The European Journal of Health Economics

, Volume 16, Issue 2, pp 201–218 | Cite as

Improving the prediction model used in risk equalization: cost and diagnostic information from multiple prior years

  • S. H. C. M. van VeenEmail author
  • R. C. van Kleef
  • W. P. M. M. van de Ven
  • R. C. J. A. van Vliet
Original Paper


Currently-used risk-equalization models do not adequately compensate insurers for predictable differences in individuals’ health care expenses. Consequently, insurers face incentives for risk rating and risk selection, both of which jeopardize affordability of coverage, accessibility to health care, and quality of care. This study explores to what extent the predictive performance of the prediction model used in risk equalization can be improved by using additional administrative information on costs and diagnoses from three prior years. We analyze data from 13.8 million individuals in the Netherlands in the period 2006–2009. First, we show that there is potential for improving models’ predictive performance at both the population and subgroup level by extending them with risk adjusters based on cost and/or diagnostic information from multiple prior years. Second, we show that even these extended models do not adequately compensate insurers. By using these extended models incentives for risk rating and risk selection can be reduced substantially but not removed completely. The extent to which risk-equalization models can be improved in practice may differ across countries, depending on the availability of data, the method chosen to calculate risk-adjusted payments, the value judgment by the regulator about risk factors for which the model should and should not compensate insurers, and the trade-off between risk selection and efficiency.


Competitive health care schemes Health insurance Risk equalization Predictive performance 

JEL Classification

I13 I18 



The authors gratefully acknowledge the Dutch Ministry of Health, Welfare and Sport and the national association of Dutch health insurers (“Zorgverzekeraars Nederland”) for their permission to use administrative data for this study. In addition, we gratefully thank “Statistics Netherlands” (“Centraal Bureau voor Statistiek”) for providing access to the health survey data. For their helpful comments on an earlier draft, we would gratefully thank the members of the Risk Adjustment Network and the two anonymous referees. The opinions in this article are those of the authors and do not necessarily reflect those of the above-mentioned organisations and individuals.


