Skip to main content
SpringerLink
Log in

Who determines United States Healthcare out-of-pocket costs? Factor ranking and selection using ensemble learning

  • Research
  • Published:
Health Information Science and Systems Aims and scope Submit manuscript

Abstract

Purpose

Healthcare out-of-pocket (OOP) costs consist of the annual expenses paid by individuals or families that are not reimbursed by insurance. In the U.S, broadening healthcare disparities are caused by the rapid increase in OOP costs. With a precise forecast of the OOP costs, governments can improve the design of healthcare policies to better control the OOP costs. This study designs a purely data-driven ensemble learning procedure to achieve a collection of factors that best predict OOP costs.

Methods

We propose a voting ensemble learning procedure to rank and select factors of OOP costs based on the Medical Expenditure Panel Survey dataset. The method involves utilizing votes from the base learners forward subset selection, backward subset selection, random forest, and LASSO.

Results

The top-ranking factors selected by our proposed method are insurance type, age, asthma, family size, race, and number of physician office visits. The predictive models using these factors outperform the models that employ the factors commonly considered by the literature through improving the prediction error (test MSE of the OOP costs’ log-odds) from 0.462 to 0.382.

Conclusion

Our results indicate a set of factors which best explain the OOP costs behavior based on a purely data-driven solution. These findings contribute to the discussions regarding demand-side needs for containing rapidly rising OOP costs. Instead of estimating the impact of a single factor on OOP costs, our proposed method allows for the selection of arbitrary-sized factors to best explain OOP costs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. https://github.com/health-care-cost-data-analysis/factor-ranking-and-selection.

  2. http://www.meps.ahrq.gov/.

  3. http://meps.ahrq.gov/mepsweb/data_stats/download_data/pufs/h129/h129doc.shtml.

  4. https://github.com/health-care-cost-data-analysis/factor-ranking-and-selection/blob/master/MEPS_data.csv.

  5. The analyzer is available as a Python library through the PyPi server: https://phik.readthedocs.io/en/latest/.

  6. One can calculate the increment of probability through \(1-\frac{1}{1+e^{\Delta l}p_0/(1-p_0)}-p_0,\) given the corresponding base probability \(p_0\) and the increment of log-odds \(\Delta l\).

References

  1. Out-of-pocket spending. Peterson-KFF Health System Tracker. 2017. https://www.healthsystemtracker.org/indicator/access-affordability/out-of-pocket-spending/.

  2. Ubel PA, Abernethy AP, Yousuf Zafar S. Full disclosure–out-of-pocket costs as side effects. New Engl J Med. 2013;369(16):1484. https://doi.org/10.1056/NEJMp1306826.

    Article  Google Scholar 

  3. Finkelstein EA, Tangka FK, Trogdon JG, Sabatino SA, Richardson LC. Cancer treatment cost in the United States: has the burden shifted over time? Am J Manag C. 2009;15(11):801.

    Google Scholar 

  4. Baird K. High out-of-pocket medical spending. among the poor and elderly in nine developed countries. Health Serv Res. 2016;51(4):1467. https://doi.org/10.1111/1475-6773.12444.

    Article  Google Scholar 

  5. Gwet P, Machlin SR. Out-of-pocket health care Expenses for non-elderly families by income and family structure, 2015. In: Statistical Brief (Medical Expenditure Panel Survey (US)). 2018

  6. Kim NH, Look KA. Effects of the Affordable Care Act’s contraceptive coverage requirement on the utilization and out-of-pocket costs of prescribed oral contraceptives. Res Social Adm Pharm. 2018;14(5):479. https://doi.org/10.1016/j.sapharm.2017.06.005.

    Article  Google Scholar 

  7. Kang HA, Barner JC. The relationship between out-of-pocket healthcare expenditures and insurance status among individuals with chronic obstructive pulmonary disease. J Pharm Health Serv Res. 2017;8(2):107. https://doi.org/10.1111/jphs.12170.

    Article  Google Scholar 

  8. Soni A. Out-of-pocket expenditures for adults with health care expenses for multiple chronic conditions, U.S. Civilian Noninstitutionalized Population, 2014. Statistical Brief (Medical Expenditure Panel Survey (US)). 2017. https://meps.ahrq.gov/data_files/publications/st498/stat498.shtml.

  9. Hwang W, Weller W, Ireys H, Anderson G. Out-of-pocket medical spending for care of chronic conditions. Health Affairs. 2001;20(6):267. https://doi.org/10.1377/hlthaff.20.6.267.

    Article  Google Scholar 

  10. Paez KA, Zhao L, Hwang W. Rising out-of-pocket spending for chronic conditions: a ten-year trend. Health Affairs. 2009;28(1):15. https://doi.org/10.1377/hlthaff.28.1.15.

