Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,174 datasets
A dataset related to heart disease, likely containing patient attributes for analysis. It is published on the Kaggle platform. The specific source, collection method, and temporal coverage are not provided in the metadata.
HAPNEST Data provides a high-fidelity synthetic genomic resource designed to mimic the scale of modern biobanks. It contains data for 100,000 synthetic individuals across all 22 autosomes, generated by author Koka, Taulant and last updated in April 2026. This data is optimized for benchmarking large-scale genetic analysis pipelines.
100,000 synthetic individuals across all 22 autosomes are represented in this high-fidelity genomic resource. The dataset, generated using the Hapnest framework by author Koka, Taulant of HAPNEST Data, was last updated on April 9, 2026. It is designed to mimic the scale and complexity of modern biobanks for benchmarking computational genetics tools.
HAPNEST Data Full (21-30) is a high-fidelity, full-scale synthetic genomic resource generated using the Hapnest framework. It mimics the scale and complexity of modern biobanks, containing data for 100,000 synthetic individuals across all 22 autosomes. The dataset was authored by Taulant Koka and last updated on April 9, 2026.
Hospital Suspensions data tracks system-wide ambulance diversion suspension events in San Francisco. The San Francisco Emergency Medical Services Agency updates the data monthly. It records the date and time when suspensions begin and end, triggered when four or more hospitals simultaneously declare diversion.
Clinical records of individual patients diagnosed with thyroid conditions, including demographics, clinical findings, and TNM staging. The dataset was created by authors Borzooei, S., Briganti, G., Golparian, M., Lechien, J. R., & Tarokhian, A. as part of research in AI and Medicine, with no funding provided.
Clinical data from patients diagnosed with thyroid diseases, including demographics, treatment history, and TNM staging. The dataset was created by researchers Borzooei, S., Briganti, G., Golparian, M., Lechien, J. R., & Tarokhian, A. as part of AI and medical research, with no specific funding. The last update date and total number of patient records are unknown.
Patient records for thyroid disease research contain demographic, clinical, and treatment outcome attributes. The dataset was created by authors Borzooei, S., Briganti, G., Golparian, M., Lechien, J. R., & Tarokhian, A. as part of research in AI and Medicine, with licensing from UCI and Hamadan University of Medical Sciences.
The Heart-Statlog-UCI dataset is a collection of clinical attributes for predicting the presence or absence of heart disease. It was contributed by Asuncion and Newman from the UCI Machine Learning Repository. The dataset includes 13 attributes such as age, chest pain type, and maximum heart rate, with a mix of real, ordered, binary, and nominal data types.
US hospital financial data includes annual revenue, operating margins, net income, and bed counts. The dataset is hosted on Kaggle, but the author, organization, and specific time range are unknown. Its size, exact row count, and file formats are also unspecified.
Annual wages, hourly pay, and employment densities for healthcare roles across U.S. states. The data originates from the Bureau of Labor Statistics Occupational Employment and Wage Statistics program. The specific time range covered by the dataset is unknown.
Hematology-based patient records likely containing Complete Blood Count (CBC) metrics. The dataset is intended for medical diagnosis and classification tasks, sourced from Kaggle. Specific details on volume, authorship, and update recency are unavailable.
Training data for the first challenge on fully automated assessment of tumor-infiltrating lymphocytes (TILs) in breast cancer histopathology slides. The dataset was contributed by the Radboud University Medical Center and is hosted on AWS Open Data. TILs are an important biomarker that can help target immunotherapy and reduce the need for more aggressive treatments.
US hospital financial data, including revenue, operating margin, and bed counts for approximately 10,000 facilities. The data originates from the Centers for Medicare & Medicaid Services (CMS) Hospital Cost Report Information System (HCRIS).
Provider exclusion counts aggregated by source, state, and year, as described in the input. The dataset contains no personally identifiable information (PII). It is hosted on Kaggle, but the original author, organization, and specific temporal coverage are unknown.
A medical imaging benchmark for binary fracture detection. The dataset is hosted on Kaggle, but its author, size, and specific collection details are not provided. Its intended use is as a benchmark for machine learning tasks in medical diagnostics.
Healthcare Data is a dataset published on Kaggle. Its specific contents, scale, and origin are not detailed in the provided metadata. The dataset's utility and structure require verification after download.
Liqian Wang published this dataset on 2026-04-04. It contains dietary information, clinical characteristics, strain profiles, and antimicrobial resistance analysis for Clostridioides difficile strains isolated from infants with Clostridioides difficile-associated disease (CDAD). The data likely supports investigation into the association between amino acid–based formula feeding and CDAD risk in children under 2 years old.
Infant health data links amino acid-based formula feeding to increased risk of Clostridioides difficile-associated disease in children under two years old. The dataset contains dietary information, clinical characteristics, strain profiles, and antimicrobial resistance analysis for C. difficile strains isolated from infants with CDAD. It was authored by Liqian Wang and last updated in April 2026.
A large-scale collection of 12-lead electrocardiogram recordings intended for cardiac disease detection and artificial intelligence research. The dataset is hosted on Kaggle, but specific details about its size, creation date, and authors are not provided in the available metadata.