Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,178 datasets
A large-scale dataset released for the 2026 PhysioNet Challenge. The data likely contains clinical or physiological time-series records, as is typical for the challenge series. It is hosted on Kaggle, but specific details on size, features, and collection methodology are not provided in the metadata.
303 patient records from the Cleveland Clinic in the United States. The data is intended for classifying the presence of heart disease. The author, organization, and specific collection date are unknown.
Synthetic Electronic Health Record data designed for a coding challenge focused on Chronic Obstructive Pulmonary Disease prediction. The dataset is published on Kaggle, but its creation date, author, and specific scale are not provided. Its primary purpose appears to be for developing and testing predictive models in a controlled environment.
A sample of 1,005 high school juniors, 692 college juniors, and at least 140 employed adults was administered the Self-Directed Search and validation criteria. The data was used by John L. Holland to examine the validity of theoretically-derived vocational diagnostic signs for predicting self-knowledge, occupational knowledge, and decision-making ability. The study found that signs for good decision-making ability predicted scores on a decision-making task more efficiently than non-SDS variables.
Approximately 15,000 clinical polysomnography recordings from Massachusetts General Hospital patients form the initial core of this dataset, which is intended to grow to over 200,000 records. The Brain Data Science Platform shares this data to support research on sleep scoring and brain health indicators. The dataset is being used to develop CAISR, a collection of AI tools for better-than-human detection of sleep events and disease risk.
A dataset named 'Clinical Trials Trec Qrels' published on HuggingFace by user '2001jdev'. The title suggests it contains relevance judgments (qrels) for the Text REtrieval Conference (TREC) track on clinical trials. The dataset was last updated on 2026-04-20.
1,171 synthetic patient records across 15 tables provide privacy-safe electronic health data. The dataset is designed for machine learning applications in clinical settings. Its origin and specific collection details are not provided.
Non-Destructive Testing and Structural Health Monitoring data. The dataset is hosted on Kaggle, but its author, organization, and specific temporal coverage are unknown. Its size, row count, and file formats are unspecified.
A dataset comparing outcomes for epilepsy treatments, likely containing records for surgical and pharmacological interventions. The dataset is hosted on Kaggle, but its specific origin, size, and creation date are unknown. Columns and data structure must be verified after download.
74123190 bytes of supplementary video material accompany a study on epicardial adipose tissue volume and density in hypertensive patients. The videos likely contain visual data related to cardiorenal complications, coronary heart disease, and heart failure. Metadata is minimal; actual content requires verification after download.
Patient-derived orthotopic xenograft models provide a 2.1 MB dataset detailing the transcriptional and regulatory programs of pancreatic cancer during peritoneal spread. This supplementary file likely contains single-cell multi-omics analyses from patient-derived organoids, offering a molecular view of metastasis. Its cross-platform presence on figshare signals its role as a key resource for cancer biology research.
Supplementary Material 1 from a study on pancreatic ductal adenocarcinoma. The dataset likely contains single-cell multi-omics analyses from patient-derived orthotopic xenograft models and organoids, focusing on peritoneal dissemination. It is available as an XLSX file.
20398-row supplementary dataset supports a study using patient-derived orthotopic xenograft models to investigate peritoneal spread in pancreatic ductal adenocarcinoma. Columns likely contain single-cell multi-omics analyses, delineating transcriptional and regulatory programs associated with cancer dissemination. This data provides a molecular bridge between clinical patient samples and experimental in vivo models.
148,797 data points comprise this supplementary dataset from a study using patient-derived orthotopic xenograft models. The data likely contains single-cell multi-omics analyses related to the transcriptional and regulatory programs of pancreatic ductal adenocarcinoma, specifically its peritoneal dissemination. It is shared under a permissive CC-BY-4.0 license.
Supplementary Material 2 contains 24,444 rows of data from patient-derived orthotopic xenograft models of pancreatic ductal adenocarcinoma. The dataset likely contains single-cell multi-omics analyses, such as transcriptional and regulatory profiles, focused on the process of peritoneal dissemination. It is shared under a CC-BY-4.0 license.
Preliminary weekly hospital respiratory data aggregated to national and state/territory levels reported to the CDC's NHSN since August 2020. The dataset updates weekly on Wednesdays and includes metrics on hospital capacity, occupancy, hospitalizations, and new admissions. It is produced by the United States Department of Health and Human Services, Centers for Disease Control and Prevention.
Digitized ECG data published on Kaggle. The dataset likely contains time-series signals representing electrical activity of the heart. Metadata is minimal; specifics about the number of records, patient demographics, or collection methodology are unknown.
Kaggle hosts a dataset for predicting heart disease. The dataset's specific size, features, and origin are not detailed in the provided metadata. Its content likely contains clinical or lifestyle variables used for binary classification tasks.
Reconstructed micro-CT volumes of carbonized Herculaneum papyri produced for the Vesuvius Challenge. The scrolls survived the eruption of Mount Vesuvius in AD 79 and represent the only intact library known from antiquity. The data is distributed as OME-Zarr multiscale datasets to support virtual unwrapping and text recovery research.
State-level health burden data for diabetes includes prevalence, incidence, and rates of associated conditions like hypertension and stroke. Statistics derive from self-reported surveys, hospitalization records, and Medicare beneficiary files. The dataset is compiled by the U.S. Department of Health & Human Services and was last updated in 2026.