Skip to main content
SpringerLink
Log in

Optimizing Interpretable Treatment and Screening Policies in Healthcare

  • Living reference work entry
  • First Online:
Encyclopedia of Optimization

  • 110 Accesses

Introduction

Treatment and screening problems are a class of sequential decision-making problems under uncertainty that are ubiquitous in healthcare. Treatment problems aim to determine the best therapy or therapies to cure or reduce the negative impact of a diagnosed disease or group of diseases. In contrast, screening problems involve determining when a single patient or subset of patients should be assessed to detect for the presence of a disease. Optimization models have proven to be extremely useful in improving the performance of treatment and screening policies across various areas of healthcare [1, 40, 44] (see also chapter “Markov Decision Processes: Application to Treatment Planning”). However, such optimization-driven policies may be clinically unintuitive or uninterpretable, rendering them impractical for implementation.

This chapter begins by providing a general framework for sequential treatment and screening problems, followed by a description of the interpretable...

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

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Alagoz O, Hsu H, Schaefer AJ, Roberts MS (2010) Markov decision processes: a tool for sequential decision making under uncertainty. Med Decis Mak 30(4):474–483. https://doi.org/10.1177/0272989X09353194, http://mdm.sagepub.com/cgi/doi/10.1177/0272989X09353194, ISBN: 1552-681X; 0272-989X

  2. Alagoz O, Maillart LM, Schaefer AJ, Roberts MS (2004) The optimal timing of living-donor liver transplantation. Manag Sci 50(10):1420–1430. https://doi.org/10.1287/mnsc.1040.0287, ISBN: 00251909

  3. Alagoz O, Maillart LM, Schaefer AJ, Roberts MS (2007) Choosing among living-donor and cadaveric livers. Manag Sci 53(11):1702–1715. https://doi.org/10.1287/mnsc.1070.0726, http://pubsonline.informs.org/doi/abs/10.1287/mnsc.1070.0726, ISBN: 00251909

  4. Alagoz O, Maillart LM, Schaefer AJ, Roberts MS (2007) Determining the acceptance of cadaveric livers using an implicit model of the waiting list. Oper Res 55(1):24–36. https://doi.org/10.1287/opre.1060.0329, http://pubsonline.informs.org/doi/abs/10.1287/opre.1060.0329, ISBN: 1526546310

  5. Albert LA (2022) A mixed-integer programming model for identifying intuitive ambulance dispatching policies. http://arxiv.org/abs/2202.09387, arXiv:2202.09387 [cs, math]

  6. Amram M, Dunn J, Zhuo YD (2022) Optimal policy trees. Mach Learn 111(7):2741–2768. https://doi.org/10.1007/s10994-022-06128-5, https://link.springer.com/10.1007/s10994-022-06128-5

  7. Ayer T, Zhang C, Bonifonte A, Spaulding AC, Chhatwal J (2019) Prioritizing hepatitis C treatment in U.S. Prisons. Oper Res 67(3):853–873. https://doi.org/10.1287/opre.2018.1812

    Article  MathSciNet  MATH  Google Scholar 

  8. Ayvaci MUS, Alagoz O, Burnside ES (2012) The effect of budgetary restrictions on breast cancer diagnostic decisions. Manuf Serv Oper Manag 14(4):600–617. https://doi.org/10.1287/msom.1110.0371, http://pubsonline.informs.org/doi/abs/10.1287/msom.1110.0371, ISBN: 15234614

  9. Bastani H, Drakopoulos K, Gupta V, Vlachogiannis J, Hadjichristodoulou C, Lagiou P, Magiorkinis G, Paraskevis D, Tsiodras S (2022) Interpretable operations research for high-stakes decisions: designing the greek COVID-19 testing system. INFORMS J Appl Anal 52:398–411. https://doi.org/10.1287/inte.2022.1128, http://pubsonline.informs.org/doi/10.1287/inte.2022.1128

  10. Basu S, Millett C, Vijan S, Hayward RA, Kinra S, Ahuja R, Yudkin JS (2015) The health system and population health implications of large-scale diabetes screening in india: a microsimulation model of alternative approaches. PLOS Med 12(5):e1001827. https://doi.org/10.1371/journal.pmed.1001827, https://dx.plos.org/10.1371/journal.pmed.1001827

  11. Bertsimas D, Dunn J (2017) Optimal classification trees. In: Machine learning (September 2015). Springer, US. https://doi.org/10.1007/s10994-017-5633-9.

