Dr. Reut Noham.
Researcher at the School of Industrial & Intelligent Systems Engineering, Faculty of Engineering, Tel Aviv University
About Me
I am a faculty member and the HOPE lab - the lab for Healthcare and Humanitarian operations, at the School of Industrial and Intelligent Systems Engineering at Tel-Aviv University. I was a post-doctoral fellow at the Department of Industrial Engineering and Management Sciences at Northwestern University and received my Ph.D. degree in Industrial Engineering from Tel-Aviv University in 2019. My research interests include supply chain management and logistics with a focus on humanitarian supply chains, healthcare systems, and non-profit optimization. I employ Analytics and OR tools to model and analyze problems and solution methods to improve the quality of life in an uncertain world. At the HOPE lab, we develop innovative and implementable models for dynamic decision-making in collaboration with policymakers and practitioners from the public sector. I am committed to advancing innovative scientific solutions while providing a platform for engaging policymakers and the public with our cutting-edge research.
Latest Publications
Balancing effectiveness and equity in the face of uncertainty: The case of humanitarian lateral transshipments
Reut Noham, Ohad Eisenhandler. (2026), Socio-Economic Planning Sciences.
In humanitarian operations, decision makers must allocate limited resources efficiently while ensuring fair outcomes for disaster-affected communities. This paper addresses the Humanitarian Transshipment Problem (HTP), which involves the joint optimization of pre-positioned inventory and post-disaster lateral transshipments. The central challenge lies in balancing effectiveness, namely, the extent to which needs are met, and equity, namely, the fairness of aid distribution. This trade-off becomes even more complex under uncertainty, when multiple disaster scenarios must be anticipated. Existing approaches to this balance in stochastic settings often rely on ad-hoc formulations, offering little justification for how social welfare should be measured across scenarios. We propose an alternative framework that establishes an axiomatic foundation for evaluating the effectiveness–equity trade-off under uncertainty, filling a significant gap in the literature. Our formulation preserves desirable properties across scenarios while remaining tractable and interpretable, making it suitable for humanitarian decision-making. Using both real-world and synthetic data, we demonstrate that our model enhances system performance and supports equitable decision-making under uncertainty. Our results highlight the strategic value of lateral transshipments, especially under tight budgets and high uncertainty, and provide guidance for organizations seeking to improve fairness, effectiveness, and efficiency in disaster preparedness.
Recent projects
Explainable Machine Learning Analysis of Immunology Test Utilization in Hospitalized Patients
Liat Shbtay, David Hagin, Daphna Paran, Yifat Alcalay, Reut Noham
Overuse of immunology laboratory testing remains a persistent challenge in acute care, contributing to increased workload, downstream investigations, and diagnostic complexity. While machine learning (ML) and explainable artificial intelligence (XAI) are increasingly used in healthcare, most studies focus on predictive accuracy rather than on understanding how diagnostic tests contribute within real-world clinical settings. This study applies explainable ML to systematically evaluate real-world immunology test utilization in hospitalized patients. We analyzed electronic health records from a tertiary-care hospital between 2018 and 2023, including 7,402 adult patients and 78 curated clinical, laboratory, and diagnostic features. Patients were classified as having immune or non-immune discharge diagnoses. Multiple ML models were evaluated, with XGBoost selected for detailed interpretation. SHapley Additive exPlanations (SHAP) were used to examine the contribution of immunology assays across clinical contexts. Immunology assays were frequently ordered among both immune and non-immune patients, with only modest differences between groups. XGBoost achieved an AUC of 0.75 and a weighted F1 score of 0.75. SHAP analyses showed that routine clinical and laboratory variables contributed more strongly to discrimination than most immunology assays, although complement-related markers demonstrated higher context-dependent contribution. Subgroup analyses revealed context-dependent variability across clinical presentations. Simulation analyses further showed that substantial hypothetical reductions in selected immunology tests among non-immune patients preserved predictive performance. These findings demonstrate how explainable ML can support systematic evaluation of diagnostic test utilization beyond prediction alone. By linking model-derived feature importance with real-world ordering practices, this approach provides a practical framework for identifying potential overuse and supporting more selective, context-aware use of laboratory resources. Such strategies may reduce unnecessary testing and downstream investigations, improve allocation of limited healthcare resources, and support more efficient, patient-centered diagnostic care without compromising diagnostic discrimination.
Community Resilience in Emergencies: A Stochastic Optimization Framework for Locating Autonomous Response Centers (ARCs)
Reut Noham, Moran Bodas
Despite efforts by civil defense organizations to promote preparedness behavMass disasters create severe gaps between the demand for emergency services and the operational capacity of formal response agencies. This interdisciplinary study develops a stochastic optimization framework for locating Autonomous Response Centers (ARCs), integrating operations research methodologies with sociological and behavioral insights to support decentralized civilian response during the first 24–72 hours following disasters. The model incorporates logistical considerations together with factors such as community resilience, trust, self-efficacy, and social capital. The proposed framework aims to improve equitable access to essential resources, reduce dependence on emergency agencies, and strengthen local resilience during large-scale emergencies.