  1. 1.
    Adams, E.K., Bronstein, J.M., Raskind-Hood, C.: Adjusted clinical groups: predictive accuracy for medicaid enrollees in three states. Health Care Financ. Rev. 24, 43–61 (2002)PubMedCentralPubMedGoogle Scholar
  2. 2.
    Ash, A., Porell, F., Gruenberg, L., Sawitz, E., Beiser, A.: Adjusting medicare capitation payments using prior hospitalization data. Health Care Financ. Rev. 10, 17–29 (1989)PubMedCentralPubMedGoogle Scholar
  3. 3.
    Babyak, M.A.: What you see may not be what you get: a brief, nontechnical introduction to overfitting in regression-type models. Psychosom. Med. 66, 411–421 (2004)PubMedGoogle Scholar
  4. 4.
    Barry, C.L., Weiner, J.P., Lemke, K., Busch, S.H.: Risk adjustment in health insurance exchanges for individuals with mental illness. Am. J. Psychiatry 169, 704–709 (2012)CrossRefPubMedGoogle Scholar
  5. 5.
    Basu, A., Manning, W.G.: Issues for the next generation of health care costs analyses. Med. Care 47, S109–S114 (2009)CrossRefPubMedGoogle Scholar
  6. 6.
    Behrend, C., Buchner, F., Happich, M., Holle, R., Reitmeir, P., Wasem, J.: Risk-adjusted capitation payments: how well do principal inpatient diagnosis-based models work in the German situation? Results from a large data set. Eur. J. Health Econ. 8, 31–39 (2007)CrossRefPubMedGoogle Scholar
  7. 7.
    Buntin, M.B., Zaslavsky, A.M.: Too much abo about two-part models and transformation? Comparing methods of modeling medicare expenditures. J. Health Econ. 23, 525–542 (2004)CrossRefPubMedGoogle Scholar
  8. 8.
    Cumming, R.B., Knutson, D., Cameron, B.A., Derrick, B.: Claims-Based Methods of Health Risk Assessment for Commercial Populations. Research Report, Society of Actuaries, Milliman, Minneapolis (2002)Google Scholar
  9. 9.
    DeSlavo, K.B., Jones, T.M., Peabody, J., McDonald, J., Fihn, S., Fan, V., He, J., Muntner, P.: Health care expenditure prediction with a single item, self-rated health measure. Med. Care 47(4), 440–447 (2009)CrossRefGoogle Scholar
  10. 10.
    Duan, N., Manning, W.G., Morris, C.N., Newhouse, J.P.: A comparison of alternative models for the demand for medical care. J. Bus. Econ. Stat. 1(2), 115–126 (1983)Google Scholar
  11. 11.
    Dunn, G., Mirandola, M., Amaddeo, F., Tansella, M.: Describing, explaining or predicting mental health care costs: a guide to regression models: methodological review. Brit. J. Psychiat. 183, 398–404 (2003)CrossRefPubMedGoogle Scholar
  12. 12.
    Fishman, P.A., Goodman, M.J., Hornbook, M.C., Meenan, R.T., Bachman, D.J., O’Keeffe Rosetti, M.C.: Risk adjustment using automated ambulatory pharmacy data: the RxRisk model. Med. Care 41(1), 84–99 (2003)CrossRefPubMedGoogle Scholar
  13. 13.
    Fleishman, J.A., Cohen, J.W., Manning, W.G., Kosinsk, M.: Using the SF-12 health status measure to improve predictions of medical expenditures. Med. Care 44, 54–63 (2006)CrossRefGoogle Scholar
  14. 14.
    Fox, J.: Applied Regression Analysis and Generalized Linear Models. Sage, Thousand Oaks (2008)Google Scholar
  15. 15.
    Garber, A.M., Macurdy, T.E., McClellan, M.B.: Persistence of medicare expenditures among elderly beneficiaries. In: Garber, A.M. (ed.) Frontiers in Health Policy, MIT Press, Cambridge, MA, pp. 153–180 (1998) Google Scholar
  16. 16.
    Gilmer, T., Kronick, R., Fishman, P., Ganiats, T.G.: The medicaid R x model: pharmacy-based risk adjustment for public programs. Med. Care 39(11), 1188–1202 (2001)CrossRefPubMedGoogle Scholar
  17. 17.
    Hughes, J.S., Averill, R.F., Eisenhandler, J., Goldfield, N.I., Muldoon, J., Neff, J.M., Gay, J.C.: Clinical Risk Groups (CRGs): a classification system for risk-adjusted capitation-based payment and health care management. Med. Care 42(1), 81–90 (2004)CrossRefPubMedGoogle Scholar
  18. 18.
    Jones, A.M.: Models for health care. Working paper, University of York. (2010). Accessed 13 June 2013
  19. 19.