    Article  Google Scholar 

  11. Hoffman C, Rice D, Sung HY. Persons with chronic conditions. Their prevalence and costs. JAMA. 1996;276(18):1473. https://doi.org/10.1001/jama.1996.03540180029029.

    Article  Google Scholar 

  12. Carrier E, Cunningham P. Medical cost burdens among nonelderly adults with asthma. Am J Manag C. 2014;20(11):925.

    Google Scholar 

  13. Rodbard HW, Green AJ, Fox KM, S. Grandy for the SHIELD Study Group. Impact of type 2 diabetes mellitus on prescription medication burden and out-of-pocket healthcare expenses. Diabetes Res Clin Pr. 2010;87(3):360. https://doi.org/10.1016/j.diabres.2009.11.021.

    Article  Google Scholar 

  14. Opitz D, Maclin R. Popular ensemble methods: an empirical study. J Artif Intell Res. 1999;11:169. https://doi.org/10.1613/jair.614.

    Article  MATH  Google Scholar 

  15. Friedman J, Hastie T, Tibshirani R. The elements of statistical learning, vol. 1. New York: Springer; 2001.

    MATH  Google Scholar 

  16. Ho TK. Random decision forests. In: Proceedings of 3rd international conference on document analysis and recognition. 1995;1:278. https://doi.org/10.1109/ICDAR.1995.598994

  17. Cohen JW, Cohen SB, Banthin JS. The medical expenditure panel survey: a national information resource to support healthcare cost research and inform policy and practice. Med Care. 2009;47(7):S44. https://doi.org/10.1097/mlr.0b013e3181a23e3a.

    Article  Google Scholar 

  18. Cohen JW, Cohen SB, Banthin JS, The medical expenditure panel survey: a national information resource to support healthcare cost research and inform policy and practice. Medical care. 2009;47(7 Suppl 1):S44. https://doi.org/10.1097/MLR.0b013e3181a23e3a

    Article  Google Scholar 

  19. Cylus J, Hartman M, Washington B, Andrews K, Catlin A. Pronounced gender and age differences are evident in personal health care spending per person. Health Affairs. 2010;30(1):153. https://doi.org/10.1377/hlthaff.2010.0216.

    Article  Google Scholar 

  20. Cook BL, Manning WG. Measuring racial/ethnic disparities across the distribution of health care expenditures. Health Serv Res. 2009;44(5p1):1603.

    Article  Google Scholar 

  21. Derose PK, Bahney BW, Lurie N, Escarce JJ. Review: immigrants and health care access, quality, and cost. Med Care Res Rev. 2009;66(4):355. https://doi.org/10.1177/1077558708330425.

    Article  Google Scholar 

  22. Liu S, Chollet D. Price and income elasticity of the demand for health insurance and health care services: a critical review of the literature. Mathematica Policy Research. 2006.

  23. Smith-Spangler CM, Bhattacharya J, Goldhaber-Fiebert JD. Diabetes, its treatment, and catastrophic medical spending in 35 developing countries. Diabetes Care. 2012;35(2):319. https://doi.org/10.2337/dc11-1770.

    Article  Google Scholar 

  24. Einav L, Finkelstein A. Moral hazard in health insurance: what we know and how we know it. J Euro Econ Assoc. 2018;16(4):957. https://doi.org/10.1093/jeea/jvy017.

    Article  Google Scholar 

  25. Ashman JJ, Rui P, Okeyode T. Characteristics of office-based physician visits, 2016. NCHS Data Brief (CDC Stacks). 2019. https://stacks.cdc.gov/view/cdc/62369.

  26. Baak M, Koopman R, Snoek HL, Klous S. A new correlation coefficient between categorical, ordinal and interval variables with Pearson characteristics. Comput Stat Data Anal. 2020;152:107043. https://doi.org/10.1016/j.csda.2020.107043.

    Article  MathSciNet  MATH  Google Scholar 

  27. Huh M. The relationships between cognitive function and hearing loss among the elderly. J Phys Ther Sci. 2018;30(1):174. https://doi.org/10.1589/jpts.30.174.

    Article  Google Scholar 

  28. Hébert R. Functional decline in old age. CMAJ. 1997;157(8):1037.

    Google Scholar 

  29. Long AN, Dagogo-Jack S. Comorbidities of diabetes and hypertension: mechanisms and approach to target organ protection. J Clin Hypertens. 2011;13(4):244. https://doi.org/10.1111/j.1751-7176.2011.00434.x.

    Article  Google Scholar 

  30. Visscher TL, Seidell JC. The public health impact of obesity. Annu Rev Publ Health. 2001;22(1):355. https://doi.org/10.1146/annurev.publhealth.22.1.355.