  12. Bertsimas D, Klasnja P, Murphy S, Na L (2022) Data-driven interpretable policy construction for personalized mobile health. Institute of Electrical and Electronics Engineers Inc. pp 13–22. https://doi.org/10.1109/ICDH55609.2022.00010

  13. Bravo F, Shaposhnik Y (2020) Mining optimal policies: a pattern recognition approach to model analysis. INFORMS J Optim 2(3):145–166. https://doi.org/10.1287/ijoo.2019.0026, http://pubsonline.informs.org/doi/10.1287/ijoo.2019.0026

  14. Cevik M, Ayer T, Alagoz O, Sprague BL (2018) Analysis of mammography screening policies under resource constraints. Prod Oper Manag 27(5):949–972. https://doi.org/10.1111/poms.12842, http://doi.wiley.com/10.1111/poms.12842

  15. Chen Q, Ayer T, Chhatwal J (2018) Optimal M-switch surveillance policies for liver cancer in a hepatitis C–infected population. Oper Res 66(3):673–696. https://doi.org/10.1287/opre.2017.1706, http://pubsonline.informs.org/doi/10.1287/opre.2017.1706

  16. Denton BT, Kurt M, Shah ND, Bryant SC, Smith SA (2009) Optimizing the start time of statin therapy for patients with diabetes. Med Decis Mak 29(3):351–367

    Article  Google Scholar 

  17. Garcia GGP, Czerniak LL, Lavieri MS, Liebel SW, McCrea MA, McAllister TW, Pasquina PF, Broglio SP, and CARE Consortium Investigators (2022) Simulation-optimization to distinguish optimal symptom free waiting period for return-to-play from concussion. 2022 Winter Simulation Conference (WSC), Singapore, 2022, pp. 1021–1032. https://doi.org/10.1109/WSC57314.2022.10015285

    Google Scholar 

  18. Garcia GGP, Lavieri MS, Jiang R, McCrea MA, McAllister TW, Broglio SP (2020) Data-driven stochastic optimization approaches to determine decision thresholds for risk estimation models. IISE Trans 52(10):1098–1121. https://doi.org/10.1080/24725854.2020.1725254, https://www.tandfonline.com/doi/full/10.1080/24725854.2020.1725254

  19. Garcia GGP, Steimle LN, Marrero WJ, Sussman JB (2023) Interpretable policies and the price of interpretability in hypertension treatment planning. Manufacturing & Service Operations Management 0(0). https://doi.org/10.1287/msom.2021.0373

  20. van Giessen A, de Wit GA, Moons KG, Dorresteijn JA, Koffijberg H (2018) An alternative approach identified optimal risk thresholds for treatment indication: an illustration in coronary heart disease. J Clin Epidemiol 94:122–131. Publisher: Elsevier Inc. https://doi.org/10.1016/j.jclinepi.2017.09.020

  21. Gittins JC, Jones DM (1979) A dynamic allocation index for the discounted multiarmed bandit problem. Biometrika 66(3):561–565. https://doi.org/10.1093/biomet/66.3.561, https://academic.oup.com/biomet/article-lookup/doi/10.1093/biomet/66.3.561

  22. Grand-Clément J, Chan C, Goyal V, Chuang E (2021) Interpretable machine learning for resource allocation with application to ventilator triage. http://arxiv.org/abs/2110.10994, arXiv:2110.10994 [cs]

  23. Grand-Clément J, Chan CW, Goyal V, Escobar G (2022) Robustness of proactive intensive care unit transfer policies. Oper Res p opre.2022.2403. https://doi.org/10.1287/opre.2022.2403, http://pubsonline.informs.org/doi/10.1287/opre.2022.2403

  24. Gutin E, Farias V (2016) Optimistic gittins indices. In: Lee D, Sugiyama M, Luxburg U, Guyon I, Garnett R (eds) Advances in neural information processing systems, vol 29. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2016/file/452bf208bf901322968557227b8f6efe-Paper.pdf

    Google Scholar 

  25. Hajjar A, Alagoz O (2022) Personalized disease screening decisions considering a chronic condition. Manag Sci p mnsc.2022.4336. https://doi.org/10.1287/mnsc.2022.4336, http://pubsonline.informs.org/doi/10.1287/mnsc.2022.4336

