Addressing missing data in comparative effectiveness research based on electronic health records
Electronic health records (EHR) have been increasingly used for comparative effectiveness research (CER) because it contains rich clinical information that is not typically available in other secondary data sources. However, missing data is a common limitation when using EHR for CER. Much key information, such as laboratory results, imaging data, smoking status, or body mass index, is missing not completely at random. Therefore, advanced statistical methods often need to be implemented to ensure study validity. We aim to discuss key considerations and specific statistical methods to address missing data in CER based on EHR in North America and Europe.
In this webinar you will learn:
1. To discuss key considerations when designing and implementing comparative effectiveness research (CER) based on electronic health records (EHR) with missing data
2. To discuss statistical solutions for optimal validity of CER based on EHR with missing data