Abstract
The hierarchical condition category (HCC) risk adjustment model tends to produce over-predictions of health care expenditures for individuals who need less costly services and under-predictions of health care expenditures for those who need costlier services. This tendency leads health plans to effectuate service-level selection to attract profitable individuals and avoid unprofitable individuals. In this study, we propose an alternative model using machine learning (ML) techniques to reduce service-level selection by accounting for demographic and diagnostic characteristics as well as service-level propensity scores (SPS) that capture each individual’s need for each service (the HCC + SPS model). Using the 2013–2014 Truven MarketScan database, we compare the performance of the HCC model (the HCC-only model) and the HCC + SPS model. We first fit both models with ordinary least squares (OLS) because traditional risk adjustment models rely on OLS. We also fit these models with ridge regression, which is a regularized ML algorithm, in order to examine whether the performance of the HCC + SPS model improves when combined with ML techniques. We evaluate prediction performance at three levels: group-level, tail distribution, and individual-level. We find that the HCC + SPS model more accurately estimated health care expenditures when combined with ridge regression, especially for individuals with high expenditures. However, we found limited improvements when the HCC-only model was used with ridge regression or the HCC + SPS model was used with OLS. Our findings suggest that accounting for SPS in risk adjustment using ML has the potential to reduce service-level selection.
Similar content being viewed by others
References
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(7), 704–709 (2012). https://doi.org/10.1176/appi.ajp.2012.11071044
Carey, C.: Technological change and risk adjustment: benefit design incentives in Medicare Part D. Am. Econ. J. Econ. Policy 9(1), 38–73 (2017)
Centers for Medicaid and Medicare Services: 2014 Benefit year risk adjustment SAS version of HHS-developed risk adjustment model algorithm software. In. Centers for medicaid and medicare services, Baltimore, MD (2014)
Einav, L., Finkelstein, A., Kluender, R., Schrimpf, P.: Beyond statistics: the economic content of risk scores. Am. Econ. J. Appl. Econ. 8(2), 195–224 (2016)
Ellis, R.P., McGuire, T.G.: Predictability and predictiveness in health care spending. J. Health Econ. 26(1), 25–48 (2007)
Ellis, R.P., Jiang, S., Kuo, T.-C.: Does service-level spending show evidence of selection across health plan types? Appl. Econ. 45(13), 1701–1712 (2013)
Ellis, R.P., Martins, B., Zhu, W.: Demand elasticities and service selection incentives among competing private health plans. J. Health Econ. 56, 352–367 (2017)
Friedman, J.H.: reedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001)
Friedman, J.H., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 28(2), 337–407 (2000)
Glazer, J., McGuire, T.G.: Optimal risk adjustment in markets with adverse selection: an application to managed care. Am. Econ. Rev. 90(4), 1055–1071 (2000)
Han, T., Lavetti, K.: Does part D abet advantageous selection in medicare advantage? J. Health Econ. 56, 368–382 (2017)
Irvin, J.A., Kondrich, A.A., Ko, M., Rajpurkar, P., Haghgoo, B., Landon, B.E., Phillips, R.L., Petterson, S., Ng, A.Y., Basu, S.: Incorporating machine learning and social determinants of health indicators into prospective risk adjustment for health plan payments. BMC Public Health 20(1), 608 (2020). https://doi.org/10.1186/s12889-020-08735-0
Jones, A.M., Lomas, J., Rice, N.: Healthcare cost regressions: going beyond the mean to estimate the full distribution. Health Econ. 24(9), 1192–1212 (2015)
Jones, A.M., Lomas, J., Moore, P.T., Rice, N.: A quasi-Monte-Carlo comparison of parametric and semiparametric regression methods for heavy-tailed and non-normal data: an application to healthcare costs. J. R. Stat. Soc. Ser. A Stat. Soc. 179(4), 951–974 (2016). https://doi.org/10.1111/rssa.12141
Kan, H.J., Kharrazi, H., Chang, H.Y., Bodycombe, D., Lemke, K., Weiner, J.P.: Exploring the use of machine learning for risk adjustment: a comparison of standard and penalized linear regression models in predicting health care costs in older adults. PLoS ONE 14(3), e0213258 (2019). https://doi.org/10.1371/journal.pone.0213258
Kautter, J., Pope, G.C., Ingber, M., Freeman, S., Patterson, L.: The HHS-HCC risk adjustment model for individual and small group markets under the affordable care act. Medicare Medicaid Res. Rev. 4(3), E1–E46 (2014)
