Using predictive modeling to evaluate the financial effect of disease management

The objective of this study was to use predictive modeling to evaluate a disease management (DM) program's effect on a chronically ill population. Specifically, diagnostic cost grouping (DCG) predictive modeling was utilized to measure the financial effect of DM in populations of individuals with congestive heart failure and coronary artery disease. The literature of current practices regarding DM's financial effect measurement was reviewed and critiqued--especially with reference to the population-based pre-post method. The time period for the present study is three years, and the variables of interest are financial metrics. Claims data and DM program-specific data covering the 24-month period of 2001 to 2002 and the 24-month period of 2002 to 2003 were analyzed. The mean differences between DCG predicted and actual total claims costs in 2002 and in 2003 were computed. Inflation factors, based on actual health plan population experience for the populations in question, were developed and applied to accurately evaluate financial effect. The preliminary findings suggest that a study design utilizing DCG predictive modeling in evaluating DM program financial impact provides more accurate results compared with the population-based pre-post method currently favored by DM companies.