LBA: Online Learning-Based Assignment of Patients to Medical Professionals

Central to any medical domain is the challenging patient to medical professional assignment task, aimed at getting the right patient to the right medical professional at the right time. This task is highly complex and involves partially conflicting objectives such as minimizing patient wait-time while providing maximal level of care. To tackle this challenge, medical institutions apply common scheduling heuristics to guide their decisions. These generic heuristics often do not align with the expectations of each specific medical institution. In this article, we propose a novel learning-based online optimization approach we term Learning-Based Assignment (LBA), which provides decision makers with a tailored, data-centered decision support algorithm that facilitates dynamic, institution-specific multi-variate decisions, without altering existing medical workflows. We adapt our generic approach to two medical settings: (1) the assignment of patients to caregivers in an emergency department; and (2) the assignment of medical scans to radiologists. In an extensive empirical evaluation, using real-world data and medical experts’ input from two distinctive medical domains, we show that our proposed approach provides a dynamic, robust and configurable data-driven solution which can significantly improve upon existing medical practices.

[1]  Ariel Rosenfeld,et al.  Supporting users in finding successful matches in reciprocal recommender systems , 2020, User Model. User Adapt. Interact..

[2]  Yong-Hong Kuo,et al.  A decision support framework for home health care transportation with simultaneous multi-vehicle routing and staff scheduling synchronization , 2020, Decis. Support Syst..

[3]  Wojtek Michalowski,et al.  A decision support system for home dialysis visit scheduling and nurse routing , 2020, Decis. Support Syst..

[4]  Jennifer E. Moore,et al.  Agency for Healthcare Research and Quality , 2020, Definitions.

[5]  Bo An,et al.  Batch Allocation for Tasks with Overlapping Skill Requirements in Crowdsourcing , 2019, IEEE Transactions on Parallel and Distributed Systems.

[6]  Sarit Kraus,et al.  Emergency Department Online Patient-Caregiver Scheduling , 2019, AAAI.

[7]  Hakim Mitiche,et al.  Iterated Local Search for Time-extended Multi-robot Task Allocation with Spatio-temporal and Capacity Constraints , 2019, J. Intell. Syst..

[8]  Elizabeth L Stone,et al.  Clinical Decision Support Systems in the Emergency Department: Opportunities to Improve Triage Accuracy , 2019, Journal of emergency nursing: JEN : official publication of the Emergency Department Nurses Association.

[9]  Demis Hassabis,et al.  A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play , 2018, Science.

[10]  Sarit Kraus,et al.  Optimally balancing receiver and recommended users' importance in reciprocal recommender systems , 2018, RecSys.

[11]  Harold Soh,et al.  Generation meets recommendation: proposing novel items for groups of users , 2018, RecSys.

[12]  Supriyo Ghosh,et al.  Reserved Optimisation: Handling Incident Priorities in Emergency Response Systems , 2018, ICAPS.

[13]  B. Carr,et al.  Trends in the Contribution of Emergency Departments to the Provision of Hospital-Associated Health Care in the USA , 2018, International journal of health services : planning, administration, evaluation.

[14]  Melanie Erhard,et al.  State of the art in physician scheduling , 2018, Eur. J. Oper. Res..

[15]  Sarit Kraus,et al.  Predicting Human Decision-Making: From Prediction to Action , 2018, Predicting Human Decision-Making.

[16]  Christoph Trattner,et al.  Healthy Menus Recommendation: Optimizing the Use of the Pantry , 2018, HealthRecSys@RecSys.

[17]  Ward Whitt,et al.  A data-driven model of an emergency department , 2017 .

[18]  Noa Agmon,et al.  Intelligent agent supporting human-multi-robot team collaboration , 2015, Artif. Intell..

[19]  Saoussen Krichen,et al.  Scheduling Patients in Emergency Department by Considering Material Resources , 2017, KES.

[20]  Emre Kirac,et al.  Evaluating alternative resource allocation in an emergency department using discrete event simulation , 2016, Simul..

[21]  Erhan Kozan,et al.  Dynamic resource allocation to improve emergency department efficiency in real time , 2016, Eur. J. Oper. Res..

[22]  Robin Cohen,et al.  Multiagent Resource Allocation for Dynamic Task Arrivals with Preemption , 2016, ACM Trans. Intell. Syst. Technol..

