Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,157 datasets
Harvard Dataverse hosts replication data from a prospective diagnostic accuracy study authored by Suneet Sood. The dataset contains paired readings from a test device (Vivaray Hb Pro) and a reference device (Coulter blood cell counter). It was last updated on April 27, 2026.
Behruz_without_mean is a dataset published on Kaggle. Its title suggests a medical or clinical context, possibly related to a specific study or variable analysis. The dataset's specific content, size, and origin are not detailed in the available metadata.
Kaggle hosts a dataset of handwritten medical prescriptions. The dataset's specific scale, origin, and creation date are not detailed in the provided metadata. Columns and sample data are unavailable, limiting immediate assessment of content.
A dataset of medical prescription documents, sourced from Kaggle. The specific content, size, and origin are not detailed in the provided metadata. Users must download the data to verify its scope and structure.
Structured data from ClinicalTrials.gov includes a primary_endpoint_met field. The dataset's size, specific time range, and authorship are not detailed in the provided metadata. It is hosted on the Kaggle platform.
De-identified orthodontic medical records contain standardized clinical information and treatment plans. The dataset is suitable for research in orthodontic diagnosis, treatment outcome analysis, and related machine learning or statistical modeling. All patient records are anonymized to protect privacy.
Kaggle hosts a dataset titled 'Breast Cancer Diagnosis'. The dataset likely contains records related to diagnostic features for breast cancer. Metadata is minimal; the author, organization, and specific data characteristics are unknown.
Healthcare_patient_analysis_clean is a dataset hosted on Kaggle. Its title suggests it contains processed information related to patient analysis. The specific source, collection method, and temporal coverage are not provided in the available metadata.
Patient ETL Assessment Data is a dataset hosted on Kaggle. Its title suggests it relates to the assessment of Extract, Transform, Load processes for patient information. The dataset's specific content, size, and origin are not detailed in the available metadata.
SZCH-X-Rays is a medical imaging dataset released on HuggingFace by author diaoquesang. The test set is currently available, with training and validation sets scheduled for release after a related paper is officially accepted. The dataset was last updated on April 25, —.
COVID-19 Radiography Dataset is a collection of medical images, likely chest X-rays, related to COVID-19 diagnosis. It is hosted on the Kaggle platform, but details about its size, creation date, and authorship are not provided in the available metadata. The dataset's content and structure require verification after download.
Kaggle hosts this dataset for classifying electrocardiogram (ECG) signals. The title references the MIT-BIH Arrhythmia Database, a standard benchmark in cardiology. The dataset likely contains time-series ECG recordings with labels for different heart rhythms.
Healthcare Intent QoS Dataset(synthetic) is a dataset hosted on Kaggle. The title suggests it contains synthetic data related to Quality of Service metrics, likely for network traffic modeling in a healthcare context. The dataset's specific size, columns, and creation details are unknown.
A 585KB dataset integrates animal experiment biochemical measurements, processed clinical data from MIMIC-IV, and gene ontology and KEGG pathway enrichment analyses to investigate lactate-related metabolic changes. This multi-modal collection supports the specific research on the role of lactate metabolism in diabetic nephropathy. It provides a bridge between experimental findings, real-world clinical data, and systems-level biological insights.
5.5 KB of tabular data on reported COVID-19 cases, hospitalizations, and fatalities in Greater Sydney, compiled by Christopher Standen and last updated in April 2026. The dataset covers the period up to 21 February 2022 and is shared under a CC-BY-4.0 license.
LIBERO-Para is a controlled diagnostic benchmark for evaluating the paraphrase robustness of Vision-Language-Action models in robotic manipulation. It was created by HAI-Lab and was last updated in April 2026. The benchmark independently varies action expressions and object references to analyze how linguistic variation affects model performance.
Cancer patient records across India for survival analysis and healthcare ML. The dataset likely contains patient-level data relevant to oncology outcomes. The temporal coverage spans from 2022 to 2025.
A medical dataset constructed for evaluating machine learning models in predicting diabetes occurrences. It contains clinical parameters for several patients, including pregnancies, glucose, blood pressure, skin thickness, insulin, BMI, diabetes pedigree function, and age. The dataset is licensed under CC0-1.0.
Task03_Liver_clean is a subset of the Medical Segmentation Decathlon focused on liver segmentation. The dataset likely contains CT scan images and corresponding segmentation masks for training and evaluating medical image segmentation models. It is hosted on Kaggle and appears to be intended for use with the MedSAM text-prompt segmentation model.
Supplying statistics on hospital stays and in-hospital mortality for patients with a primary diagnosis of Cystic Echinococcosis in Italy from 2015 to 2022. It includes quartile values (25th percentile, median, 75th percentile) for length of stay and mortality rates, segmented by patient age categories. The data is derived from hospital discharge records.