@article{hosseinian_hemmati_dede_salzillo_dijk_mohamed_lai_schaefer_fuller_2024, title={Cluster-Based Toxicity Estimation of Osteoradionecrosis Via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification}, url={https://doi.org/10.1016/j.ijrobp.2024.02.021}, DOI={10.1016/j.ijrobp.2024.02.021}, abstractNote={<h2>Abstract</h2><h3>Purpose</h3> Given the limitations of extant models for normal tissue complication probability estimation for osteoradionecrosis (ORN) of the mandible, the purpose of this study was to enrich statistical inference by exploiting structural properties of data and provide a clinically reliable model for ORN risk evaluation through an unsupervised-learning analysis that incorporates the whole radiation dose distribution on the mandible. <h3>Materials and Methods</h3> The analysis was conducted on retrospective data of 1,259 head and neck cancer (HNC) patients treated at XXX between 2005 and 2015. During a minimum 12-month post-therapy follow-up period, 173 patients in this cohort (13.7%) developed ORN (grades I to IV). The (structural) clusters of mandibular dose-volume histograms (DVHs) for these patients were identified using the K-means clustering method. A soft-margin support vector machine (SVM) was used to determine the cluster borders and partition the dose-volume space. The risk of ORN for each dose-volume region was calculated based on incidence rates and other clinical risk factors. <h3>Results</h3> The K-means clustering method identified six clusters among the DVHs. Based on the first five clusters, the dose-volume space was partitioned by the soft-margin SVM into distinct regions with different risk indices. The sixth cluster entirely overlapped with the others; the region of this cluster was determined by its envelopes. For each region, the ORN incidence rate per pre-radiation dental extraction status (a statistically significant, non-dose related risk factor for ORN) was reported as the corresponding risk index. <h3>Conclusion</h3> This study presents an unsupervised-learning analysis of a large-scale data set to evaluate the risk of mandibular ORN among HNC patients. The results provide a visual risk-assessment tool for ORN (based on the whole DVH and pre-radiation dental extraction status) as well as a range of constraints for dose optimization under different risk levels.}, journal={International Journal of Radiation Oncology*Biology*Physics}, author={Hosseinian, Seyedmohammadhossein and Hemmati, Mehdi and Dede, Cem and Salzillo, Travis C. and Dijk, Lisanne V. and Mohamed, Abdallah S.R. and Lai, Stephen Y. and Schaefer, Andrew J. and Fuller, Clifton D.}, year={2024}, month={Aug} }
 @article{mccullum_karagoz_dede_garcia_nosrat_hemmati_hosseinian_schaefer_fuller_2024, title={Markov models for clinical decision‐making in radiation oncology: A systematic review}, url={https://doi.org/10.1111/1754-9485.13656}, DOI={10.1111/1754-9485.13656}, abstractNote={Abstract The intrinsic stochasticity of patients' response to treatment is a major consideration for clinical decision‐making in radiation therapy. Markov models are powerful tools to capture this stochasticity and render effective treatment decisions. This paper provides an overview of the Markov models for clinical decision analysis in radiation oncology. A comprehensive literature search was conducted within MEDLINE using PubMed, following the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) guidelines. Only studies published from 2000 to 2023 were considered. Selected publications were summarized in two categories: (i) studies that compare two (or more) fixed treatment policies using Monte Carlo simulation and (ii) studies that seek an optimal treatment policy through Markov Decision Processes (MDPs). Relevant to the scope of this study, 61 publications were selected for detailed review. The majority of these publications ( n = 56) focused on comparative analysis of two or more fixed treatment policies using Monte Carlo simulation. Classifications based on cancer site, utility measures and the type of sensitivity analysis are presented. Five publications considered MDPs with the aim of computing an optimal treatment policy; a detailed statement of the analysis and results is provided for each work. As an extension of Markov model‐based simulation analysis, MDP offers a flexible framework to identify an optimal treatment policy among a possibly large set of treatment policies. However, the applications of MDPs to oncological decision‐making have been understudied, and the full capacity of this framework to render complex optimal treatment decisions warrants further consideration.}, journal={Journal of Medical Imaging and Radiation Oncology}, author={McCullum, Lucas B and Karagoz, Aysenur and Dede, Cem and Garcia, Raul and Nosrat, Fatemeh and Hemmati, Mehdi and Hosseinian, Seyedmohammadhossein and Schaefer, Andrew J and Fuller, Clifton D}, year={2024}, month={Aug} }
