Data-Driven Hospital Admission Control: A Learning Approach

References

• Abbasi-Yadkori Y, Pál D, Szepesvári C (2011) Improved algorithms for linear stochastic bandits. Shawe-Taylor J, Zemel RS, Bartlett PL, Pereira FCN, Weinberger KQ, eds. Adv. Neural Inform. Processing Systems (NIPS), vol. 24 (Curran Associates, Red Hook, NY), 2312–2320.Google Scholar
• Agrawal S, Devanur N (2014) Bandits with concave rewards and convex knapsacks. Proc. 15th ACM Conf. Econom. Comput. (ACM, Palo Alto, CA), 989–1006.Google Scholar
• Agrawal S, Devanur N (2016) Linear contextual bandits with knapsacks. Lee DD, Sugiyama M, Luxburg UV, Guyon I, Garnett R, eds. Adv. Neural Inform. Processing Systems (NIPS), vol. 29 (Curran Associates Inc., Red Hook, NY), 3450–3458.Google Scholar
• Agrawal S, Devanur NR, Li L (2016) An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives. J. Machine Learn. Res. 49:4–18.Google Scholar
• Ahuja V, Birge JR (2016) Response-adaptive designs for clinical trials: Simultaneous learning from multiple patients. Eur. J. Oper. Res. 248(2):619–633.Crossref, Google Scholar
• Auer P (2002) Using confidence bounds for exploitation-exploration trade-offs. J. Machine Learn. Res. 3:397–422.Google Scholar
• Auer P, Cesa-Bianchi N, Fischer P (2002) Finite-time analysis of the multiarmed bandit problem. Machine Learn. 47(2):235–256.Crossref, Google Scholar
• Badanidiyuru A, Kleinberg R, Slivkins A (2013) Bandits with knapsacks. Proc. 54th Annual Sympos. Foundations Comput. Sci. (IEEE, Piscataway, NJ), 207–216.Google Scholar
• Badanidiyuru A, Langford J, Slivkins A (2014) Resourceful contextual bandits. Proc. 27th Annual Conf. Learn. Theory, vol. 35 (PMLR, New York), 1109–1134.Google Scholar
• Balseiro S, Golrezaei N, Mahdian M, Mirrokni V, Schneider J (2019) Contextual bandits with cross-learning. Wallach H, Larochelle H, Beygelzimer A, d’Alché-Buc F, Fox E, Garnett R, eds. Adv. Processing Systems (NIPS), vol. 32 (Curran Associates, Red Hook, NY), 9676–9685.Google Scholar
• Bastani H, Bayati M (2020) Online decision-making with high-dimensional covariates. Oper. Res. 68(1):276–294.Google Scholar
• Bastani H, Bayati M, Khosravi K (2021) Mostly exploration-free algorithms for contextual bandits. Management Sci. 67(3):1329–1349.Google Scholar
• Bäuerle N (2000) Asymptotic optimality of tracking policies in stochastic networks. Ann. Appl. Probab. 10(4):1065–1083.Crossref, Google Scholar
• Benbassat J, Taragin M (2000) Hospital readmissions as a measure of quality of healthcare: Advantages and limitations. Arch. Internal Medicine 160(8):1074–1081.Crossref, Google Scholar
• Bimpikis K, Markakis MG (2019) Learning and hierarchies in service systems. Management Sci. 65(3):1268–1285.Link, Google Scholar
• Brown DB, Zhang J (2021) Dynamic programs with shared resources and signals: Dynamic fluid policies and asymptotic optimality. Oper. Res. 70(5):3015–3033.Link, Google Scholar
• Chan CW, Green LV, Lekwijit S, Lu L, Escobar G (2018) Assessing the impact of service level when customer needs are uncertain: An empirical investigation of hospital step-down units. Management Sci. 65(2):751–775.Link, Google Scholar
• Chen J, Dong J, Shi P (2021) Optimal routing under demand surges: The value of future arrival rates. Preprint, submitted December 14, https://dx.doi.org/10.2139/ssrn.3980227.Google Scholar
• Chen LM, Kennedy EH, Sales A, Hofer TP (2013) Use of health IT for higher-value critical care. New England J. Medicine 368(7):594–597.Crossref, Google Scholar
• Chen LM, Render M, Sales A, Kennedy EH, Wiitala W, Hofer TP (2012) Intensive care unit admitting patterns in the Veterans Affairs healthcare system. Arch. Internal Medicine 172(16):1220–1226.Crossref, Google Scholar
• Chen Y, Levi R, Shi C (2017) Revenue management of reusable resources with advanced reservations. Production Oper. Management 26(5):836–859.Crossref, Google Scholar
• Cheung WC, Simchi-Levi D, Zhu R (2022) Hedging the drift: Learning to optimize under nonstationarity. Management Sci. 68(3):1696–1713.Google Scholar