  26. Hu X, Hsueh PY, Chen CH, Diaz KM, Parsons FE, Ensari I, Qian M, Cheung YK (2018) An interpretable health behavioral intervention policy for mobile device users. IBM J Res Dev 62. https://doi.org/10.1147/JRD.2017.2769320

  27. Kim M, Ghate A, Phillips MH (2009) A Markov decision process approach to temporal modulation of dose fractions in radiation therapy planning. Phys Med Biol 54(14):4455

    Article  Google Scholar 

  28. Kotas J, Ghate A (2016) Response-guided dosing for rheumatoid arthritis. IIE Trans Healthcare Syst Eng 6(1):1–21. https://doi.org/10.1080/19488300.2015.1126873, http://www.tandfonline.com/doi/full/10.1080/19488300.2015.1126873

  29. Laber EB, Zhao YQ (2015) Tree-based methods for individualized treatment regimes. Biometrika 102:501–514. https://doi.org/10.1093/biomet/asv028

    Article  MathSciNet  MATH  Google Scholar 

  30. Li W, Denton BT, Morgan TM (2022) Optimizing active surveillance for prostate cancer using partially observable Markov decision processes. Eur J Oper Res. Publisher: Elsevier B.V. https://doi.org/10.1016/j.ejor.2022.05.043

  31. Maillart LM, Ivy JS, Ransom S, Diehl K (2008) Assessing dynamic breast cancer screening policies. Oper Res 56(6):1411–1427. https://doi.org/10.1287/opre.1080.0614, ISBN: 1526546310

    Article  Google Scholar 

  32. Odetola FO, Bruski L, Zayas-Caban G, Lavieri M (2016) An innovative framework to improve efficiency of interhospital transfer of children in respiratory failure. Ann Am Thorac Soc 13(5):671–677. https://doi.org/10.1513/AnnalsATS.201507-401OC

    Article  Google Scholar 

  33. Pauker SG, Kassirer JP (1975) Therapeutic decision making: a cost-benefit analysis. N Engl J Med 293(5):229–234. https://doi.org/10.1056/NEJM197507312930505, http://www.nejm.org/doi/abs/10.1056/NEJM197507312930505

  34. Pauker SG, Kassirer JP (1980) The threshold approach to clinical decision making. N Engl J Med 302(20):1109–1117. https://doi.org/10.1056/NEJM198005153022003, http://www.nejm.org/doi/abs/10.1056/NEJM198005153022003

  35. Petrik M, Luss R (2016) Interpretable policies for dynamic product recommendations. In: 32nd Conference on Uncertainty in Artificial Intelligence 2016, pp 607–616

    Google Scholar 

  36. Puterman ML (2014) Markov decision processes: discrete stochastic dynamic programming. Wiley-Interscience. OCLC: 904962147

    Google Scholar 

  37. Saghafian S, Trichakis N, Zhu R, Shih HA (2022) Joint patient selection and scheduling under no-shows: theory and application in proton therapy. Prod Oper Manag p poms.13886. https://doi.org/10.1111/poms.13886, https://onlinelibrary.wiley.com/doi/10.1111/poms.13886

  38. Sandıkçı B, Maillart LM, Schaefer AJ, Alagoz O, Roberts MS (2008) Estimating the patient’s price of privacy in liver transplantation. Oper Res 56(6):1393–1410. https://doi.org/10.1287/opre.1080.0648, http://pubsonline.informs.org/doi/abs/10.1287/opre.1080.0648, ISBN: 0030-364X

  39. Sandıkçı B, Maillart LM, Schaefer AJ, Roberts MS (2013) Alleviating the patient’s price of privacy through a partially observable waiting list. Manag Sci 59(8):1836–1854. https://doi.org/10.1287/mnsc.1120.1671, http://mansci.journal.informs.org/content/early/2013/03/04/mnsc.1120.1671.abstract

  40. Schaefer AJ, Bailey MD, Shechter SM, Roberts MS (2005) Modeling medical treatment using Markov decision processes. In: Operations research and health care. Springer, pp 593–612

    Google Scholar 

  41. Shechter SM, Bailey MD, Schaefer AJ (2008) A modeling framework for replacing medical therapies. IIE Trans 40(9):861–869. https://doi.org/10.1080/07408170802165898, http://www.tandfonline.com/doi/abs/10.1080/07408170802165898

