ABSTRACT
Of great value to modern municipalities is the task of emergency medical response in the community. Resource allocation is vital to ensure minimal response times, which we may perform via human experts or automate by maximising ambulance coverage. To combat black-box modelling, we propose a modularised Genetic Programming Hyper Heuristic framework to learn the five key decisions of Emergency Medical Dispatch (EMD) within a reactive decision-making process. We minimise the representational distance between our work and reality by working with our local ambulance service to design a set of heuristics approximating their current decision-making processes and a set of synthetic datasets influenced by existing patterns in practice. Through our modularised framework, we learn each decision independently to identify those most valuable to EMD and learn all five decisions simultaneously, improving performance by 69% on the largest novel dataset. We analyse the decision-making logic behind several learned rules to further improve our understanding of EMD. For example, we find that emergency urgency is not necessarily considered when dispatching idle ambulances in favour of maximising fleet availability.
- Ramon Alanis, Armann Ingolfsson, and Bora Kolfal. 2013. A Markov chain model for an EMS system with repositioning. Production and operations management 22, 1 (2013), 216--231.Google Scholar
- Tobias Andersson and Peter Värbrand. 2007. Decision support tools for ambulance dispatch and relocation. Operational Research for Emergency Planning in Healthcare 1 (2007), 36--51.Google Scholar
- Jacques Benders. 1962. Partitioning Procedures for Solving Mixed-Variable Programming Problems. Numerische Matkematic 4 (1962), 238--252.Google ScholarDigital Library
- Patrizia Beraldi and Maria Elena Bruni. 2009. A probabilistic model applied to emergency service vehicle location. European Journal of Operational Research 196, 1 (2009), 323--331.Google ScholarCross Ref
- José Brandão and Richard Eglese. 2008. A deterministic tabu search algorithm for the capacitated arc routing problem. Computers & Operations Research 35, 4 (2008), 1112--1126.Google ScholarDigital Library
- Edmund K Burke, Mathew R Hyde, Graham Kendall, Gabriela Ochoa, Ender Ozcan, and John R Woodward. 2009. Exploring hyper-heuristic methodologies with genetic programming. In Computational intelligence. Springer, 177--201.Google Scholar
- Xinan Chen, Ruibin Bai, Rong Qu, and Haibo Dong. 2022. Cooperative Double-Layer Genetic Programming Hyper-Heuristic for Online Container Terminal Truck Dispatching. IEEE Transactions on Evolutionary Computation (2022).Google ScholarDigital Library
- Richard Church and Charles ReVelle. 1974. The maximal covering location problem. In Papers of the Regional Science Association, Vol. 32. Springer, 101--118.Google Scholar
- Federal Communications Commission et al. 2020. Wireless E911 location accuracy requirements. Federal Register 07-114 (2020).Google Scholar
- Tan N Doan, Brendan V Schultz, Stephen Rashford, and Emma Bosley. 2020. Surviving out-of-hospital cardiac arrest: the important role of bystander interventions. Australasian Emergency Care 23, 1 (2020), 47--54.Google ScholarCross Ref
- Shakiba Enayati, Osman Y. Özaltın, Maria E. Mayorga, and Cem Saydam. 2018. Ambulance redeployment and dispatching under uncertainty with personnel workload limitations. IISE Transactions 50, 9 (2018), 777--788.Google ScholarCross Ref
- Huali Fan, Hegen Xiong, and Mark Goh. 2021. Genetic programming-based hyper-heuristic approach for solving dynamic job shop scheduling problem with extended technical precedence constraints. Computers & Operations Research 134 (2021), 105401.Google ScholarCross Ref
- Michel Gendreau, Ola Jabali, and Walter Rei. 2016. 50th anniversary invited article-future research directions in stochastic vehicle routing. Transportation Science 50, 4 (2016), 1163--1173.Google ScholarCross Ref
- Michel Gendreau, Gilbert Laporte, and Frédéric Semet. 1997. Solving an ambulance location model by tabu search. Location science 5, 2 (1997), 75--88.Google Scholar
- Vincent Guigues, Anton Kleywegt, and Victor Hugo Nascimento. 2022. Operation of an ambulance fleet under uncertainty. arXiv preprint arXiv:2203.16371 (2022).Google Scholar
- Johan Holmén, Johan Herlitz, Sven-Erik Ricksten, Anneli Strömsöe, Eva Hagberg, Christer Axelsson, and Araz Rawshani. 2020. Shortening ambulance response time increases survival in out-of-hospital cardiac arrest. Journal of the American Heart Association 9, 21 (2020), e017048.Google ScholarCross Ref
