Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep;25(7):1117-1131.
doi: 10.1007/s10198-023-01656-w. Epub 2024 Jan 3.

Risk adjustment for regional healthcare funding allocations with ensemble methods: an empirical study and interpretation

Tuukka Holster  1 , Shaoxiong Ji  2   3 , Pekka Marttinen  2   3
Affiliations

Risk adjustment for regional healthcare funding allocations with ensemble methods: an empirical study and interpretation

Tuukka Holster et al. Eur J Health Econ. 2024 Sep.

Abstract

We experiment with recent ensemble machine learning methods in estimating healthcare costs, utilizing Finnish data containing rich individual-level information on healthcare costs, socioeconomic status and diagnostic data from multiple registries. Our data are a random 10% sample (553,675 observations) from the Finnish population in 2017. Using annual healthcare cost in 2017 as a response variable, we compare the performance of Random forest, Gradient Boosting Machine (GBM) and eXtreme Gradient Boosting (XGBoost) to linear regression. As machine learning methods are often seen as unsuitable in risk adjustment applications because of their relative opaqueness, we also introduce visualizations from the machine learning literature to help interpret the contribution of individual variables to the prediction. Our results show that ensemble machine learning methods can improve predictive performance, with all of them significantly outperforming linear regression, and that a certain level of interpretation can be provided for them. We also find individual-level socioeconomic variables to improve prediction accuracy and that their effect is larger for machine learning methods. However, we find that the predictions used for funding allocations are sensitive to model selection, highlighting the need for comprehensive robustness testing when estimating risk adjustment models used in applications.

Keywords: Healthcare costs; Interpretation; Machine learning; Predictive modeling; Risk adjustment; Socioeconomic information.

PubMed Disclaimer

Conflict of interest statement

The authors report no conflicts of interest.

Figures

Fig. 1
Fig. 1
Distribution of healthcare costs in 2017, whole sample (N = 553,675)
Fig. 2
Fig. 2
Model predicted values plotted against each other, validation sample
Fig. 3
Fig. 3
Model predictions plotted against the actual values, validation sample
Fig. 4
Fig. 4
Need multipliers calculated with different models plotted against each other, validation sample
Fig. 5
Fig. 5
Predictor variable importance of (a) random forest, (b) GBM and (c) XGBoost, estimation sample
Fig. 6
Fig. 6
Partial dependence plots of (a) random forest, (b) GBM and (c) XGBoost, estimation sample
Fig. 7
Fig. 7
LIME explanations of (a) random forest, (b) GBM and (c) XGBoost, estimation sample
See this image and copyright information in PMC

References

    1. Geruso, M., Layton, T.J.: Selection in health insurance markets and its policy remedies. J. Econ. Perspectives 31(4), 23–50 (2017). 10.1257/jep.31.4.23 10.1257/jep.31.4.23 - DOI - PMC - PubMed
    1. Breyer, F., Bundorf, M. K., Pauly, M. V.: Health care spending risk, health insurance, and payment to health plans. In: Pauly, M. V., McGuire, T. G., Barros, P. P. (eds.) Handbook of Health Economics Vol. 2, pp. 691–762. Elsevier (2011) 10.1016/B978-0-444-53592-4.00011-6
    1. van Kleef, R. C., Schut, F. T., van de Ven, W. P.: Premium regulation, risk equalization, risk sharing, and subsidies: Effects on affordability and efficiency. In: McGuire. T. G., van Kleef, R. C. (eds.) Risk adjustment, risk sharing and premium regulation in health insurance markets, pp. 21– 54. Academic Press (2018). 10.1016/B978-0-12-811325-7.00002-6
    1. Chaplin, M., Beatson, S., Yiu-Shing, L., Davies, C., Smyth, C., Burrows, J., Weir, R., Tatarek-Gintowt, R.: Refreshing the Formulae for CCG Allocations. For allocations to Clinical Commissioning Groups from 2016–2017. Report on the methods and modelling. ANHS England, Analytical Services (Finance) (2016)
    1. Smith, P.C.: Formula funding of public services: an economic analysis. Oxf. Rev. Econ. Policy. Rev. Econ. Policy 19(2), 301–322 (2003). 10.1093/oxrep/19.2.301 10.1093/oxrep/19.2.301 - DOI

LinkOut - more resources