A Hybrid Simulated Annealing Approach for the Patient Bed Assignment Problem

Dorgham, Khouloud; Nouaouri, Issam; Ben-Romdhane, Hajer; Krichen, Saoussen

doi:10.1016/j.procs.2019.09.195

Cited by 12 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meta-heuristic searching optimization algorithms are set of optimization algorithms with capability of solving complex optimization problem based on generating candidate solutions randomly and enabling an evolving of them based on heuristics [8]. The literature contains wide range of meta-heuristic optimization algorithms, some of them are inspired from biological phenomena such as genetic algorithm [9], others are inspired from physical phenomena such as simulation annealing [10]. In addition, there is numerous metaphors used for deriving metaheuristic algorithm such as ant colony [11], artificial bee colony [12], particle swarm optimization [13]…etc.…”

Section: Introductionmentioning

confidence: 99%

Simulation for Dynamic Patients Scheduling based on Many Objective Optimization and Coordinator

Mahmed,

Kahar

2024

IJCAI

View full text Add to dashboard Cite

The Patient Admission Scheduling Problem (PASP) involves scheduling patient admissions, hospital time locations, to achieve certain quality of service and cost objectives, making it a multi-objective combinatorial optimization problem and NP-hard in nature. In addition, PASP is used in dynamic scenarios where patients are expected to arrive at the hospital sequentially, which requires dynamic optimization handling. Taking both aspects, optimization and dynamic utilization, we propose a simulation for dynamic patient scheduling based on multi-objective optimization, window, and coordinator. The role of multi-objective optimization deals with many soft constraints and providing a set of non-dominated solution coordinators. The role of the counter is to collect newly arrived patients and previously unconfirmed patients with the aim of passing them on to the coordinator. Finally, the role of the coordinator is to select a subset of patients from the window and pass them to the optimization algorithm. On the other hand, the coordinator is also responsible for those selected from the non-dominant solutions to activate it in the hospital and decide on unconfirmed employees to place them in the window for the next round. Simulator evaluation and comparison between several optimization algorithms show the superiority of NSGA-III in terms of set criticality and soft constraint values. Therefore, it treats PASP as a multi-objective dynamic optimization of a useful solution. NSGA-II is guaranteed 0.96 percent dominance over NSGA-II and 100 percent dominance of all other algorithms. Povzetek: Gre za dinamično razporejanje pacientov z uporabo večciljne optimizacije, ki obravnava kompleksni problem razporejanja sprejema pacientov v bolnišnico, izboljšuje kakovost storitev in učinkovitost z uporabo NSGA-II algoritma za optimizacijo.

show abstract

Section: Introductionmentioning

confidence: 99%

Simulation for Dynamic Patients Scheduling based on Many Objective Optimization and Coordinator

Mahmed,

Kahar

2024

IJCAI

View full text Add to dashboard Cite

show abstract

An Adaptive Tribal Topology for Particle Swarm Optimization

Brezinski

Ferens

2021

Transactions on Computational Science and Computational Intelligence

View full text Add to dashboard Cite

Combining machine learning and optimization for the operational patient-bed assignment problem

Schäfer,

Walther,

Grimm

et al. 2023

Health Care Manag Sci

View full text Add to dashboard Cite

Assigning inpatients to hospital beds impacts patient satisfaction and the workload of nurses and doctors. The assignment is subject to unknown inpatient arrivals, in particular for emergency patients. Hospitals, therefore, need to deal with uncertainty on actual bed requirements and potential shortage situations as bed capacities are limited. This paper develops a model and solution approach for solving the patient bed-assignment problem that is based on a machine learning (ML) approach to forecasting emergency patients. First, it contributes by improving the anticipation of emergency patients using ML approaches, incorporating weather data, time and dates, important local and regional events, as well as current and historical occupancy levels. Drawing on real-life data from a large case hospital, we were able to improve forecasting accuracy for emergency inpatient arrivals. We achieved up to 17% better root mean square error (RMSE) when using ML methods compared to a baseline approach relying on averages for historical arrival rates. We further show that the ML methods outperform time series forecasts. Second, we develop a new hyper-heuristic for solving real-life problem instances based on the pilot method and a specialized greedy look-ahead (GLA) heuristic. When applying the hyper-heuristic in test sets we were able to increase the objective function by up to 5.3% in comparison to the benchmark approach in [40]. A benchmark with a Genetic Algorithm shows also the superiority of the hyper-heuristic. Third, the combination of ML for emergency patient admission forecasting with advanced optimization through the hyper-heuristic allowed us to obtain an improvement of up to 3.3% on a real-life problem.

show abstract

A Hybrid Simulated Annealing Approach for the Patient Bed Assignment Problem

Cited by 12 publications

References 26 publications

Simulation for Dynamic Patients Scheduling based on Many Objective Optimization and Coordinator

Simulation for Dynamic Patients Scheduling based on Many Objective Optimization and Coordinator

An Adaptive Tribal Topology for Particle Swarm Optimization

Combining machine learning and optimization for the operational patient-bed assignment problem

Contact Info

Product

Resources

About