Data-Driven Simulation-Optimization (DSO): An Efficient Approach to Optimize Simulation Models with Databases

Dehghanimohammadabadi, Mohammad

doi:10.1007/978-3-031-22039-5_10

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The remainder of this paper is organized as follows: In section 2, relevant studies are reviewed to highlight the contribution of this work. The DSO model is introduced by [Dehghanimohammadabadi] 8 which interested readers are encouraged to read the given reference to gain more insights The proposed framework is discussed in section 3, and its implementation details are provided in section 4. Section 5 demonstrated the applicability of the proposed model in a cancer clinic case study.…”

Section: Motivation and Objectivesmentioning

confidence: 99%

Multi-Objective Patient Appointment Scheduling Framework (MO-PASS): a data-table input simulation–optimization approach

Dehghanimohammadabadi

Rezaeiahari

Seif

2022

SIMULATION

View full text Add to dashboard Cite

Appointment scheduling is one of the critical factors for improving patient satisfaction with healthcare services. A practical and robust appointment scheduling solution allows clinics to efficiently utilize medical devices, equipment, and other resources. This study introduces a Multi-Objective Patient Appointment Scheduling (MO-PASS) framework to enhance clinic operations and quality of care. The proposed framework integrates three modules: (1) Optimization (using MATLAB), (2) Data-Exchange (MS Excel), and (3) Simulation (Simio). To implement MO-PASS, the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm is coded in MATLAB, and a Simio API is developed, which exchanges simulated scenarios with MOPSO via Excel. The efficiency of the proposed framework is evaluated in a breast cancer clinic with multiple physicians and patient types. Two objective functions are defined for evaluating the solutions of the AS problem: (1) minimizing the total service time and (2) maximizing the number of (admitted) patients with zero overtime. Finally, the performance of MO-PASS is tested against three heuristic approaches with respect to objective functions. The computational experiment results show that the proposed MO-PASS outperforms the existing heuristic benchmarks. Also, the framework is accompanied by all the necessary details to make it practical and easy to implement.

show abstract

Section: Motivation and Objectivesmentioning

confidence: 99%