 @article{garcia_hosseinian_pai_schaefer_2024, title={Strategy investments in zero-sum games}, url={https://doi.org/10.1007/s11590-024-02130-z}, DOI={10.1007/s11590-024-02130-z}, abstractNote={Abstract We propose an extension of two-player zero-sum games, where one player may select available actions for themselves and the opponent, subject to a budget constraint. We present a mixed-integer linear programming (MILP) formulation for the problem, provide analytical results regarding its solution, and discuss applications in the security and advertising domains. Our computational experiments demonstrate that heuristic approaches, on average, yield suboptimal solutions with at least a 20% relative gap with those obtained by the MILP formulation.}, journal={Optimization Letters}, author={Garcia, Raul and Hosseinian, Seyedmohammadhossein and Pai, Mallesh and Schaefer, Andrew J.}, year={2024}, month={Nov} }
 @article{hosseinian_hemmati_dede_salzillo_dijk_mohamed_lai_schaefer_fuller_2023, title={Cluster-Based Toxicity Estimation of Osteoradionecrosis via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification}, url={https://doi.org/10.1101/2023.03.24.23287710}, DOI={10.1101/2023.03.24.23287710}, abstractNote={Abstract Purpose Given the limitations of extant models for normal tissue complication probability estimation for osteoradionecrosis (ORN) of the mandible, the purpose of this study was to enrich statistical inference by exploiting structural properties of data and provide a clinically reliable model for ORN risk evaluation through an unsupervised-learning analysis. Materials and Methods The analysis was conducted on retrospective data of 1,259 head and neck cancer (HNC) patients treated at the University of Texas MD Anderson Cancer Center between 2005 and 2015. The (structural) clusters of mandibular dose-volume histograms (DVHs) were identified through the K-means clustering method. A soft-margin support vector machine (SVM) was used to determine the cluster borders and partition the dose-volume space. The risk of ORN for each dose-volume region was calculated based on the clinical risk factors and incidence rates. Results The K-means clustering method identified six clusters among the DVHs. Based on the first five clusters, the dose-volume space was partitioned almost perfectly by the soft-margin SVM into distinct regions with different risk indices. The sixth cluster overlapped the others entirely; the region of this cluster was determined by its envelops. These regions and the associated risk indices provide a range of constraints for dose optimization under different risk levels. Conclusion This study presents an unsupervised-learning analysis of a large-scale data set to evaluate the risk of mandibular ORN among HNC patients. The results provide a visual risk-assessment tool (based on the whole DVH) and a spectrum of dose constraints for radiation planning.}, author={Hosseinian, Seyedmohammadhossein and Hemmati, Mehdi and Dede, Cem and Salzillo, Travis C. and Dijk, Lisanne V. and Mohamed, Abdallah S. R. and Lai, Stephen Y. and Schaefer, Andrew J. and Fuller, Clifton D.}, year={2023}, month={Mar} }
 @article{ajayi_hosseinian_schaefer_fuller_2023, title={Code and Data Repository for Combination Chemotherapy Optimization with Discrete Dosing}, url={https://doi.org/10.1287/ijoc.2022.0207.cd}, DOI={10.1287/ijoc.2022.0207.cd}, abstractNote={This repository contains supporting material for the paper Combination Chemotherapy Optimization with Discrete Dosing by Temitayo Ajayi, Seyedmohammadhossein Hosseinian, Andrew J. Schaefer, and Clifton D. Fuller. This archive is distributed in association with the INFORMS Journal on Computing under the MIT License. The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper.}, journal={INFORMS Journal on Computing}, author={Ajayi, Temitayo and Hosseinian, Seyedmohammadhossein and Schaefer, Andrew J. and Fuller, Clifton D.}, year={2023}, month={Nov} }
