Statistical Prediction of High-Cost Claimants Using Commercial Health Plan Data

  • Amy Z. Cao
  • Liana DesHarnais CastelEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 69)


Among Cigna’s claimant population with at least one year of continuous medical or pharmacy eligibility over 2014–2015 (N = 2.7 million), our objective was to accurately identify high-cost claimants and identify clinical and demographic cost drivers among individuals with commercial health plan benefits. High-cost claimants were defined as those with annual costs over $100,000. We collected 800+ potential risk factors and utilized multivariable weighted logistic regression on an oversampled model dataset to estimate odds ratios for clinical and demographic factors available in claims data. We used decision tree methodology to assist in variable selection/reduction. High-cost claimants (n = 17,702) comprised only 0.6% of the 2015–2016 population, but accounted for over 20% of 2015–2016 total costs. Our optimized maximum likelihood estimation model identified cost drivers including: actuarial prospective episode-related group (ERG) risk score, prior-year medical claim costs, prior-year pharmacy claim costs, gaps in care/noncompliance score, hemophilia, short stature, and end-stage renal disease. Our findings show that weighted logistic regression modeling with oversampling techniques can be used to identify high-cost claimants in the upcoming year more accurately than traditional maximum likelihood estimation. Managed care decision makers should use prospective claims data analyses to target and implement intervention programs, with the goal of managing care among those at risk for incurring catastrophic costs.


Data science Rare event statistical prediction Managed care administration 



The authors gratefully acknowledge the technical and editorial assistance provided by Jeffrey Young, MS, Janki S. Bhatt, PhD, Stuart Lustig, MD, Joshua Barrett, MS, Jeanne Fox, BNS, Qun Wang, PhD, Nick Tschaika, BS and Lillian Thomas, BS.


  1. 1.
    Keehan, S.P., Stone, D.A., Poisal, J.A., Cuckler, G.A., Sisko, A.M., Smith, S.D., et al.: National health expenditure projections, 2016-25: price increases, aging push sector to 20 percent of economy. Health Aff. (Millwood) 36, 553–563 (2017)CrossRefGoogle Scholar
  2. 2.
    Thorpe, K.E., Ogden, L.L., Galactionova, K.: Chronic conditions account for rise in medicare spending from 1987 to 2006. Health Aff. (Millwood) 29, 718–724 (2010)CrossRefGoogle Scholar
  3. 3.
    Wilson, D.M., Troy, T.D., Jones, K.L.: American Health Policy Institute: High Cost Claimants: Private vs. Public Sector Approaches (2016)Google Scholar
  4. 4.
    Joynt, K.E., Figueroa, J.F., Beaulieu, N., Wild, R.C., Orav, E.J., Jha, A.K.: Segmenting high-cost medicare patients into potentially actionable cohorts. Healthc. (Amst) 5, 62–67 (2017)CrossRefGoogle Scholar
  5. 5.
    Figueroa, J.F., Joynt Maddox, K.E., Beaulieu, N., Wild, R.C., Jha, A.K.: Concentration of potentially preventable spending among high-cost medicare subpopulations: an observational study. Ann. Intern. Med. 167, 706–713 (2017)CrossRefGoogle Scholar
  6. 6.
    United States Census Bureau: Health Insurance Coverage in the United States: 2015, Report P60-257 (2016)Google Scholar
  7. 7.
    King, G., Zeng, L.: Logistic regression in rare events data. Polit. Anal. 9, 137–163 (2001)CrossRefGoogle Scholar
  8. 8.
    Charlson, M., Wells, M.T., Ullman, R., King, F., Shmukler, C.: The Charlson comorbidity index can be used prospectively to identify patients who will incur high future costs. PLoS ONE 9, e112479 (2014)CrossRefGoogle Scholar
  9. 9.
    Charlson, M.E., Pompei, P., Ales, K.L., MacKenzie, C.R.: A new method of classifying prognostic comorbidity in longitudinal studies: development and validation. J. Chronic Dis. 40, 373–383 (1987)CrossRefGoogle Scholar
  10. 10.
    Optum Insight: Symmetry Episode Treatment Groups: Measuring Health Care with Meaningful Episodes of Care. White Paper (2012).
  11. 11.
    Sun Life Financial: Third Annual Sun Life Stop-Loss Research Report, Spring 2015. Stop Loss Insurance Brokers, Ltd. Accessed 24 Apr 2018
  12. 12.
    Figueroa, J.F., Frakt, A.B., Lyon, Z.M., Zhou, X., Jha, A.K.: Characteristics and spending patterns of high cost, non-elderly adults in Massachusetts. Healthc. (Amst) 5, 165–170 (2017)CrossRefGoogle Scholar
  13. 13.
    Robinson, T.N., Wu, D.S., Stiegmann, G.V., Moss, M.: Frailty predicts increased hospital and six-month healthcare cost following colorectal surgery in older adults. Am. J. Surg. 202, 511–514 (2011)CrossRefGoogle Scholar
  14. 14.
    Shugarman, L.R., Campbell, D.E., Bird, C.E., Gabel, J., Louis, T.A., Lynn, J.: Differences in medicare expenditures during the last 3 years of life. J. Gen. Intern. Med. 19, 127–135 (2004)CrossRefGoogle Scholar
  15. 15.
    Figueroa, J.F., Tsugawa, Y., Zheng, J., Orav, E.J., Jha, A.K.: Association between the value-based purchasing pay for performance program and patient mortality in US hospitals: observational study. BMJ 353, i2214 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Cigna Health and Life Insurance CompanyBloomfieldUSA
  2. 2.Lundy-Fetterman School of BusinessCampbell UniversityBuies CreekUSA

Personalised recommendations