The GEMINI Database

GEMINI holds administrative and clinical data from over 2 million hospital admissions across more than 30 hospitals, and updates this regularly.

GEMINI currently contains these types of data

Administrative Data

Data reported to Canadian Institute for Health Information (CIHI) DAD and NACRS databases which includes administrative and demographic information associated with acute inpatient and emergency department care


Costs associated with each hospital encounter

Room/Bed Transfers

Information about bed, room and unit transfers during each hospital encounter


Physician details associated with each hospital encounter


Tests orders and results from Transfusion Medicine, Biochemistry, Hematology, Immunology and Microbiology


Medical imaging test orders and reports


Medication orders during the hospital encounter


Electronically captured vital signs

GEMINI Data Dictionary

This document describes the metadata of all the data tables within GEMINI. Individuals will be granted access to a subset of tables needed to investigate their research question. For any questions or feedback, please contact

Why is it important to collect, clean, and standardize data?

Health care organizations collect information from every patient they see. This could include anything from lab results and radiology reports to age, gender, and why and how frequently they’ve been admitted to a hospital. This information is collected as “data” and is analyzed by physicians, health care teams, and hospitals to make important operational and clinical decisions.

Over time, each hospital, and often even each department, has established their own way of collecting, labeling, and organizing their data. As a result, it can be challenging for physicians, care teams, and hospitals to compile their data into a format that can be analyzed across departments and sights to generate insights that improve patient care.

Our methods achieve 98-100% accuracy compared to manual review of medical records

To ensure that GEMINI data meet the highest quality standards, GEMINI performs rigorous data cleaning and validation processes for every batch of data we receive.