• Chu W, Li L, Reyzin L, Schapire R (2011) Contextual bandits with linear payoff functions. Proc. 14th Internat. Conf. Artificial Intelligence Statist., vol. 15 (PMLR, New York), 208–214.Google Scholar
• Cowen ME, Strawderman RL, Czerwinski JL, Smith MJ, Halasyamani LK (2013) Mortality predictions on admission as a context for organizing care activities. J. Hospital Medicine 8(5):229–235.Crossref, Google Scholar
• Dai J, Shi P (2019) Inpatient overflow: An approximate dynamic programming approach. Manufacturing Service Oper. Management 21(4):894–911.Link, Google Scholar
• Dani V, Hayes TP, Kakade SM (2008) Stochastic linear optimization under bandit feedback. Working paper, University of Chicago, IL.Google Scholar
• Dong J, Shi P, Zheng F, Jin X (2019) Off-service placement in inpatient ward network: Resource pooling vs. service slowdown. Columbia Business School Research Paper, New York.Google Scholar
• Elmachtoub AN, McNellis R, Oh S, Petrik M (2017) A practical method for solving contextual bandit problems using decision trees. Preprint, submitted June 14, https://arxiv.org/abs/1706.04687.Google Scholar
• Filippi S, Cappe O, Garivier A, Szepesvári C (2010) Parametric bandits: The generalized linear case. Lafferty JD, Williams CKI, Shawe-Taylor J, Zemel RS, Culotta A, eds. Adv. Neural Inform. Processing Systems, vol. 23 (Curran Associates, Inc., New York), 586–594.Google Scholar
• Gallego G, Iyengar G, Phillips R, Dubey A (2020) Managing flexible products on a network. Preprint, submitted April 27, http://dx.doi.org/10.2139/ssrn.3567371.Google Scholar
• Gerhardt G, Yemane A, Hickman P, Oelschlaeger A, Rollins E, Brennan N (2013) Data shows reduction in Medicare hospital readmission rates during 2012. Medicare Medicaid Res. Rev. 3(2):E1–E11.Crossref, Google Scholar
• Halpern NA, Pastores SM, Thaler HT, Greenstein RJ (2007) Critical care medicine use and cost among Medicare beneficiaries 1995–2000: Major discrepancies between two United States federal Medicare databases. Critical Care Medicine 35(3):692–699.Crossref, Google Scholar
• Helm JE, Van Oyen MP (2014) Design and optimization methods for elective hospital admissions. Oper. Res. 62(6):1265–1282.Link, Google Scholar
• Helm JE, Alaeddini A, Stauffer JM, Bretthauer KM, Skolarus TA (2016) Reducing hospital readmissions by integrating empirical prediction with resource optimization. Production Oper. Management 25(2):233–257.Crossref, Google Scholar
• Johari R, Kamble V, Kanoria Y (2021) Matching while learning. Oper. Res. 69(2):655–681.Link, Google Scholar
• Kaplan RS, Porter ME (2011) How to solve the cost crisis in healthcare. Harvard Bus. Rev. 89(9):46–52.Google Scholar
• Keyvanshokooh E, Zhalechian M, Shi C, Van Oyen MP, Kazemian P (2019) Contextual learning with online convex optimization: Theory and application to chronic diseases. Preprint, submitted December 31, https://dx.doi.org/10.2139/ssrn.3501316.Google Scholar
• Kim SH, Chan CW, Olivares M, Escobar G (2015) ICU admission control: An empirical study of capacity allocation and its implication for patient outcomes. Management Sci. 61(1):19–38.Link, Google Scholar
• Krishnasamy S, Sen R, Johari R, Shakkottai S (2016) Regret of queueing bandits. Lee DD, von Luxburg U, Garnett R, Sugiyama M, Guyon I, eds. Adv. Neural Inform. Processing Systems, vol. 30 (Curran Associates, Red Hook, NY), 1669–1677.Google Scholar
• Krishnasamy S, Sen R, Johari R, Shakkottai S (2021) Learning unknown service rates in queues: A multiarmed bandit approach. Oper. Res. 69(1):315–330.Link, Google Scholar
• Lattimore T, Szepesvári C (2020) Bandit Algorithms (Cambridge University Press).Crossref, Google Scholar
• Lei YM, Jasin S (2020) Real-time dynamic pricing for revenue management with reusable resources, advance reservation, and deterministic service time requirements. Oper. Res. 68(3):676–685.Link, Google Scholar