    Kronick, R., Gilmer, T., Dreyfus, T., Lee, L.: Improving health-based payment for medicaid beneficiaries: CDPS. Health Care Financ. Rev. 21(3), 29–64 (2000)PubMedCentralPubMedGoogle Scholar
  20. 20.
    Lamers, L.M., van Vliet, R.C.J.A.: Multiyear diagnostic information from prior hospitalizations as a risk-adjuster for capitation payments. Med. Care 34, 549–561 (1996)CrossRefPubMedGoogle Scholar
  21. 21.
    Lamers, L. M.: Capitation payments to competing Dutch sickness funds based on diagnostic information from prior hospitalizations. Ph.D. Dissertation, Erasmus University Rotterdam, Rotterdam (1997)Google Scholar
  22. 22.
    Lamers, L.M.: Health-based risk adjustment: is inpatient and outpatient diagnostic information sufficient? Inquiry 38(4), 423–431 (2001)PubMedGoogle Scholar
  23. 23.
    Lamers, L.M., van Vliet, R.C.J.A.: Health-based risk adjustment improving the pharmacy-based cost group model to reduce gaming possibilities. Euro. J. Health Econ. 4, 107–114 (2003)CrossRefGoogle Scholar
  24. 24.
    Lamers, L.M., van Vliet, R.C.J.A.: The pharmacy-based cost group model: validating and adjusting the classification of medications for chronic conditions to the Dutch situation. Health Policy 68, 113–121 (2004)CrossRefPubMedGoogle Scholar
  25. 25.
    Manning, W.G., Mullahy, J.: Estimating log models: to transform or not to transform? J. Health Econ. 20, 461–494 (2001)CrossRefPubMedGoogle Scholar
  26. 26.
    Manning, W.G., Busa, A., Mullahy, J.: Generalized modelling approaches to risk adjustment of skewed outcomes data. J. Health Econ. 24, 465–488 (2005)CrossRefPubMedGoogle Scholar
  27. 27.
    Monheit, A.C.: Persistence in health expenditures in the short run: prevalence and consequences. Med. Care 41(7), 53–64 (2003)CrossRefGoogle Scholar
  28. 28.
    McIntyre, S.H., Montgomery, D.B., Srinivasan, V., Weitz, B.A.: Evaluating the statistical significance of models developed by stepwise regression. J. Mark. Res. 20, 1–11 (1983)CrossRefGoogle Scholar
  29. 29.
    Mihaylova, B., Briggs, A., O’Hagan, A., Thompson, S.G.: Review of statistical methods for analysing healthcare resources and costs. Health Econ. 20, 879–916 (2011)CrossRefGoogle Scholar
  30. 30.
    Newhouse, J.P.: Reimbursing health plans and health providers: efficiency in production versus selection. J. Econ. Lit. XXXIV, 1236–1263 (1996)Google Scholar
  31. 31.
    Pindyck, R.S., Rubinfeld, D.L.: Econometric models and economic forecasts. McGraw-Hill, New York City (1998)Google Scholar
  32. 32.
    Pope, G.C., Ellis, R.P., Ash, A.S., Liu, C.F., Ayanian, J.Z., Bates, D.W., Burstin, H., Iezzoni, L.I., Ingber, M.J.: Principal inpatient diagnostic cost group model for medicare risk adjustment. Health Care Financ. Rev. 21(3), 93–118 (2000)PubMedCentralPubMedGoogle Scholar
  33. 33.
    Pope, G.C., Kautter, J., Ellis, R.P., Ash, A.S., Ayanian, J.Z., Iezzoni, L.I., Ingber, M.J., Levy, J.M., Robs, J.: Risk adjustment of medicare capitation payments using the CMS-HCC model. Health Care Financ. Rev. 25(4), 119–141 (2004)PubMedCentralPubMedGoogle Scholar
  34. 34.
    Powers, C.A., Meyer, C.M., Roebuck, M.C., Vaziri, B.: Predictive modeling of total healthcare costs using pharmacy claims data. A comparison of alternative econometric cost modeling techniques. Med. Care 43, 1065–1072 (2005)CrossRefPubMedGoogle Scholar
  35. 35.
    Prinsze, F.J., van Vliet, R.C.J.A.: Health-based risk adjustment: improving the pharmacy-based cost group model by adding diagnostic cost groups. Inquiry 44(4), 469–480 (2007)PubMedGoogle Scholar
  36. 36.
    Schokkaert, E., van de Voorde, C.: Risk selection and the specification of the conventional risk adjustment formula. Eur. J. Health Econ. 23, 1237–1259 (2004)CrossRefGoogle Scholar
  37. 37.
    Schokkaert, E., van de Voorde, C.: Incentives for risk selection and omitted variables in the risk adjustment formula. Ann. Econ. Stat. 83(84), 327–351 (2006)Google Scholar
