Embedded Files
Kaggle Datasets
Kaggle Datasets
Kaggle offers a wide range of free, open datasets that are available to use for practice. Type 'health' (or any other keyword) in the search field to find datasets related to health.
Health Data Research Network Canada
Health Data Research Network Canada
The Data Access Support Hub (DASH) of the HDRN provides a comprehensive list of health data resources available across Canada, as well as support for data access and an algorithm inventory. Costs may be associated with use of the DASH and/or for data sources.
Canadian Primary Care Sentinel Surveillance Network (CPCSSN)
Canadian Primary Care Sentinel Surveillance Network (CPCSSN)
This pan-Canadian database contains de-identified information for nearly 1.9 million patients, extracted from the electronic medical records (EMRs) of primary care providers. This includes demographics, diagnoses and medical history, prescribed medications, laboratory results, physical measurements, behavioural risk factors, billing, vaccinations, and allergies. Fees apply and data are analyzed within a virtual secure research environment.
Institute for Clinical Evaluative Sciences (ICES)
Institute for Clinical Evaluative Sciences (ICES)
ICES offers a wealth of data reflecting nearly all interactions with the health system in Ontario, including registries, health service administrative data, survey data, clinical data, and special collections. Researchers can submit a request for data or analytic services HERE.
GEMINI Hospital Database
GEMINI Hospital Database
Clinical and administrative data are collected as part of the GEMINI database from over 20 hospitals in Ontario for more than 370,000 patients. This database is available for research purposes. Researchers must submit a proposal for review and follow the steps outlined HERE. Fees may apply.
Medical Information Mart for Intensive Care (MIMIC III)
Medical Information Mart for Intensive Care (MIMIC III)
This is a large, free, publicly available database containing de-identified data for patients admitted to the Beth Israel Deaconess Medical Center in Boston, Massachusetts. There are several steps to complete before access is granted, which are detailed HERE.
More information about MIMIC: https://mimic.mit.edu
Synthetic EHR Data
Synthetic EHR Data
SyntheaTM is an open-source patient data simulator that has created several large synthetic EHR datasets freely available for secondary uses. See paper by Walonoski et al. for more details about the methods and software.
Page updated
Google Sites
Report abuse