- Cheng Hua and Tauhid Zaman. 2020. Optimal dispatch in emergency service system via reinforcement learning. In INFORMS International Conference on Service Science. Springer, 75--87.Google Scholar
- Zhixing Huang, Fangfang Zhang, Yi Mei, and Mengjie Zhang. 2022. An Investigation of Multitask Linear Genetic Programming for Dynamic Job Shop Scheduling. In the European Conference on Genetic Programming. Springer, 162--178.Google Scholar
- Caroline J Jagtenberg, Sandjai Bhulai, and Robert D van der Mei. 2017. Dynamic ambulance dispatching: is the closest-idle policy always optimal? Health Care Management Science 20, 4 (2017), 517--531.Google ScholarCross Ref
- Håkon Leknes, Eirik Skorge Aartun, Henrik Andersson, Marielle Christiansen, and Tobias Andersson Granberg. 2017. Strategic ambulance location for heterogeneous regions. European Journal of Operational Research 260, 1 (2017), 122--133.Google ScholarCross Ref
- Leon Y O Li. 1992. Vehicle Routeing for Winter Gritting. Ph. D. Dissertation. Lancaster University.Google Scholar
- Leon Y O Li and Richard W Eglese. 1996. An interactive algorithm for vehicle routeing for winter---gritting. Journal of the Operational Research Society 47, 2 (1996), 217--228.Google ScholarCross Ref
- Kunpeng Liu, Xiaolin Li, Cliff C Zou, Haibo Huang, and Yanjie Fu. 2020. Ambulance dispatch via deep reinforcement learning. In Proceedings of the 28th International Conference on Advances in Geographic Information Systems. 123--126.Google ScholarDigital Library
- Yuxin Liu, Yi Mei, Mengjie Zhang, and Zili Zhang. 2020. A predictive-reactive approach with genetic programming and cooperative coevolution for the uncertain capacitated arc routing problem. Evolutionary computation 28, 2 (2020), 289--316.Google Scholar
- Jordan MacLachlan, Yi Mei, Juergen Branke, and Mengjie Zhang. 2020. Genetic programming hyper-heuristics with vehicle collaboration for uncertain capacitated arc routing problems. Evolutionary computation 28, 4 (2020), 563--593.Google Scholar
- Jordan MacLachlan, Yi Mei, Fangfang Zhang, and Mengjie Zhang. 2022. Genetic Programming for Vehicle Subset Selection in Ambulance Dispatching. In 2022 IEEE Congress on Evolutionary Computation. IEEE, 1--8.Google Scholar
- Jordan MacLachlan, Yi Mei, Fangfang Zhang, Mengjie Zhang, and Jessica Signal. 2023. A novel set of Emergency Medical Dispatch datasets. Retrieved April 11, 2023 from https://tinyurl.com/emd23Google Scholar
- Matthew S Maxwell, Shane G Henderson, and Huseyin Topaloglu. 2009. Ambulance redeployment: An approximate dynamic programming approach. In the Winter Simulation Conference. IEEE, 1850--1860.Google ScholarCross Ref
- Matthew S Maxwell, Mateo Restrepo, Shane G Henderson, and Huseyin Topaloglu. 2010. Approximate dynamic programming for ambulance redeployment. INFORMS Journal on Computing 22, 2 (2010), 266--281.Google ScholarDigital Library
- Richard McCormack and Graham Coates. 2015. A simulation model to enable the optimization of ambulance fleet allocation and base station location for increased patient survival. European Journal of Operational Research 247, 1 (2015), 294--309.Google ScholarCross Ref
- Laura A McLay and Maria E Mayorga. 2013. A model for optimally dispatching ambulances to emergency calls with classification errors in patient priorities. IIE Transactions 45, 1 (2013), 1--24.Google ScholarCross Ref
- Yi Mei and Mengjie Zhang. 2018. Genetic programming hyper-heuristic for multi-vehicle uncertain capacitated arc routing problem. In the Proceedings of the Genetic and Evolutionary Computation Conference Companion. 141--142.Google ScholarDigital Library
- Mateo Restrepo. 2008. Computational Methods for Static Allocation and Real-Time Redeployment of Ambulances. Ph. D. Dissertation. Cornell University.Google Scholar
- Andrew Runka. 2011. Genetic programming for the RoboCup Rescue simulation system. (2011).Google Scholar
- Christian Schaack and Richard C Larson. 1989. An N server cutoff priority queue where arriving customers request a random number of servers. Management Science 35, 5 (1989), 614--634.Google ScholarDigital Library
- Verena Schmid and Karl F Doerner. 2010. Ambulance location and relocation problems with time-dependent travel times. European Journal of Operational Research 207, 3 (2010), 1293--1303.Google ScholarCross Ref
- Lihua Sun, L Jeff Hong, and Zhaolin Hu. 2014. Balancing exploitation and exploration in discrete optimization via simulation through a Gaussian process-based search. Operations Research 62, 6 (2014), 1416--1438.Google ScholarDigital Library
