Marwan Shams Eddin

Dr. Marwan Shams Eddin

orcid
Sr. Operations Research Consultant at American Airlines, PhD...

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 April 2024 in IISE Transactions
Verified
Journal Article
Closed access
Marwan Shams EddinMarwan Shams Eddin
Marwan Shams Eddin
HEHadi El-Amine
Hadi El-Amine
HAHrayer Aprahamian
Hrayer Aprahamian

17 September 2025 in Healthcare
Verified
Journal Article
Open access
PDF file
Marwan Shams EddinMarwan Shams Eddin
Marwan Shams Eddin
HHHussein El Hajj
Hussein El Hajj
Background: Emerging pandemics can rapidly overwhelm hospital capacity, leading to increased mortality and healthcare costs. Objective: We develop an optimization-based framework that dynamically schedules hospital beds across multiple facilities to minimize total healthcare costs, including patient rejections and logistical expenses, under resource constraints. Methods: The model integrates several real-world flexibilities: standard hospital beds, buffer capacity from non-pandemic wards, in situ field hospitals, and inter-hospital patient transfers. To capture demand uncertainty, we link the model with an SEIRD epidemic forecasting approach and further extend it with a robust optimization variant that safeguards against worst-case surges. Recognizing computational challenges, we reformulate the problem to significantly reduce solution times and derive structural properties that provide guidance on when to open field hospitals, allocate buffer beds, and prioritize patients across facilities. Results: A case study based on COVID-19 data from Northern Virginia shows that the proposed framework reduces healthcare costs by more than 50% compared with current practice, mainly by lowering patient rejection rates. Conclusions: These results highlight the value of combining epidemic forecasting with prescriptive optimization to improve resilience and inform healthcare policy during crises.

8 July 2025 in Epidemiologia
Verified
Journal Article
Open access
PDF file
Marwan Shams EddinMarwan Shams Eddin
Marwan Shams Eddin
HHHussein El Hajj
Hussein El Hajj
RZRamez Mohammad Zayyat
Ramez Mohammad Zayyat
GLGayeon Lee
Gayeon Lee
Background/Objectives: The COVID-19 pandemic highlighted the critical need for accurate predictive models to guide public health interventions and optimize healthcare resource allocation. This study evaluates how the complexity of compartmental infectious disease models influences their forecasting accuracy and utility for pandemic resource planning. Methods: We analyzed a range of compartmental models, including simple susceptible-infected-recovered (SIR) models and more complex frameworks incorporating asymptomatic carriers and deaths. These models were calibrated and tested using real-world COVID-19 data from the United States to assess their performance in predicting symptomatic and asymptomatic infection counts, peak infection timing, and resource demands. Both adaptive models (updating parameters with real-time data) and non-adaptive models were evaluated. Results: Numerical results show that while more complex models capture detailed disease dynamics, simpler models often yield better forecast accuracy, especially during early pandemic stages or when predicting peak infection periods. Adaptive models provided the most accurate short-term forecasts but required substantial computational resources, making them less practical for long-term planning. Non-adaptive models produced stable long-term forecasts useful for strategic resource allocation, such as hospital bed and ICU planning. Conclusions: Model selection should align with the pandemic stage and decision-making horizon. Simpler models are effective for rapid early-stage interventions, adaptive models excel in short-term operational forecasting, and non-adaptive models remain valuable for long-term resource planning. These findings can inform policymakers on selecting appropriate modeling approaches to improve pandemic response effectiveness.

22 August 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Marwan Shams EddinMarwan Shams Eddin
Marwan Shams Eddin
HHHussein El Hajj
Hussein El Hajj
Emerging pandemics and peak infection periods can overwhelm healthcare systems, especially under limited resource availability such as hospital beds, ventilators, and ICU capacity. This strain may lead to elevated mortality rates and increased healthcare costs. In this paper, we present a novel optimization-based framework that dynamically schedules hospital beds to minimize total healthcare costs, primarily composed of patient rejection costs and associated logistical expenses, while operating under strict resource constraints. Our model accounts for multiple sources of bed supply, including standard hospital beds, in-situ hospital beds, and buffer beds, and incorporates flexible resource sharing to better accommodate patient demand. Recognizing the computational complexity of the resulting optimization model, we propose a reformulation that significantly reduces run-time. We also analyze key structural properties and derive optimal solutions under specific conditions. To account for demand uncertainty, we extend the framework by integrating an SEIRD model to simulate patient demand in future pandemics and to inform proactive bed scheduling. To evaluate the practical utility of our approach, we conduct a case study based on the COVID-19 pandemic in the Northern Virginia (NOVA) region. Our results demonstrate that the proposed framework can reduce total healthcare costs by more than 55%, highlighting its potential in guiding resource allocation and preparedness strategies during health crises.

4 November 2025 in European Journal of Business and Management Research
Verified
Journal Article
Open access
PDF file
ADAnanda S. Datta
Ananda S. Datta
SRShreyas Ravishankar
Shreyas Ravishankar
Marwan Shams EddinMarwan Shams Eddin
Marwan Shams Eddin
MAMehdi Ansari
Mehdi Ansari
CMChip Mayer
Chip Mayer
Legality violations pose significant operational challenges for airlines. Introducing buffer times in crew flight duty periods during the planning phase can mitigate these violations but often lead to higher planning costs. This paper presents a machine learning-based framework coupled with simulation-based analysis to balance this trade-off. We developed CatBoost models that accurately predict flight delays, translating these predictions into optimal buffer-time allocations within crew schedules. Our findings highlight the critical role of delay prediction profiles and conservatism in achieving this balance. A case study using American Airlines data demonstrates how our approach helps decision makers identify buffer levels that minimize legality violations while controlling costs.

1 March 2026 in INFORMS Journal on Computing
Verified
Journal Article
Closed access
Marwan Shams EddinMarwan Shams Eddin
Marwan Shams Eddin
HEHadi El-Amine
Hadi El-Amine
HAHrayer Aprahamian
Hrayer Aprahamian
We propose an optimization framework to solve problems that involve parameters that are forecast to vary over a given time horizon. We model uncertainty in the forecast through the use of lower and upper bounds that can be seen as time-dependent uncertainty levels. Our framework is applicable in long-term budget planning or resource allocation settings. We propose a model to minimize the maximum deviation from a so-called “ideal function” that we then show can be reformulated as a narrowest path problem on an acyclic directed graph with weights determined by solving minimax regret problems. Given that constructing the graph might be computationally demanding, we devise an optimal path discovery iterative scheme that computes edge weights on an as-needed basis and that results in ε-optimal solutions in a finite number of steps. We conduct an extensive numerical analysis of the proposed procedure to determine average-case performance. We then apply our proposed framework in two real-life settings: (1) large-scale screening of populations for West Nile Virus and (2) the allocation of resources in blood donation centers. The results from both case studies indicate significant reductions in yearly societal costs. History: Accepted by J. Paul Brooks, Area Editor for Applications in Biology, Medicine, & Healthcare. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0048 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0048 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .