Datasets

IDR data experts have developed a real-world COVID-19 patient dataset for use across the UF community.

Google’s search engine specifically for datasets enables users to find the datasets stored in thousands of repositories.

The de-identified annotated medical imaging data from Stanford AIMI has been made available to foster transparent and reproducible collaborative research.

NIH has a long tradition of making available to the public the results of research it supports and conducts, including publications and scientific data. Sharing data enables reuse, increases transparency, and facilitates reproducibility of research results.

V7 lists 65+ publicly available datasets for machine learning.

MIT’s MIMIC-IV (Medical Information Mart for Intensive Care) is a large database of deidentified health-related data from patients admitted to critical care units of Beth Israel Deaconess Medical Center.

PIC is a large, single-center database of information relating to patients admitted to critical care units at the Children’s Hospital of Zhejiang University School of Medicine.

The eICU-CRD is a large, multicenter, critical care database made available by Philips Healthcare in partnership with the MIT Laboratory for Computational Physiology.

An intensive care database from within the European Union containing de-identified health data related to tens of thousands of European intensive care unit admissions, including demographics, vital signs, laboratory tests, and medications.

HiRID (High-time Resolution ICU Dataset) is a critical care dataset containing data relating to more than 33,000 patient admissions to the Department of Intensive Care Medicine of the Bern University Hospital, Switzerland (ICU), an interdisciplinary 60-bed unit admitting >6,500 patients per year.