  42. Shechter SM, Bailey MD, Schaefer AJ, Roberts MS (2008) The optimal time to initiate HIV therapy under ordered health states. Oper Res 56(1):20–33. https://doi.org/10.1287/opre.1070.0480, ISBN: 0030-364X

  43. Skandari MR, Shechter SM (2021) Patient-type bayes-adaptive treatment plans. Oper Res 69(2):574–598

    Article  MathSciNet  MATH  Google Scholar 

  44. Steimle LN, Denton BT (2017) Markov decision processes for screening and treatment of chronic diseases. In: Boucherie RJ, van Dijk NM (eds) Markov decision processes in practice, vol 248. Series Title: International Series in Operations Research & Management Science. Springer International Publishing, Cham, pp 189–222. https://doi.org/10.1007/978-3-319-47766-4_6, http://link.springer.com/10.1007/978-3-319-47766-4_6

  45. Utomo CP, Li X, Chen W (2018) Treatment recommendation in critical care: a scalable and interpretable approach in partially observable health states. In: International Conference on Interaction Sciences

    Google Scholar 

  46. Weber RR, Weiss G (1990) On an index policy for restless bandits. J Appl Probab 27(3):637–648. https://doi.org/10.2307/3214547, https://www. cambridge.org/core/product/identifier/S00219002000 39176/type/journal_article

  47. Whittle P (1988) Restless bandits: activity allocation in a changing world. J Appl Probab 25(A):287–298. https://doi.org/10.2307/3214163, https://www.cambridge.org/core/product/identifier/S0021900200040420/type/journal_article

  48. Wu CC, Suen SC (2022) Optimizing diabetes screening frequencies for at-risk groups. Health Care Manag Sci 25(1):1–23

    Article  Google Scholar 

  49. Zargoush M, Gümüş M, Verter V, Daskalopoulou SS (2018) Designing risk-adjusted therapy for patients with hypertension. Prod Oper Manag 27(12):2291–2312. https://doi.org/10.1111/poms.12872, http://doi.wiley.com/10.1111/poms.12872

  50. Zhang J, Denton BT, Balasubramanian H, Shah ND, Inman BA (2012) Optimization of prostate biopsy referral decisions. Manuf Serv Oper Manag 14(4):529–547. https://doi.org/10.1287/msom.1120.0388, http://pubsonline.informs.org/doi/abs/10.1287/msom.1120.0388, ISBN: 15234614

  51. Zhang Y, Laber EB, Tsiatis A, Davidian M (2015) Using decision lists to construct interpretable and parsimonious treatment regimes. Biometrics 71:895–904. https://doi.org/10.1111/biom.12354

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. H. Milton Stewart School of Industrial and Systems Engineering, GeorgiaInstitute of Technology, Atlanta, GA, USA

    Amaya K. McNealey, Lauren N. Steimle & Gian-Gabriel P. Garcia

  2. Thayer School of Engineering, Dartmouth College, Hanover, NH, USA

    Wesley J. Marrero

Authors
  1. Amaya K. McNealey
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wesley J. Marrero
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lauren N. Steimle
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gian-Gabriel P. Garcia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gian-Gabriel P. Garcia .

Editor information

Editors and Affiliations

  1. Department of Industrial & Systems Engin, University of Florida, Gainesville, FL, USA

    Panos M. Pardalos

  2. Departmentl of Industrial Engineering, University of Pittsburgh, Pittsburgh, PA, USA

    Oleg A. Prokopyev

Rights and permissions

Reprints and permissions

Copyright information

© 2023 Springer Nature Switzerland AG

About this entry

Check for updates. Verify currency and authenticity via CrossMark

Cite this entry

McNealey, A.K., Marrero, W.J., Steimle, L.N., Garcia, GG.P. (2023). Optimizing Interpretable Treatment and Screening Policies in Healthcare. In: Pardalos, P.M., Prokopyev, O.A. (eds) Encyclopedia of Optimization. Springer, Cham. https://doi.org/10.1007/978-3-030-54621-2_866-1

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-54621-2_866-1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-54621-2

  • Online ISBN: 978-3-030-54621-2

  • eBook Packages: Springer Reference MathematicsReference Module Computer Science and Engineering

Publish with us

Policies and ethics

Search

Navigation