This course aims to teach the concepts of clinical data models and common data models. Upon completion of this course, learners will be able to interpret and evaluate data model designs using Entity-Relationship Diagrams (ERDs), differentiate between data models and articulate how each are used to support clinical care and data science, and create SQL statements in Google BigQuery to query the MIMIC3 clinical data model and the OMOP common data model.
Introduction: Clinical Data Models and Common Data Models
-This week describes clinical data models and explains the need for and use of common data models in national and international data networks. We will also cover the features of Entity-Relationship Diagrams (ERDs) to describe the key technical features of data models.
Tools: Querying Clinical Data Models
-We take a deep dive into the technical features of clinical data models using MIMIC3 as our example and research common data models using OMOP as our example.
Techniques: Extract-Transform-Load and Terminology Mapping
-This module teaches learners about the processes and challenges with extracting, transforming and loading (ETL) data with real-world examples in data and terminology mapping.
Techniques: Data Quality Assessments
-We explore the dimensions of data quality by reviewing its challenges, data quality measurements used to measure it, and data quality rules to assess its acceptability for use.
Practical Application: Create an ETL Process to Transform a MIMIC-III Table to OMOP
-In this module, you gather everything you’ve learned to complete a real-world hands-on exercise using ETL methods to convert MIMIC3 data into the OMOP common data model.
Laura K. Wiley, PhD and Michael G. Kahn, MD, PhD