Exploring data to build cohorts for downstream analysis
For most research studies using real world health data, the first step is the important process of defining the cohort of interest. Cohort building uses defined inclusion and exclusion criteria that fits a given research question, and then the cohort can be used for downstream analysis, such as GWAS or diagnostic discovery. Health data can also be explored to find data trends or phenotypes of interest for hypothesis generation.
This first training session of the Data Science Get Results series will demonstrate how to find real world health data within the Lifebit Platform, introduce standardised versus non-standardised data, show useful ways for exploring data, and present different types of querying for building a cohort.
Note, that the data utilised in this session is synthetic, and does not include any participant identifiable information. Only users who are registered to use the Lifebit Platform across any Lifebit client will be eligible to attend this course. Any attendees who do not meet this criteria will be unregistered prior to the course.
What you will learn
- How to use and explore standardised data versus source, non-standardised data
- How to create a query with an easy to use point and click interface
- How to identify simple cohort insights
- How to export cohorts for downstream analysis
Module
Data Science
Target audience
This course is intended for researchers who need to browse data and create cohorts with inclusion/exclusion criteria using a graphical user interface. Attendees tend to be academic researchers, data scientists, pharmaceutical researchers or clinicians. Only users who are registered to use the Lifebit Platform across any Lifebit client will be eligible to attend this course.