Lavetti, K., Simon, K.: Strategic formulary design in Medicare Part D plans. Am. Econ. J. Econ. Policy 10(3), 154–192 (2018)
Layton, T.J., McGuire, T.G., van Kleef, R.C.: Deriving risk adjustment payment weights to maximize efficiency of health insurance markets. J. Health Econ. 61, 93–110 (2018). https://doi.org/10.1016/j.jhealeco.2018.07.001
Lissenden, B.: The effect of cancer diagnosis on switching health insurance in medicare. Health Econ. 28(3), 339–349 (2019). https://doi.org/10.1002/hec.3843
Marquardt, D.W., Snee, R.D.: Ridge regression in practice. Am. Stat. 29(1), 3–20 (1975)
McGuire, T.G., Newhouse, J.P., Normand, S.-L., Shi, J., Zuvekase, S.: Assessing incentives for service-level selection in private health insurance exchanges. J. Health Econ. 35(1), 47–63 (2014)
Medicare Payment Advisory Commission: Report to the congress: medicare payment policy. In. Medicare payment advisory commission, Washington, DC (2011)
Medicare Payment Advisory Commission: Report to the congress: medicare and the health care delivery system. In. Medicare payment advisory commission, Washington, DC (2012)
Medicare Payment Advisory Commission: Report to the congress: medicare and the health care delivery system. In. Medicare payment advisory commission, Washington, DC (2014)
Meyers, D.J., Belanger, E., Joyce, N., McHugh, J., Rahman, M., Mor, V.: Analysis of drivers of disenrollment and plan switching among medicare advantage beneficiaries. JAMA Int. Med. 179(4), 524–532 (2019). https://doi.org/10.1001/jamainternmed.2018.7639
Montz, E., Layton, T., Busch, A.B., Ellis, R.P., Rose, S., McGuire, T.G.: Risk-adjustment simulation: plans may have incentives to distort mental health and substance use coverage. Health Aff. (Project Hope) 35(6), 1022–1028 (2016). https://doi.org/10.1377/hlthaff.2015.1668
Park, S., Basu, A.: Alternative evaluation metrics for risk adjustment methods. Health Econ. 27(6), 984–1010 (2018). https://doi.org/10.1002/hec.3657
Park, S., Basu, A., Coe, N.B., Khalil, F.: Service-level selection: strategic risk selection in medicare advantage in response to risk adjustment. NBER Working Paper No. 24038 (2017)
Park, S., Fishman, P., White, L., Larson, E.B., Coe, N.B.: Disease-specific plan switching between traditional medicare and medicare advantage. Perm. J. 24, 19.059 (2019)
Park, S., Meyers, D.J., Langellier, B.A.: Rural enrollees in Medicare Advantage have substantial rates of switching to traditional Medicare. Health Aff. (Project Hope) (Forthcoming)
Pope, G.C., Kautter, J., Ellis, R.P., Ash, A.S., Ayanian, J.Z., Iezzoni, L.I., Ingber, M.J., Levy, J.M., Robst, J.: Risk adjustment of medicare capitation payments using the CMS-HCC model. Health Care Financ. Rev. 25(4), 119–141 (2004)
Pope, G.C., Kautter, J., Ingber, J.M., Freeman, S., Sekar, R., Newhart, C.: Evaluation of the CMS-HCC risk adjustment model. In: RTI international research triangle park, NC (2011)
Rahman, M., Laura, K., Trivedi, A.N., Mor, V.: High-cost patients had substantial rates of leaving medicare advantage and joining Traditional Medicare. Health Aff. (Project Hope) 34(10), 1675–1681 (2015)
Rose, S., Bergquist, S.L., Layton, T.J.: Computational health economics for identification of unprofitable health care enrollees. Biostatistics 18(4), 682–694 (2017). https://doi.org/10.1093/biostatistics/kxx012
Shrestha, A., Bergquist, S., Montz, E., Rose, S.: Mental health risk adjustment with clinical categories and machine learning. Health Serv. Res. (2017). https://doi.org/10.1111/1475-6773.12818
Stuart, E.A.: Matching methods for causal inference: a review and a look forward. Stat. Sci. 25(1), 1–21 (2010). https://doi.org/10.1214/09-STS313
Weiner, J.P., Trish, E., Abrams, C., Lemke, K.: Adjusting for risk selection in state health insurance exchanges will be critically important and feasible But Not Easy. Health Aff. (Project Hope) 31(2), 306–315 (2012). https://doi.org/10.1377/hlthaff.2011.0420
Acknowledgements
We would like to thank Sherri Rose and James Lomas for providing expert support in statistical software and related documentation.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by SP. The first draft of the manuscript was written by SP and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Park, S., Basu, A. Improving risk adjustment with machine learning: accounting for service-level propensity scores to reduce service-level selection. Health Serv Outcomes Res Method 21, 363–388 (2021). https://doi.org/10.1007/s10742-020-00239-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10742-020-00239-z