• Levi R, Radovanović A (2010) Provably near-optimal LP-based policies for revenue management in systems with reusable resources. Oper. Res. 58(2):503–507.Link, Google Scholar
• Li L, Lu Y, Zhou D (2017) Provably optimal algorithms for generalized linear contextual bandits. Proc. 34th Internat. Conf. Machine Learn. vol. 70 (Curran Associates Inc., New York), 2071–2080.Google Scholar
• Li L, Chu W, Langford J, Schapire RE (2010) A contextual-bandit approach to personalized news article recommendation. Proc. 19th Internat. Conf. World Wide Web (ACM, New York), 661–670.Google Scholar
• Liu Q, Van Ryzin G (2008) On the choice-based linear programming model for network revenue management. Manufacturing Service Oper. Management 10(2):288–310.Link, Google Scholar
• Maglaras C (2000) Discrete-review policies for scheduling stochastic networks: Trajectory tracking and fluid-scale asymptotic optimality. Ann. Appl. Probab. 10(3):897–929.Crossref, Google Scholar
• Miller TE, Thacker JK, White WD, Mantyh C, Migaly J, Jin J, Roche AM, et al. (2014) Reduced length of hospital stay in colorectal surgery after implementation of an enhanced recovery protocol. Anesthesia Analgesia 118(5):1052–1061.Crossref, Google Scholar
• Mintz Y, Aswani A, Kaminsky P, Flowers E, Fukuoka Y (2020) Non-stationary bandits with habituation and recovery dynamics. Oper. Res. 68(5):1493–1516.Google Scholar
• Negoescu DM, Bimpikis K, Brandeau ML, Iancu DA (2017) Dynamic learning of patient response types: An application to treating chronic diseases. Management Sci. 64(8):3469–3488.Link, Google Scholar
• O’Connor AM, Llewellyn-Thomas HA, Flood AB (2004) Modifying unwarranted variations in healthcare: Shared decision making using patient decision aids: A review of the evidence base for shared decision making. Health Affairs 23(Suppl2):VAR–63.Crossref, Google Scholar
• Owen Z, Simchi-Levi D (2018) Price and assortment optimization for reusable resources. Preprint, submitted November 16, 2017, https://dx.doi.org/10.2139/ssrn.3070625.Google Scholar
• Prin M, Wunsch H (2014) The role of stepdown beds in hospital care. Amer. J. Respiratory Critical Care Medicine 190(11):1210–1216.Crossref, Google Scholar
• Reis Miranda D, Jegers M (2012) Monitoring costs in the ICU: A search for a pertinent methodology. Acta Anaesthesiologica Scandinavica 56(9):1104–1113.Crossref, Google Scholar
• Rusmevichientong P, Tsitsiklis JN (2010) Linearly parameterized bandits. Math. Oper. Res. 35(2):395–411.Link, Google Scholar
• Russo D, Van Roy B (2014) Learning to optimize via posterior sampling. Math. Oper. Res. 39(4):1221–1243.Link, Google Scholar
• Samiedaluie S, Kucukyazici B, Verter V, Zhang D (2017) Managing patient admissions in a neurology ward. Oper. Res. 65(3):635–656.Link, Google Scholar
• Shah V, Gulikers L, Massoulié L, Vojnović M (2020) Adaptive matching for expert systems with uncertain task types. Oper. Res. 68(5):1403–1424.Link, Google Scholar
• Shmueli A, Sprung CL, Kaplan EH (2003) Optimizing admissions to an intensive care unit. Health Care Management Sci. 6(3):131–136.Crossref, Google Scholar
• Slivkins A (2019) Introduction to multi-armed bandits. Foundations and Trends in Machine Learning, vol. 12 (Now Publishers, Boston).Google Scholar
• Thiele RH, Rea KM, Turrentine FE, Friel CM, Hassinger TE, Goudreau BJ, Umapathi BA, et al. (2015) Standardization of care: Impact of an enhanced recovery protocol on length of stay, complications, and direct costs after colorectal surgery. J. Amer. College Surgeons 220(4):430–443.Crossref, Google Scholar
• Wang Y, Wang C, Powell W (2016) The knowledge gradient for sequential decision making with stochastic binary feedbacks. Lawrence N, Reid M, eds. Internat. Conf. Machine Learn. (PMLR, New York), 1138–1147.Google Scholar
• Zayas-Caban G, Jasin S, Wang G (2019) An asymptotically optimal heuristic for general nonstationary finite-horizon restless multi-armed, multi-action bandits. Adv. Appl. Probab. 51(3):745–772.Crossref, Google Scholar