Advertisement

Stratified Breast Cancer Follow-Up Using a Partially Observable MDP

  • J. W. M. Otten
  • A. WitteveenEmail author
  • I. M. H. Vliegen
  • S. Siesling
  • J. B. Timmer
  • M. J. IJzerman
Chapter
Part of the International Series in Operations Research & Management Science book series (ISOR, volume 248)

Abstract

Frequency and duration of follow-up for patients with breast cancer is still under discussion. Current follow-up consists of annual mammography for the first five years after treatment and does not depend on the personal risk of developing a locoregional recurrence (LRR) or second primary tumor. Aim of this study is to gain insight in how to allocate resources for optimal and personal follow-up. We formulate a discrete-time Partially Observable Markov Decision Process (POMDP) with a finite horizon in which we aim to maximize the total expected number of quality-adjusted life years (QALYs). Transition probabilities were obtained from data from the Netherlands Cancer Registry (NCR). Twice a year the decision is made whether or not a mammography will be performed. Recurrent disease can be detected by both mammography or women themselves (self-detection). The optimal policies were determined for three risk categories based on differentiation of the primary tumor. Our results suggest a slightly more intensive follow-up for patients with a high risk and poorly differentiated tumor, and a less intensive schedule for the other risk groups.

Keywords

Optimal Policy Markov Decision Process Belief State Optimality Equation Partially Observable Markov Decision Process 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    W.L. Lu, L. Jansen, W.J. Post, J. Bonnema, J.C. van de Velde, G.H. De Bock, Impact on survival of early detection of isolated breast recurrences after the primary treatment for breast cancer: a meta-analysis. Breast Cancer Res. Treat. 114, 403–412 (2009). http://dx.doi.org/10.1007/s10549-008-0023-4 CrossRefGoogle Scholar
  2. 2.
    M. Moossdorff, L.M. van Roozendaal, L.J.A. Strobbe, S. Aebi, D.A. Cameron, J.M. Dixon, A.E. Giuliano, B.G. Haffty, B.E. Hickey, C.A. Hudis, V.S. Klimberg, B. Koczwara, T. Kühn, M.E. Lippman, A. Lucci, M. Piccart, B.D. Smith, V.C.G. Tjan-Heijnen, C.J.H. van de Velde, K.J.V. Zee, J.B. Vermorken, G. Viale, A.C. Voogd, I.L. Wapnir, J.R. White, M.L. Smidt, Maastricht Delphi consensus on event definitions for classification of recurrence in breast cancer research. J. Natl. Cancer Inst. 106 (12), 1–7 (2014). http://dx.doi.org//10.1093/jnci/dju288
  3. 3.
    IKNL, Dutch Breast Cancer Guideline (2016), available: https://www.oncoline.nl/ [Online]. Accessed 2 March 2016
  4. 4.
    S.M.E. Geurts, F. de Vegt, S. Siesling, K. Flobbe, K.K.H. Aben, M. van der Heiden-van der Loo, A.L.M. Verbeek, J.A.A.M. van Dijck, V.C.G. Tjan-Heijnen, Pattern of follow-up care and early relapse detection in breast cancer patients. Breast Cancer Res. Treat. 136, 859–868 (2012). http://dx.doi.org/10.1007/s10549-012-2297-9 CrossRefGoogle Scholar
  5. 5.
    A. Witteveen, I.M.H. Vliegen, G.S. Sonke, J.M. Klaase, M.J. IJzerman, S. Siesling, Personalisation of breast cancer follow-up: a time-dependent prognostic nomogram for the estimation of annual risk of locoregional recurrence in early breast cancer patients. Breast Cancer Res. Treat. 152, 627–636 (2015). http://dx.doi.org/10.1007/s10549-015-3490-4 CrossRefGoogle Scholar
  6. 6.
    M. IJzerman, A. Manca, J. Keizer, S. Ramsey, Implementing comparative effectiveness research in personalized medicine applications in oncology: current and future perspectives. Comp. Eff. Res. 26 (5), 65–72 (2015). https://dx.doi.org/10.2147/CER.S92212 Google Scholar
  7. 7.
    R.D. Smallwood, E.J. Sondik, The optimal control of partially observable Markov processes over a finite horizon. Oper. Res. 21 (5), 1071–1088 (1973). http://dx.doi.org/10.1287/opre.21.5.1071 CrossRefGoogle Scholar
