Resources
Understand healthcare data and learn to use it.
Study Designer
Define your variables, inclusion criteria, and analysis plan in an interface designed for clinicians.
Understanding the basics
A progressive introduction to the field, designed for clinicians.
Manual data collection in the age of the electronic health record
Manual collection remains the norm in clinical research. Health data warehouses offer an alternative that is still largely underused.
Defining your variables well: the key to reliable data collection
Concept, temporal anchor, time window, and aggregate function — four dimensions for unambiguous variables.
Health data warehouses: leveraging data already collected
Care data is already in your hospital software. A data warehouse makes it usable for research.
From raw data to usable data
Warehouse data is rarely ready to use. Data quality is a massive cumulative investment — but a lasting one.
How is this data organized
Tables, relationships, joins — understanding data structure to communicate with a data scientist.
Speaking the same language: data models and terminologies
OMOP, SNOMED, LOINC — why standards matter and how they work.
Designing a research project on a data warehouse
From research question to publication: the steps, the roles, and where Linkr fits in.
Go further
Programming, machine learning, data models in detail.
Learn to code
Resources to get started with R, Python, and SQL.
Machine learning in healthcare
Courses and resources to apply ML to clinical data.
OMOP Tutorial
An interactive tutorial to learn the OMOP model with SQL exercises.
Public databases
MIMIC, eICU, PhysioNet — access real data to practice.