Large administrative claims data are often used to describe real-world healthcare utilization, costs, treatment patterns, and effectiveness and safety of medications. These research activities often require identifying patients with particular medical conditions.
When diagnostic codes are unavailable or inaccurate, however, claims analyses can be uninformative or misleading. Supervised machine learning coupled with validation can expand the utility of claims databases – allowing for the accurate characterization of difficult to measure populations or study endpoints.
This webinar will discuss the importance of accurate algorithms, the utility of validation, and the application of predictive models using machine learning to identify cases more accurately and improve the utility of claims analyses.
Register now for an informative webinar to:
- Understand the importance of accurate algorithms and validation in claims based research.
- Understand the reasons that algorithms that have been validated previously may not perform well in your study; and
- Learn how predictive models can be used to identify cases more accurately.