- C Swoveland, D Uyeno, I Vertinsky, and R Vickson. 1973. Ambulance location: a probabilistic enumeration approach. Management Science 20, 4-part-ii (1973), 686--698.Google ScholarDigital Library
- Ke Tang, Juan Wang, Xiaodong Li, and Xin Yao. 2016. A scalable approach to capacitated arc routing problems based on hierarchical decomposition. IEEE Transactions on Cybernetics 47, 11 (August 2016), 3928--3940.Google Scholar
- Joseph Tassone and Salimur Choudhury. 2020. A comprehensive survey on the ambulance routing and location problems. arXiv preprint arXiv:2001.05288 (2020).Google Scholar
- IDS Taylor and James GC Templeton. 1980. Waiting time in a multi-server cutoff-priority queue, and its application to an urban ambulance service. Operations Research 28, 5 (1980), 1168--1188.Google ScholarCross Ref
- Constantine Toregas, Ralph Swain, Charles ReVelle, and Lawrence Bergman. 1971. The location of emergency service facilities. Operations research 19, 6 (1971), 1363--1373.Google Scholar
- Tonguç Ünlüyurt and Yasir Tunçer. 2016. Estimating the performance of emergency medical service location models via discrete event simulation. Computers & Industrial Engineering 102 (2016), 467--475.Google ScholarDigital Library
- Juan Wang, Ke Tang, Jose A Lozano, and Xin Yao. 2016. Estimation of the distribution algorithm with a stochastic local search for uncertain capacitated arc routing problems. IEEE Transactions on Evolutionary Computation 20, 1 (2016), 96--109.Google ScholarDigital Library
- Shaolin Wang, Yi Mei, Mengjie Zhang, and Xin Yao. 2021. Genetic programming with niching for uncertain capacitated arc routing problem. IEEE Transactions on Evolutionary Computation (2021).Google Scholar
- Wei Yang, Qiang Su, Samuel H Huang, Qiugen Wang, Yanhong Zhu, and Ming Zhou. 2019. Simulation modeling and optimization for ambulance allocation considering spatiotemporal stochastic demand. Journal of Management Science and Engineering 4, 4 (2019), 252--265.Google ScholarCross Ref
- Wei Yang, Qiang Su, Ming Zhou, and Xinghong Qin. 2020. Ambulance allocation considering the spatial randomness of demand. Computers & Industrial Engineering 139 (2020), 106202.Google ScholarDigital Library
- Soovin Yoon and Laura A Albert. 2018. An expected coverage model with a cutoff priority queue. Health Care Management Science 21, 4 (2018), 517--533.Google ScholarCross Ref
- Soovin Yoon and Laura A Albert. 2020. A dynamic ambulance routing model with multiple response. Transportation Research Part E: Logistics and Transportation Review 133 (January 2020), 101807.Google Scholar
- Soovin Yoon and Laura A Albert. 2021. Dynamic dispatch policies for emergency response with multiple types of vehicles. Transportation Research Part E: Logistics and Transportation Review 152 (2021), 102405.Google ScholarCross Ref
- Soovin Yoon, Laura A Albert, and Veronica M White. 2021. A stochastic programming approach for locating and dispatching two types of ambulances. Transportation Science 55, 2 (2021), 275--296.Google ScholarDigital Library
- Fangfang Zhang, Yi Mei, Su Nguyen, Mengjie Zhang, and Kay Chen Tan. 2021. Surrogate-assisted evolutionary multitask genetic programming for dynamic flexible job shop scheduling. IEEE Transactions on Evolutionary Computation 25, 4 (2021), 651--665.Google ScholarDigital Library
Index Terms
- Learning Emergency Medical Dispatch Policies Via Genetic Programming
Recommendations
Impact of Ambulance Dispatch Policies on Performance of Emergency Medical Services
In ambulance location models, fleet size and ambulance location sites are two critical factors that emergency medical service (EMS) managers can control to ensure efficient delivery of the system. The ambulance relocation and dispatch policies that are ...
Evolving heuristics with genetic programming
GECCO '08: Proceedings of the 10th annual conference on Genetic and evolutionary computationHyper-Heuristics are methods to choose and combine heuristics to generate new ones. In this work, we use a grammar-based genetic programming system as a Hyper-Heuristic framework. The framework is used for evolving effective incremental solvers for SAT (...
Emergency Response Community Effectiveness
Mobile emergency response applications involving location-based alerts and physical response of networked members increasingly appear on smartphones to address a variety of emergencies. EMS (Emergency Medical Services) administrators, policy makers, and ...
Comments