Predictive Modeling of Total Healthcare Costs Using Pharmacy Claims Data

OBJECTIVE: We sought to evaluate several statistical modeling approaches in predicting prospective total annual health costs (medical plus pharmacy) of health plan participants using Pharmacy Health Dimensions (PHD), a pharmacy claims-based risk index. METHODS: We undertook a 2-year (baseline year/follow-up year) longitudinal analysis of integrated medical and pharmacy claims. Included were plan participants younger than 65 years of age with continuous medical and pharmacy coverage (n = 344,832). PHD drug categories, age, gender, and pharmacy costs were derived across the baseline year. Annual total health costs were calculated for each plan participant in follow-up year. Models examined included ordinary least squares (OLS) regression, log-transformed OLS regression with smearing estimator, and 3 two-part models using OLS regression, log-OLS regression with smearing estimator, and generalized linear modeling (GLM), respectively. A 10% random sample was withheld for model validation, which was assessed via adjusted r, mean absolute prediction error, specificity, and positive predictive value. RESULTS: Most PHD drug categories were significant independent predictors of total costs. Among models tested, the OLS model had the lowest mean absolute prediction error and highest adjusted r. The log-OLS and 2-part log-OLS models did not predict costs accurately as the result of issues of log-scale heteroscedasticity. The 2-part model using GLM had lower adjusted r but similar performance in other assessment measures compared with the OLS or 2-part OLS models. CONCLUSION: The PHD system derived solely from pharmacy claims data can be used to predict future total health costs. Using PHD with a simple OLS model may provide similar predictive accuracy in comparison to more advanced econometric models

Econometrics · Economics · Family medicine · Health care · Heteroscedasticity · Linear regression · Ordinary least squares · Predictive modelling · Regression analysis · Statistics · Chronic Disease Management Strategies · Demography · Health Systems, Economic Evaluations, Quality of Life · Mathematics · Medication Adherence and Compliance · Medicine · Pharmacy

• Risk Adjustment for Health Care Financing in Chronic Disease

  Theodore A Omachi, Steven E Gregorich et al.•Medical Care•2013

  Añadir item

• Predicting Healthcare Utilization Using a Pharmacy-based Metric With the WHO’s Anatomic Therapeutic Chemical Algorithm

  Raymond N Kuo, Yaa-Hui Dong et al.•Medical Care•2011

  Añadir item

• Longitudinal Patterns of Spending Enhance the Ability to Predict Costly Patients

  Julie C Lauffenburger, Jessica M Franklin et al.•Medical Care•2017

  Añadir item

• Mothers of Children Diagnosed With Attention-Deficit/Hyperactivity Disorder

  G Thomas Ray, Lisa A Croen et al.•Medical Care•2009

  Añadir item

• A Simple Test for Heteroscedasticity and Random Coefficient Variation

  Trevor Breusch, T S Breusch et al.•Econometrica•1979

  Añadir item

• Diagnostics for heteroscedasticity in regression

  R Dennis Cook, Sanford Weisberg•Biometrika•1983

  Añadir item

• Smearing Estimate

  Naihua Duan•Journal of the American…•1983

  Añadir item

• Much ado about two

  Open Access•John Mullahy•Journal of Health Economics•1998

  Añadir item

• Too much ado about two-part models and transformation?

  Open Access•Melinda Beeuwkes Buntin, Alan M Zaslavsky•Journal of Health Economics•2004

  Añadir item

• Estimating log models

  Open Access•Willard G Manning, John Mullahy•Journal of Health Economics•2001

  Añadir item

• The logged dependent variable, heteroscedasticity, and the retransformation problem

  Open Access•Willard G Manning•Journal of Health Economics•1998

  Añadir item

• Predicting Costs of Care Using a Pharmacy-Based Measure Risk Adjustment in a Veteran Population

  Anne E Sales, Chuan-Fen Liu et al.•Medical Care•2003

  Añadir item

• Construction and Characteristics of the RxRisk-V

  Kevin L Sloan, Anne E Sales et al.•Medical Care•2003

  Añadir item

• Improving Risk Adjustment for Medicare Capitated Reimbursement Using Nonlinear Models

  Peter J Veazie, Willard G Manning et al.•Medical Care•2003

  Añadir item

• Development and Estimation of a Pediatric Chronic Disease Score Using Automated Pharmacy Data

  Paul Fishman, Paul A Fishman et al.•Medical Care•1999

  Añadir item

• The Medicaid Rx Model

  Todd Gilmer, Richard Kronick et al.•Medical Care•2001

  Añadir item

• Risk Adjustment Using Automated Ambulatory Pharmacy Data

  Paul Fishman, Paul A Fishman et al.•Medical Care•2003

  Añadir item

• A Chronic Disease Score with Empirically Derived Weights

  Daniel O Clark, MICHAEL VON KORFF et al.•Medical Care•1995

  Añadir item

• Pharmacy Costs Groups

  Leida M Lamers•Medical Care•1999

  Añadir item