IDEAS home Printed from https://ideas.repec.org/p/zbw/hcherp/202124.html
   My bibliography  Save this paper

Power of machine learning algorithms for predicting dropouts from a German telemonitoring program using standardized claims data

Author

Listed:
  • Hofer, Florian
  • Birkner, Benjamin
  • Spindler, Martin

Abstract

Background: Statutory health insurers in Germany offer a variety of disease management, prevention and health promotion programs to their insurees. Identifying patients with a high probability of leaving these programs prematurely helps insurers to offer better support to those at the highest risk of dropping out, potentially reducing costs and improving health outcomes for the most vulnerable. Objective: To evaluate whether machine learning methods outperform linear regression in predicting dropouts from a telemonitoring program. Methods: Use of linear regression and machine learning to predict dropouts from a telemonitoring program for patients with COPD by using information derived from claims data only. Different feature sets are used to compare model performance between and within different methods. Repeated 10-fold cross-validation with downsampling followed by grid searches was applied to tune relevant hyperparameters. Results: Random forest performed best with the highest AUC of 0.60. Applying logistic regression resulted in higher predictive power with regard to the correct classification of dropouts compared to neural networks with a sensitivity of 56%. All machine learning algorithms outperformed linear regression with respect to specificity. Overall predictive performance of all methods was only modest at best. Conclusion: Using features derived from claims data only, machine learning methods performed similar in comparison to linear regression in predicting dropouts from a telemonitoring program. However, as our data set contained information from only 1,302 individuals, our results may not be generalizable to the broader population.

Suggested Citation

  • Hofer, Florian & Birkner, Benjamin & Spindler, Martin, 2021. "Power of machine learning algorithms for predicting dropouts from a German telemonitoring program using standardized claims data," hche Research Papers 2021/24, University of Hamburg, Hamburg Center for Health Economics (hche).
  • Handle: RePEc:zbw:hcherp:202124
    as

