OBJECTIVE: To contrast the advantages and limitations of using medication, diagnostic, and cost data to prospectively identify candidates for care management programs. METHODS: Risk scores from prior-cost information and a set of clinically based predictive models (PMs) derived from diagnostic and medication data sources, as well as from a combination of all 3 data sources, were assigned to a national sample of commercially insured, non-elderly adults (n = 2,259,584). Clinical relevance of risk groups and statistical performance using future costs as the outcome were contrasted across the PMs. RESULTS: Compared with prior cost, diagnostic and medication-based PMs identified high-risk groups with a higher burden of clinically actionable characteristics. Statistical performance was similar and in some cases better for the clinical PMs compared with prior cost. The best classification accuracy was obtained with a comprehensive model that united diagnostic, medication, and prior-cost risk factors. CONCLUSIONS: Clinically based PMs are a better choice than prior cost alone for programs that seek to identify high-risk groups of patients who are amenable to care management services.
OBJECTIVE: To contrast the advantages and limitations of using medication, diagnostic, and cost data to prospectively identify candidates for care management programs. METHODS: Risk scores from prior-cost information and a set of clinically based predictive models (PMs) derived from diagnostic and medication data sources, as well as from a combination of all 3 data sources, were assigned to a national sample of commercially insured, non-elderly adults (n = 2,259,584). Clinical relevance of risk groups and statistical performance using future costs as the outcome were contrasted across the PMs. RESULTS: Compared with prior cost, diagnostic and medication-based PMs identified high-risk groups with a higher burden of clinically actionable characteristics. Statistical performance was similar and in some cases better for the clinical PMs compared with prior cost. The best classification accuracy was obtained with a comprehensive model that united diagnostic, medication, and prior-cost risk factors. CONCLUSIONS: Clinically based PMs are a better choice than prior cost alone for programs that seek to identify high-risk groups of patients who are amenable to care management services.
Authors: Peter J Fagan; Alyson B Schuster; Cynthia Boyd; Jill A Marsteller; Michael Griswold; Shannon M E Murphy; Linda Dunbar; Christopher B Forrest Journal: Health Serv Res Date: 2010-09-17 Impact factor: 3.402
Authors: Tobias Freund; Michel Wensing; Stefan Geissler; Frank Peters-Klimm; Cornelia Mahler; Cynthia M Boyd; Joachim Szecsenyi Journal: Am J Manag Care Date: 2012-04-01 Impact factor: 2.229
Authors: Amaia Calderón-Larrañaga; Chad Abrams; Beatriz Poblador-Plou; Jonathan P Weiner; Alexandra Prados-Torres Journal: BMC Health Serv Res Date: 2010-01-21 Impact factor: 2.655