    Article  Google Scholar 

  31. Hastie TJ, Tibshirani RJ. Generalized additive models, vol. 43. New York: CRC Press; 1990.

    MATH  Google Scholar 

  32. Kominski GF, Rasmussen PW, Zhang C, Hassan S, Freund D. Ten years of the Affordable Care Act: Major gains and ongoing disparities. UCLA Center for Health Policy Research. 2020. http://healthpolicy.ucla.edu/publications/search/pages/detail.aspx?PubID=1930.

  33. Waidmann T. Estimating the cost of racial and ethnic health disparities. Washington, DC: Urban Institute; 2009.

    Google Scholar 

  34. Jacobs EA, Karavolos K, Rathouz PJ, Ferris TG, Powell LH. Limited English proficiency and breast and cervical cancer screening in a multiethnic population. Am J Public Health. 2005;95(8):1410.

    Article  Google Scholar 

  35. Harlan LC, Bernstein AB, Kessler LG. Cervical cancer screening: who is not screened and why? Am J Public Health. 1991;81(7):885. https://doi.org/10.2105/AJPH.81.7.885.

    Article  Google Scholar 

  36. Hu DJ, Covell RM. Health care usage by Hispanic outpatients as function of primary language. Western J Med. 1986;144(4):490.

    Google Scholar 

  37. Cheng EM, Chen A, Cunningham W. Primary language and receipt of recommended health care among Hispanics in the United States. J Gen Intern Med. 2007;22(Suppl 2):283.

    Article  Google Scholar 

  38. Planned knee and hip replacement surgeries are on the rise in the us. Blue Cross Blue Shield, Chicago. 2019. https://www.bcbs.com/the-health-of-america/reports/planned-knee-and-hip-replacement-surgeries-are-the-rise-the-us.

  39. Barnes PM, Bloom B, Nahin RL. Complementary and alternative medicine use among adults and children; United States, 2007. National Health Statistics Report (CDC). 2008. https://stacks.cdc.gov/view/cdc/5266.

  40. Nahin RL, Stussman BJ, Herman PM. Out-of-pocket expenditures on complementary health approaches associated with painful health conditions in a nationally representative adult sample. J Pain. 2015;16(11):1147. https://doi.org/10.1016/j.jpain.2015.07.013.

    Article  Google Scholar 

  41. Seuring T, Archangelidi O, Suhrcke M. The economic costs of type 2 diabetes: a global systematic review. Pharmacoeconomics. 2015;33(8):811. https://doi.org/10.1007/s40273-015-0268-9.

    Article  Google Scholar 

  42. Karaca-Mandic P, Jena AB, Joyce GF, Goldman DP. Out-of-pocket medication costs and use of medications and health care services among children with asthma. JAMA. 2012;307(12):1284. https://doi.org/10.1001/jama.2012.340.

    Article  Google Scholar 

  43. Genuer R, Poggi JM, Tuleau-Malot C. Variable selection using random forests. Pattern Recog Lett. 2010;31(14):2225. https://doi.org/10.1016/j.patrec.2010.03.014.

    Article  Google Scholar 

  44. Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc: Series B (Methodological). 1996;58(1):267. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x.

    Article  MathSciNet  MATH  Google Scholar 

  45. Breiman L. Manual on setting up, using, and understanding random forests v3. 1. Statistics Department University of California Berkeley. CA, USA. 2002;1:58. 

  46. Yu H, Dick AW, Szilagyi PG. Does public insurance provide better financial protection against rising health care costs for families of children with special health care needs? Med Care. 2008;46(10):1064. https://doi.org/10.1097/MLR.0b013e318185cdf2.

    Article  Google Scholar 

  47. Shen C. Determinants of health care decisions: insurance, utilization, and expenditures. Rev Econ Stat. 2013;95(1):142. https://doi.org/10.1162/REST_a_00232.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Claremont Graduate University, Department of Economic Sciences, 150 E. 10th Street, California, Claremont, USA

    Chengcheng Zhang, Yujia Ding & Qidi Peng

  2. Claremont Graduate University, Institute of Mathematical Sciences, 150 E. 10th Street, California, Claremont, USA

    Yujia Ding & Qidi Peng

Authors
  1. Chengcheng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yujia Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qidi Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chengcheng Zhang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, C., Ding, Y. & Peng, Q. Who determines United States Healthcare out-of-pocket costs? Factor ranking and selection using ensemble learning. Health Inf Sci Syst 9, 22 (2021). https://doi.org/10.1007/s13755-021-00153-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13755-021-00153-9

Keywords

Mathematics Subject Classification

Search

Navigation