 @article{ajayi_hosseinian_schaefer_fuller_2024, title={Combination Chemotherapy Optimization with Discrete Dosing}, url={https://doi.org/10.1287/ijoc.2022.0207}, DOI={10.1287/ijoc.2022.0207}, abstractNote={Chemotherapy drug administration is a complex problem that often requires expensive clinical trials to evaluate potential regimens; one way to alleviate this burden and better inform future trials is to build reliable models for drug administration. This paper presents a mixed-integer program for combination chemotherapy (utilization of multiple drugs) optimization that incorporates various important operational constraints and, besides dose and concentration limits, controls treatment toxicity based on its effect on the count of white blood cells. To address the uncertainty of tumor heterogeneity, we also propose chance constraints that guarantee reaching an operable tumor size with a high probability in a neoadjuvant setting. We present analytical results pertinent to the accuracy of the model in representing biological processes of chemotherapy and establish its potential for clinical applications through a numerical study of breast cancer. History: Accepted by Paul Brooks, Area Editor for Applications in Biology, Medicine, & Healthcare. Funding: This work was supported by the National Science Foundation [Grants CMMI-1933369 and CMMI-1933373]. 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.2022.0207 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0207 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .}, journal={INFORMS Journal on Computing}, author={Ajayi, Temitayo and Hosseinian, Seyedmohammadhossein and Schaefer, Andrew J. and Fuller, Clifton D.}, year={2024}, month={Mar} }
 @article{hosseinian_butenko_2022, title={An improved approximation for Maximum k-dependent Set on bipartite graphs}, url={https://doi.org/10.1016/j.dam.2021.10.015}, DOI={10.1016/j.dam.2021.10.015}, abstractNote={We present a (1+kk+2)-approximation algorithm for the Maximum k-dependent Set problem on bipartite graphs for any k≥1. For a graph with n vertices and m edges, the algorithm runs in O(kmn) time and improves upon the previously best-known approximation ratio of 1+kk+1 established by Kumar et al. (2014). Our proof also indicates that the algorithm retains its approximation ratio when applied to the (more general) class of König–Egerváry graphs.}, journal={Discrete Applied Mathematics}, author={Hosseinian, Seyedmohammadhossein and Butenko, Sergiy}, year={2022}, month={Jan} }
 @article{hosseinian_butenko_2021, title={Polyhedral properties of the induced cluster subgraphs}, url={https://doi.org/10.1016/j.dam.2021.02.040}, DOI={10.1016/j.dam.2021.02.040}, abstractNote={A cluster graph is a graph whose every connected component is a complete graph. Given a simple undirected graph G, a subset of vertices inducing a cluster graph is called an independent union of cliques (IUC), and the IUC polytope associated with G is defined as the convex hull of the incidence vectors of all IUCs in the graph. The Maximum IUC problem, which is to find a maximum-cardinality IUC in a graph, finds applications in network-based data analysis. In this paper, we derive several families of facet-defining valid inequalities for the IUC polytope. We also give a complete description of this polytope for some special classes of graphs. We establish computational complexity of the separation problem for most of the considered families of valid inequalities and explore the effectiveness of employing the corresponding cutting planes in an integer (linear) programming framework for the Maximum IUC problem through computational experiments.}, journal={Discrete Applied Mathematics}, author={Hosseinian, Seyedmohammadhossein and Butenko, Sergiy}, year={2021}, month={Jul} }
 @article{hosseinian_fontes_butenko_2020, title={A Lagrangian Bound on the Clique Number and an Exact Algorithm for the Maximum Edge Weight Clique Problem}, volume={32}, url={https://doi.org/10.1287/ijoc.2019.0898}, DOI={10.1287/ijoc.2019.0898}, abstractNote={This paper explores the connections between the classical maximum clique problem and its edge-weighted generalization, the maximum edge weight clique (MEWC) problem. As a result, a new analytic upper bound on the clique number of a graph is obtained and an exact algorithm for solving the MEWC problem is developed. The bound on the clique number is derived using a Lagrangian relaxation of an integer (linear) programming formulation of the MEWC problem. Furthermore, coloring-based bounds on the clique number are used in a novel upper-bounding scheme for the MEWC problem. This scheme is employed within a combinatorial branch-and-bound framework, yielding an exact algorithm for the MEWC problem. Results of computational experiments demonstrate a superior performance of the proposed algorithm compared with existing approaches.}, number={3}, journal={INFORMS Journal on Computing}, publisher={Institute for Operations Research and the Management Sciences (INFORMS)}, author={Hosseinian, Seyedmohammadhossein and Fontes, Dalila B. M. M. and Butenko, Sergiy}, year={2020}, month={Jul}, pages={747–762} }