  38. 38.
    Schokkaert, E., van de Voorde, C.: Direct versus indirect standardization in risk adjustment. J. Health Econ. 28, 361–374 (2009)CrossRefPubMedGoogle Scholar
  39. 39.
    Schut, F.T., van de Ven, W.P.M.M.: Uitvoering AWBZ door zorgverzekeraars onverstandig. ESB 95(4591), 486–489 (2010)Google Scholar
  40. 40.
    Stam, P.J.A.: Testing the effectiveness of risk equalization models in health insurance. Ph.D. Dissertation, Erasmus University Rotterdam, Rotterdam (2007)Google Scholar
  41. 41.
    Stam, P.J.A., van de Ven, W.P.M.M.: Risicoverevening in de zorgverzekering: Een evaluatie en oplossingsrichtingen voor verbetering. Research Report, iBMG, Erasmus University Rotterdam, Rotterdam (2006)Google Scholar
  42. 42.
    Stam, P.J.A., van de Ven, W.P.M.M.: De harde kern in risicoverevening. ESB. February, 104-7 (2008)Google Scholar
  43. 43.
    Stam, P.J.A., van Vliet, R.C.J.A., van de Ven, W.P.M.M.: Diagnostic, pharmacy-based, and self-reported health measures in risk equalization models. Med. Care 48, 448–457 (2010)CrossRefPubMedGoogle Scholar
  44. 44.
    Thompson, M.L.: Selection of variables in multiple regression: part 1. a review and evaluation. Int. Stat. Rev. 46, 1–19 (1978)CrossRefGoogle Scholar
  45. 45.
    Veazie, P.J., Manning, W.G., Kane, R.L.: Improving risk adjustment for medicare capitated reimbursement using nonlinear models. Med. Care 41, 741–752 (2003)PubMedGoogle Scholar
  46. 46.
    van Kleef, R.C., van Vliet, R.C.J.A.: Prior use of durable medical equipment as a risk adjuster for health-based capitation. Inquiry 47, 1–16 (2010)Google Scholar
  47. 47.
    van Kleef, R.C., van Vliet, R.C.J.A.: Improving risk equalization using multi-year high cost as a health indicator. Med. Care 50, 140–144 (2012)CrossRefPubMedGoogle Scholar
  48. 48.
    van Kleef, R.C., van Vliet, R.C.J.A., van de Ven, W.P.M.M.: Risicoverevening tussen zorgverzekeraars: Kwantificering modelverbeteringen 1993–2011. TSG 90, 312–326 (2012)CrossRefGoogle Scholar
  49. 49.
    van Kleef, R.C, van Vliet, R.C.J.A., van de Ven, W.P.M.M.: Risicoverevening 2012. Een analyse van voorspelbare winsten en verliezen op subgroep niveau. Research report, iBMG, Erasmus University Rotterdam, Rotterdam (2012)Google Scholar
  50. 50.
    van Kleef, R.C., van Vliet, R.C.J.A., van de Ven, W.P.M.M.: Diagnosis-based cost groups in risk adjustment: The effects of including outpatient diagnoses. Research report, iBMG, Erasmus University Rotterdam, Rotterdam (2012)Google Scholar
  51. 51.
    van de Ven, W.P.M.M., Ellis, R.P.: Risk adjustment in competitive health plan markets. In: Cutler, A., Newhouse, J.P. (eds) Handbook of health economics, pp. 755-845. Elsevier Science B.V., Amsterdam (2000)Google Scholar
  52. 52.
    van de Ven, W.P.M.M., Schut, F.T.: Guaranteed access to affordable coverage in individual health insurance markets. In: Glied, S., Smith, P. (eds.) The Oxford Handbook of Health Economics, pp. 380–404. Oxford University Press, Oxford (2011)Google Scholar
  53. 53.
    van Vliet, R.C.J.A., van de Ven, W.P.M.M.: Towards a capitation formula for competing health insurers: an empirical analysis. Soc. Sci. Med. 34, 1035–1048 (1992)CrossRefPubMedGoogle Scholar
  54. 54.
    van Vliet, R.C.J.A., van de Ven, W.P.M.M.: Capitation payments based on prior hospitalizations. Health Econ. 2, 177–188 (1993)CrossRefPubMedGoogle Scholar
  55. 55.
    Ware Jr, J.E., Kosinski, M., Keller, S.D.: A 12-item short-form health survey: construction of scales and preliminary tests of reliability and validity. Med. Care 34, 220–233 (1996)CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • S. H. C. M. van Veen
    • 1
    Email author
  • R. C. van Kleef
    • 1
  • W. P. M. M. van de Ven
    • 1
  • R. C. J. A. van Vliet
    • 1
  1. 1.Institute Health Policy and ManagementErasmus University RotterdamRotterdamThe Netherlands

Personalised recommendations