Summary |
The first two Chapters are background reading that cover the essentials of health risk, a key concept that must be understood before any risk adjustment or predictive modeling may be performed. Chapter 3 covers claims data in a great deal of detail – probably more detail than the average actuary or analyst is accustomed to.
Chapter 4 and 5 cover two sides of the same issue: if you are going to identify patients or health plan members with a particular condition from claims, how do you do it? You either build an algorithm (Chapter 4) or use a clinical grouper (Chapter 5). Understanding how these grouper and algorithms are constructed is an important component of model building. Chapter 6 discusses in more detail the development of some commonly-encountered models. Chapters 7 through 12 are technical chapters, covering different models.
Chapters 13 through 20 are case studies that cover different predictive modeling and risk adjustment examples, ranging from Medicare and Medicaid through provider profiling and creation of models for different care management uses.
|
