Using individualized predictive disease modeling to identify patients with the potential to benefit from a disease management program for diabetes mellitus.

Abstract

Diabetes is an increasing health problem, but efforts to handle this pandemic by disease management programs (DMP) have shown conflicting results. Our hypothesis is that, in addition to a program's content and setting, the choice of the right patients is crucial to a program's efficacy and effectiveness. We used individualized predictive disease modeling (IPDM) on a cohort of 918 patients with type 2 diabetes to identify those patients with the greatest potential to benefit from inclusion in a DMP. A portion of the patients (4.7%) did not have even a theoretical potential for an increase in life expectancy and would therefore be unlikely to benefit from a DMP. Approximately 16.1% had an increase in life expectancy of less than half a year. Stratification of the entire cohort by surrogate parameters like preventable 10-year costs or gain in life expectancy was much more effective than stratification by classical clinical parameters such as high HbA1c level. Preventable costs increased up to 50.6% (or 1,010 per patient (1 = US dollars 1.28), p < 0.01) and life expectancy increased up to 54.8% (or 2.3 years, p < 0.01). IPDM is a valuable strategy to identify those patients with the greatest potential to avoid diabetes-related complications and thus can improve the overall effectiveness and efficacy of DMPs for diabetes mellitus.