    Download full text from publisher

    File URL: https://www.econstor.eu/bitstream/10419/246585/1/1776480082.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Kifmann Mathias & Nell Martin, 2014. "Fairer Systemwettbewerb zwischen gesetzlicher und privater Krankenversicherung," Perspektiven der Wirtschaftspolitik, De Gruyter, vol. 15(1), pages 75-87, February.
    2. Kifmann, Mathias & Nell, Martin, 2013. "Fairer Systemwettbewerb zwischen gesetzlicher und privater Krankenversicherung," hche Research Papers 2013/06, University of Hamburg, Hamburg Center for Health Economics (hche).
    3. Mathias Kifmann & Luigi Siciliani, 2017. "Average‐Cost Pricing and Dynamic Selection Incentives in the Hospital Sector," Health Economics, John Wiley & Sons, Ltd., vol. 26(12), pages 1566-1582, December.
    4. Yauheniya Varabyova & Carl Rudolf Blankart & Jonas Schreyögg, 2017. "Using nonparametric conditional approach to integrate quality into efficiency analysis: empirical evidence from cardiology departments," Health Care Management Science, Springer, vol. 20(4), pages 565-576, December.
    5. Kifmann, Mathias & Roeder, Kerstin, 2011. "Premium subsidies and social health insurance: Substitutes or complements?," Journal of Health Economics, Elsevier, vol. 30(6), pages 1207-1218.
    6. Oliver Tiemann & Jonas Schreyögg, 2012. "Changes in hospital efficiency after privatization," Health Care Management Science, Springer, vol. 15(4), pages 310-326, December.
    7. Mathias Kifmann & Kerstin Roeder, "undated". "Premium Subsidies and Social Insurance: Substitutes or Complements?," Working Papers 2011/01, Hamburg Center for Health Economics, University of Hamburg.
    8. Hinz, Vera & Drevs, Florian & Wehner, Jürgen, 2012. "Electronic word of mouth about medical services," hche Research Papers 2012/05, University of Hamburg, Hamburg Center for Health Economics (hche).
    9. Tom Stargardt & Jonas Schreyögg & Ivan Kondofersky, 2014. "Measuring The Relationship Between Costs And Outcomes: The Example Of Acute Myocardial Infarction In German Hospitals," Health Economics, John Wiley & Sons, Ltd., vol. 23(6), pages 653-669, June.
    10. Bahrs, Michael & Schumann, Mathias, 2016. "Unlucky to Be Young? The Long-Term Effects of School Starting Age on Smoking Behaviour and Health," hche Research Papers 2016/13, University of Hamburg, Hamburg Center for Health Economics (hche).
    11. Bach, Philipp & Farbmacher, Helmut & Spindler, Martin, 2018. "Semiparametric count data modeling with an application to health service demand," Econometrics and Statistics, Elsevier, vol. 8(C), pages 125-140.
    12. Blome, Christine & Augustin, Matthias, 2016. "Measuring change in subjective wellbeing: Methods to quantify recall bias and recalibration response shift," hche Research Papers 2016/12, University of Hamburg, Hamburg Center for Health Economics (hche).
    13. Kathrin Roll & Tom Stargardt & Jonas Schreyögg, 2012. "Effect of Type of Insurance and Income on Waiting Time for Outpatient Care," The Geneva Papers on Risk and Insurance - Issues and Practice, Palgrave Macmillan;The Geneva Association, vol. 37(4), pages 609-632, October.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kathrin Roll & Tom Stargardt & Jonas Schreyögg, 2012. "Effect of Type of Insurance and Income on Waiting Time for Outpatient Care," The Geneva Papers on Risk and Insurance - Issues and Practice, Palgrave Macmillan;The Geneva Association, vol. 37(4), pages 609-632, October.
    2. Oliver Tiemann & Jonas Schreyögg, 2012. "Changes in hospital efficiency after privatization," Health Care Management Science, Springer, vol. 15(4), pages 310-326, December.
    3. Nuscheler, Robert & Roeder, Kerstin, 2015. "Financing and funding health care: Optimal policy and political implementability," Journal of Health Economics, Elsevier, vol. 42(C), pages 197-208.
    4. Mathias Kifmann & Kerstin Roeder, "undated". "Premium Subsidies and Social Insurance: Substitutes or Complements?," Working Papers 2011/01, Hamburg Center for Health Economics, University of Hamburg.
    5. Jan Brosse & Mathias Kifmann, 2013. "Competition in Health Insurance and Premium Regulation," ifo DICE Report, ifo Institute - Leibniz Institute for Economic Research at the University of Munich, vol. 11(01), pages 21-26, April.
    6. repec:ces:ifodic:v:11:y:2013:i:1:p:19083487 is not listed on IDEAS
    7. Indra Kurniawan, Muhammad, 2021. "Has access to health insurance through the Indonesian social security system improved peoples understanding of health issues? Evidence from a national survey," Warwick-Monash Economics Student Papers 14, Warwick Monash Economics Student Papers.
    8. Lindlbauer, Ivonne & Schreyögg, Jonas & Winter, Vera, 2016. "Changes in technical efficiency after quality management certification: A DEA approach using difference-in-difference estimation with genetic matching in the hospital industry," European Journal of Operational Research, Elsevier, vol. 250(3), pages 1026-1036.
    9. Ousmane Traoré, 2021. "The relationship between health poverty and income poverty in Sub-Saharan African countries: evidence from index correlations," SN Business & Economics, Springer, vol. 1(10), pages 1-19, October.
    10. Christian Bührer & Steffen Fetzer & Christian Hagist, 2017. "Das Hamburger Beihilfemodell - Ein Vergleich der internen Renditen von GKV und PKV," WHU Working Paper Series - Economics Group 17-06, WHU - Otto Beisheim School of Management.
    11. Jan Brosse & Mathias Kifmann, 2013. "Competition in Health Insurance and Premium Regulation," ifo DICE Report, ifo Institute - Leibniz Institute for Economic Research at the University of Munich, vol. 11(1), pages 21-26, 04.
    12. Christian Pfarr & Andreas Schmid, 2016. "Redistribution through social health insurance: evidence on citizen preferences," The European Journal of Health Economics, Springer;Deutsche Gesellschaft für Gesundheitsökonomie (DGGÖ), vol. 17(5), pages 611-628, June.
    13. Pfarr, Christian & Schmid, Andreas, 2013. "The political economics of social health insurance: the tricky case of individuals’ preferences," MPRA Paper 44534, University Library of Munich, Germany.
    14. Schmitz, Hendrik, 2013. "Practice budgets and the patient mix of physicians – The effect of a remuneration system reform on health care utilisation," Journal of Health Economics, Elsevier, vol. 32(6), pages 1240-1249.
    15. Peter Oberender & Jürgen Zerth & Stefan Felder & Martin Nell & Bernd Raffelhüschen & Christian Hagist, 2013. "Reform des Gesundheitssystems: Kommt die Einheitskasse?," ifo Schnelldienst, ifo Institute - Leibniz Institute for Economic Research at the University of Munich, vol. 66(19), pages 03-15, October.
    16. Sebastian Panthöfer, 2016. "Risk Selection under Public Health Insurance with Opt‐Out," Health Economics, John Wiley & Sons, Ltd., vol. 25(9), pages 1163-1181, September.
    17. Ferreira, D.C. & Marques, R.C., 2019. "Do quality and access to hospital services impact on their technical efficiency?," Omega, Elsevier, vol. 86(C), pages 218-236.
    18. Bührer, Christian & Fetzer, Stefan & Hagist, Christian, 2020. "Adverse selection in the German Health Insurance System – the case of civil servants," Health Policy, Elsevier, vol. 124(8), pages 888-894.
    19. Kifmann, Mathias, 2017. "Competition policy for health care provision in Germany," Health Policy, Elsevier, vol. 121(2), pages 119-125.
    20. Annika Maren Schneider & Eva-Maria Oppel & Jonas Schreyögg, 2020. "Investigating the link between medical urgency and hospital efficiency – Insights from the German hospital market," Health Care Management Science, Springer, vol. 23(4), pages 649-660, December.
    21. Heinrich Nils & Wübker Ansgar & Wuckel Christiane, 2018. "Waiting Times for Outpatient Treatment in Germany: New Experimental Evidence from Primary Data," Journal of Economics and Statistics (Jahrbuecher fuer Nationaloekonomie und Statistik), De Gruyter, vol. 238(5), pages 375-394, September.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:zbw:hcherp:202124. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: . General contact details of provider: https://edirc.repec.org/data/chhamde.html .

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ZBW - Leibniz Information Centre for Economics (email available below). General contact details of provider: https://edirc.repec.org/data/chhamde.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.