from Dataverse describes a new 2D Coordination Polymer with the formula [Cu2(IBA)2(OH2)4]n·6nH2O. The data likely contains results from quantitative total X-Ray Fluorescence analyses and performance tests as an artificial multienzyme. The dataset was authored by Amo-Ochoa, Pilar and last updated on May 5, 2024.
An augmented version of the NIH Chest X-Ray 14 dataset, published on HuggingFace by BahaaEldin0. The dataset was last updated on June 16, 2024. The title suggests it contains a 70 percent augmented subset of the original NIH chest X-ray collection.
Autism Diagnostics Chat En Pt is a dataset uploaded to HuggingFace by author rexionmars on June 20, 2024. The dataset likely contains chat or conversational text related to autism diagnostics. Columns and sample data are unknown, requiring verification after download.
RESPOND-HCWs is a longitudinal dataset from a 2020-2023 EU-funded randomized controlled trial among Spanish healthcare workers with psychological distress. It contains anonymized participant-level data from a stepped-care mental health program evaluation. The dataset includes repeated measures of standardized self-reported mental health scales like PHQ-9, GAD-7, PCL-5, and K-10.
92 heterogeneous Blender models with different height, mass, weight, bone length, and muscular tone. Each model includes four movements: Shoulder Flexion-Extension, Shoulder Abduction-Adduction, Elbow Flexion-Extension, and Forearm Supination-Pronation. The dataset, created by Rubén de-la-Torre Cañizares and harvested from e-cienciaDatos, was last updated on May 5, 2024.
A Norwegian clinical study of 28 individuals with obesity, with 13 achieving ≥5% weight loss. The dataset underpins a 2019 manuscript investigating changes in insulin resistance, leptin sensitivity, and adipokine ratios following weight loss. It includes results from Oral Fat and Glucose Tolerance Tests conducted at the University Hospital of North Norway.
A dataset designed to evaluate the diagnostic capabilities of Large Language Models in the domain of oral disease. It was created by Lines and last updated on April 28, 2024. The dataset includes evaluation data for models such as GPT-3.5, GPT-4, Palm2, and Llama2-70B.