  8. 8.
    L.N. Steimle, B.T. Denton, Markov decision processes for screening and treatment of chronic diseases, in Markov Decision Processes in Practice, ed. by R. Boucherie, N.M. van Dijk (Springer, New York, 2016)Google Scholar
  9. 9.
    T. Ayer, O. Alagoz, N.K. Stout, A POMDP approach to personalize mammography screening decisions. Oper. Res. 60 (5), 1019–1034 (2012). http://dx.doi.org/10.1287/opre.1110.1019 CrossRefGoogle Scholar
  10. 10.
    M.U.S. Ayvaci, O. Alagoz, E.S. Burnside, The effect of budgetary restrictions on breast cancer diagnostic decisions. MSOM 14 (4), 600–617 (2012). http://dx.doi.org/10.1287/msom.1110.0371 CrossRefGoogle Scholar
  11. 11.
    J. Zhang, B.T. Denton, H. Balasubramanian, N.D. Shah, B.A. Inman, Optimization of PSA screening policies: a comparison of the patient and societal perspectives. Med. Decis. Making 32 (1), 337–349 (2012). http://dx.doi.org/10.1177/0272989X11416513 CrossRefGoogle Scholar
  12. 12.
    F.A. Sonnenberg, J.R. Back, Markov models in medical decision making, a practical guide. Med. Decis. Making 13 (4), 322–338 (1993). http://dx.doi.org/10.1177/0272989X9301300409 CrossRefGoogle Scholar
  13. 13.
    G.E. Monahan, A survey of partially observable Markov decision processes: theory, models and algorithms. Manag. Sci. 28 (1), 1–16 (1982). http://dx.doi.org/10.1287/mnsc.28.1.1 CrossRefGoogle Scholar
  14. 14.
    W.S. Lovejoy, A survey of algorithmic methods for partially observed Markov decision processes. Ann. Oper. Res. 28 (1), 47–65 (1991). http://dx.doi.org/10.1007/BF02055574 CrossRefGoogle Scholar
  15. 15.
    J.N. Eagle, The optimal search for a moving target when the search path is constrained. Oper. Res. 32 (5), 1107–1115 (1984). http://www.jstor.org/stable/170656 CrossRefGoogle Scholar
  16. 16.
    CBS, Statline (2016), available: http://statline.cbs.nl/Statweb/ [Online]. Accessed 18 May 2016
  17. 17.
    Netherlands Comprehensive Cancer Organisation (IKNL), Netherlands Cancer Registry (2016), available: https://www.cijfersoverkanker.nl/ [Online]
  18. 18.
    J.S. Mandelblatt, M.E. Wheat, M. Monane, R.D. Moshief, J.P. Hollenberg, J. Tang, Breast cancer screening for elderly women with and without comorbid conditions: a decision analysis model. Ann. Internal Med. 116 (9), 722–730 (2002). http://dx.doi.org/10.7326/0003-4819-116-9-722 CrossRefGoogle Scholar
  19. 19.
    V. Velanovich, Immediate biopsy versus observation for abnormal findings on mammograms: an analysis of potential outcomes and costs. Am. J. Surg. 170 (4), 327–332 (1995). http://dx.doi.org/10.1016/S0002-9610(99)80298-0
  20. 20.
    T.M. Kolb, J. Lichy, J.H. Newhouse, Comparison of the performance of screening mammography, physical examination, and breast us and evaluation of factors that influence them: an analysis of 27,825 patient evaluations. Radiology 225, 165–175 (2002). http://dx.doi.org/10.1148/radiol.2251011667 CrossRefGoogle Scholar
  21. 21.
    WHO, The world health report: 2002: reducing risks, promoting healthy life. World Health Organization (2002)Google Scholar
  22. 22.
    M. Fine, B. Rimer, P. Watts, Women’s responses to the mammography experience. J. Am. Board Fam. Pract. 6 (6), 546–555 (1993)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • J. W. M. Otten
    • 1
  • A. Witteveen
    • 2
    Email author
  • I. M. H. Vliegen
    • 3
  • S. Siesling
    • 2
    • 4
  • J. B. Timmer
    • 1
  • M. J. IJzerman
    • 2
  1. 1.Department of Stochastic Operations ResearchUniversity of TwenteEnschedeThe Netherlands
  2. 2.Department of Health Technology and Services ResearchUniversity of TwenteEnschedeThe Netherlands
  3. 3.Department of Industrial Engineering and Business Information SystemsUniversity of TwenteEnschedeThe Netherlands
  4. 4.Department of ResearchComprehensive Cancer OrganisationUtrechtThe Netherlands

Personalised recommendations