[23]  Julie A. Shah,et al.  Apprenticeship Scheduling: Learning to Schedule from Human Experts , 2016, IJCAI.

[24]  Ness B. Shroff,et al.  Online multi-resource allocation for deadline sensitive jobs with partial values in the cloud , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[25]  C. Gomez-Uribe,et al.  The Netflix Recommender System: Algorithms, Business Value, and Innovation , 2016, ACM Trans. Manag. Inf. Syst..

[26]  Soroush Saghafian,et al.  Operations research/management contributions to emergency department patient flow optimization: Review and research prospects , 2015 .

[27]  Siba Prasada Panigrahi,et al.  A new training scheme for neural networks and application in non-linear channel equalization , 2015, Appl. Soft Comput..

[28]  A. Forster,et al.  Adverse events in patients with return emergency department visits , 2014, BMJ quality & safety.

[29]  Sasmita Kumari Padhy,et al.  Dynamic task scheduling using a directed neural network , 2015, J. Parallel Distributed Comput..

[30]  Helen Burstin,et al.  Quality measurement in the emergency department: past and future. , 2013, Health affairs.

[31]  Amos Azaria,et al.  Movie recommender system for profit maximization , 2013, AAAI.

[32]  Lewis Ntaimo,et al.  Stochastic online appointment scheduling of multi-step sequential procedures in nuclear medicine , 2013, Health care management science.

[33]  Kwai-Sang Chin,et al.  Modeling daily patient arrivals at Emergency Department and quantifying the relative importance of contributing variables using artificial neural network , 2013, Decis. Support Syst..

[34]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Jing Shi,et al.  Rescheduling of elective patients upon the arrival of emergency patients , 2012, Decis. Support Syst..

[36]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[37]  Franco Scarselli,et al.  SortNet: Learning to Rank by a Neural Preference Function , 2011, IEEE Transactions on Neural Networks.

[38]  Shari J. Welch,et al.  Emergency department operational metrics, measures and definitions: results of the Second Performance Measures and Benchmarking Summit. , 2011, Annals of emergency medicine.

[39]  Ying Liu,et al.  Opportunistic decision making and complexity in emergency care , 2011, J. Biomed. Informatics.

[40]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[41]  Michael Christ,et al.  Modern triage in the emergency department. , 2010, Deutsches Arzteblatt international.

[42]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[43]  Mark P. Graus,et al.  Understanding choice overload in recommender systems , 2010, RecSys '10.

[44]  Christopher J. C. Burges,et al.  From RankNet to LambdaRank to LambdaMART: An Overview , 2010 .

[45]  W. Dunsmuir,et al.  Association of interruptions with an increased risk and severity of medication administration errors. , 2010, Archives of internal medicine.

[46]  European Society of Radiology 2009 The future role of radiology in healthcare , 2010, Insights into imaging.

[47]  Gerard FitzGerald,et al.  Emergency department triage revisited , 2009, Emergency Medicine Journal.

[48]  Yariv N. Marmor,et al.  Emergency department operations: The basis for developing a simulation tool , 2005 .

[49]  S. Trzeciak,et al.  Clinical review: Emergency department overcrowding and the potential impact on the critically ill , 2004, Critical care.

[50]  Guy Shani,et al.  An MDP-Based Recommender System , 2002, J. Mach. Learn. Res..

[51]  P. Yarnold,et al.  Reliability and validity of scores on The Emergency Severity Index version 3. , 2004, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[52]  S. Trzeciak,et al.  Emergency department overcrowding in the United States: an emerging threat to patient safety and public health , 2003, Emergency medicine journal : EMJ.

[53]  Avery S. Hart,et al.  America's Health Care Safety Net: Intact but Endangered , 2000 .

[54]  Keith S. Decker,et al.  Coordinated hospital patient scheduling , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[55]  J. Mowen,et al.  Waiting in the emergency room: how to improve patient satisfaction. , 1993, Journal of health care marketing.

[56]  Joseph Y.-T. Leung,et al.  Minimizing the number of late jobs on unrelated machines , 1991, Oper. Res. Lett..

[57]  W. E. Hick Quarterly Journal of Experimental Psychology , 1948, Nature.

[58]  P. Samuelson Consumption Theory in Terms of Revealed Preference , 1948 .