07.12.12

Exploring Robust Methods for Evaluating Treatment and Comparison Groups in Chronic Care Management Programs

Published in Population Health Management

Author(s): Aaron R. Wells, PhD; Brent Hamar, DDS, MPH; Chastity Bradley, PhD; William M. Gandy, EdD; Patricia L. Harrison, MPH; James A. Sidney, MA; Carter R. Coberley, PhD; Elizabeth Y. Rula, PhD; and James E. Pope, MD

Evaluation of chronic care management (CCM) programs is necessary to determine the behavioral, clinical, and financial value of the programs. Financial outcomes of members who are exposed to interventions (treatment group) typically are compared to those not exposed (comparison group) in a quasi-experimental study design. However, because member assignment is not randomized, outcomes reported from these designs may be biased or inefficient if study groups are not comparable or balanced prior to analysis. Two matching techniques used to achieve balanced groups are Propensity Score Matching (PSM) and Coarsened Exact Matching (CEM). Unlike PSM, CEM has been shown to yield estimates of causal (program) effects that are lowest in variance and bias for any given sample size. The objective of this case study was to provide a comprehensive comparison of these 2 matching methods within an evaluation of a CCM program administered to a large health plan during a 2-year time period. Descriptive and statistical methods were used to assess the level of balance between comparison and treatment members pre matching. Compared with PSM, CEM retained more members, achieved better balance between matched members, and resulted in a statistically insignificant Wald test statistic for group aggregation. In terms of program performance, the results showed an overall higher medical cost savings among treatment members matched using CEM compared with those matched using PSM (-$25.57 versus -$19.78, respectively). Collectively, the results suggest CEM is a viable alternative, if not the most appropriate matching method, to apply when evaluating CCM program performance.

Key Takeaways:

  • Two statistical methods, both using comparison groups, evaluated chronic care management programs.
  • Both methods found significant savings, but the newer CEM method provided a more accurate measurement of savings.
  • CEM provides objective parameters to assess the overall quality of matched groups, contributing to a more balanced comparative outcomes analysis.
Read Article