Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,161 datasets
A multi-center dataset of paired Cardiac Magnetic Resonance (CMR) images and pixel-level segmentation labels. It covers two core clinical sequences: CINE for functional analysis and LGE for scar tissue detection. The dataset was created by TaipingQu and last updated on April 2,我们发现2026.
Quarterly financial and operational data for hospitals, as reported to the state of Washington. The dataset includes detailed metrics on revenue, patient days, discharges, and contractual allowances segmented by payer type. Columns suggest a focus on Skilled Nursing Facility (SNF), Swing Bed, and Acute Care services.
A dataset titled 'detection disease' published on Kaggle. The specific content, scope, and origin are not detailed in the provided metadata. Its potential applications relate to disease identification and analysis.
A synthetic clinical dataset for predicting fatty liver disease grades, including non-alcoholic and alcoholic fatty liver disease. The dataset appears to contain biomarker data for modeling disease progression. Its origin, size, and specific features are not detailed in the provided metadata.
Figshare hosts a dataset comparing NINJ1 protein levels between patients with coronary heart disease (CHD) and healthy controls. The data is provided in an XLSX file of 15.9 KB, authored by 'yu' and last updated in March 2026.
Estonia began securing over a million citizens' health records with blockchain technology in 2016, following a 2011 partnership with the private startup Guardtime. This case study details the country's GovTech innovation strategy, which positioned it as a global leader in applying distributed ledger technology beyond finance and law into public healthcare. The text-based analysis explores the process of implementing a radical platform innovation to manage medical data and insurance systems.
3.4 million screening and diagnostic mammography images from 110,000 patients collected between 2013 and 2020, with equal representation of Black and White women. The dataset includes 2D, synthetic 2D (C-view), and 3D (DBT) images, with 60,000 lesions linked to structured descriptors and pathologic outcomes. This release represents 20% of the total 2D and C-view data, with DBT, US, and MRI exams to be added later.
France during the first wave of the pandemic, from March to April 2020, is the geographic and temporal scope of this collection. It contains Computed Tomography (CT) images from 10,735 individuals suspected of SARS-CoV-2 infection. The dataset, from the Radboud University Medical Center, provides binary labels for COVID-19 presence based on RT-PCR tests and severity defined as intubation or death within one month.
Kaggle hosts a dataset intended for predicting heart disease rates. The dataset's specific size, features, and origin are not detailed in the provided metadata. Its primary focus is on modeling and forecasting the incidence of heart disease.
An AI-generated synthetic healthcare dataset intended for analytics, dashboards, and machine learning applications. The dataset's provenance, size, and specific features are not detailed in the available metadata. It is hosted on the Kaggle platform.
Baseline demographics and disease characteristics from the Phase II LEAP-005 clinical trial. The dataset details patient information for a study on lenvatinib plus pembrolizumab treatment for advanced gastric, biliary tract, or pancreatic cancer. It was authored by Mariano Ponz-Sarvisé and published under a CC BY license.
Clinical trial data from the Phase II LEAP-005 study assessing lenvatinib plus pembrolizumab for advanced gastric, biliary tract, or pancreatic cancer. The dataset contains antitumor activity assessments per RECIST version 1.1 by Blinded Independent Central Review (BICR). It was authored by Mariano Ponz-Sarvisé and shared under a CC BY license.
Treatment-related adverse events among participants in the LEAP-005 phase II study of lenvatinib plus pembrolizumab for advanced gastric, biliary tract, or pancreatic cancer. The data is a single table (Table 3) from the study results, authored by Mariano Ponz-Sarvisé and last updated in March 2026.
medical-disease-prediction-using basic-symptoms is a dataset hosted on Kaggle. The dataset likely contains records of basic symptoms associated with various medical conditions for predictive modeling. The author, organization, and specific data characteristics are not provided in the available metadata.
Chicago Department of Public Health aggregates weekly positive influenza PCR tests from a network of hospital and commercial laboratories. The data, available from the 2010-2011 season onward, tracks counts and percentages for influenza types A and B and subtypes H3N2 and H1N1pdm09. All data are provisional and represent both Chicago and non-Chicago residents tested by reporting facilities.
412 survey responses from employees in the hospitality sector in Puebla, Mexico. The data were collected by Valentinotti, María to analyze relationships between work–life conflict, emotional exhaustion, and turnover intention. It was last updated on 2026-04-13.
Hospital diversion events declared by San Francisco hospitals, detailing ambulance rerouting. The dataset records diversion start and end times, duration, and hospital names, updated monthly by the San Francisco Emergency Medical Services Agency. It documents the operational rules, including a 2-hour maximum diversion period and system-wide suspensions triggered when four or more hospitals divert simultaneously.
858 patient records from 'Hospital Universitario de Caracas' in Caracas, Venezuela, comprise this dataset for multilabel classification. It includes demographic information, habits, and historic medical records, collected by Kelwin Fernandes, Jaime S. Cardoso, and Jessica Fernandes. Several patients decided not to answer some questions, resulting in missing values.
A retrospective cohort of pediatric patients admitted with abdominal pain to Children's Hospital St. Hedwig in Regensburg, Germany. The dataset includes multiple abdominal B-mode ultrasound images per patient, alongside laboratory tests, physical examination results, and clinical scores like Alvarado and pediatric appendicitis scores. Subjects are labeled for diagnosis, management, and severity of appendicitis.
Clinical data from the PhysioNet/Computing in Cardiology Challenge 2019, focused on the early detection of sepsis. The dataset was created by Matthew Reyna et al. and is licensed under PhysioNet. The description cites significant public health statistics, including an estimated 30 million global sepsis cases annually.