 @article{hosseinian_butenko_2019, title={Algorithms for the generalized independent set problem based on a quadratic optimization approach}, volume={13}, url={https://doi.org/10.1007/s11590-019-01418-9}, DOI={10.1007/s11590-019-01418-9}, number={6}, journal={Optimization Letters}, publisher={Springer Science and Business Media LLC}, author={Hosseinian, Seyedmohammadhossein and Butenko, Sergiy}, year={2019}, month={Sep}, pages={1211–1222} }
 @article{hosseinian_fontes_butenko_2018, title={A nonconvex quadratic optimization approach to the maximum edge weight clique problem}, volume={72}, DOI={10.1007/s10898-018-0630-5}, number={2}, journal={Journal of Global Optimization}, publisher={Springer Nature}, author={Hosseinian, Seyedmohammadhossein and Fontes, Dalila B. M. M. and Butenko, Sergiy}, year={2018}, month={Mar}, pages={219–240} }
 @article{cisneros-saldana_hosseinian_butenko_2018, title={Network-based optimization techniques for wind farm location decisions}, volume={5}, DOI={10.15302/j-fem-2018025}, number={4}, journal={Frontiers of Engineering Management}, publisher={Editorial Department of Engineering Sciences}, author={CISNEROS-SALDANA, Jorge Ignacio and HOSSEINIAN, Seyedmohammadhossein and BUTENKO, Sergiy}, year={2018}, pages={533} }
 @article{hosseinian_choi_bae_2017, title={IRIER: A Decision-Support Model for Optimal Energy Retrofit Investments}, volume={143}, DOI={10.1061/(asce)co.1943-7862.0001362}, abstractNote={The importance of energy efficiency investment has grown substantially in recent decades, although research into the decision-making processes under energy saving uncertainties has been fairly limited. The main objective of this study is to create and test a multicriteria risk-based decision-support model for investment in energy efficiency projects under uncertainty of building energy retrofits: Integrated Risk-based decision-support model for investment in energy retrofits (IRIER). The results of a risk assessment are used in the modeling framework to help render optimal investment decisions from both energy and financial standpoints through advanced knowledge about uncertainties. The IRIER model accomplishes this by adopting a multicriteria analysis through stochastic simulations. An illustrative case study clearly shows that full-cost investment would not be optimal in the presence of uncertainty when considering both energy-saving and financial outcomes, in terms of the project's total energy savings and the investment's internal rate of return. The IRIER model can assist building owners and investors with assessing various investment scenarios in energy retrofits, thus enabling them to choose the most economical investment strategies that account for the level of risk.}, number={9}, journal={Journal of Construction Engineering and Management}, publisher={American Society of Civil Engineers (ASCE)}, author={Hosseinian, Seyedmohammadhossein and Choi, Kunhee and Bae, Junseo}, year={2017}, month={Sep}, pages={05017016} }
 @article{hosseinian_fontes_butenko_nardelli_fornari_curtarolo_2017, title={The Maximum Edge Weight Clique Problem: Formulations and Solution Approaches}, DOI={10.1007/978-3-319-68640-0_10}, abstractNote={Given an edge-weighted graph, the maximum edge weight clique (MEWC) problem is to find a clique that maximizes the sum of edge weights within the corresponding complete subgraph. This problem generalizes the classical maximum clique problem and finds many real-world applications in molecular biology, broadband network design, pattern recognition and robotics, information retrieval, marketing, and bioinformatics among other areas. The main goal of this chapter is to provide an up-to-date review of mathematical optimization formulations and solution approaches for the MEWC problem. Information on standard benchmark instances and state-of-the-art computational results is also included.}, journal={Optimization Methods and Applications}, publisher={Springer International Publishing}, author={Hosseinian, Seyedmohammadhossein and Fontes, Dalila B. M. M. and Butenko, Sergiy and Nardelli, Marco Buongiorno and Fornari, Marco and Curtarolo, Stefano}, year={2017}, pages={217–237} }
 @article{hosseinian_reinschmidt_2015, title={Finding Best Model to Forecast Construction Duration of Road Tunnels with New Austrian Tunneling Method Using Bayesian Inference}, volume={2522}, DOI={10.3141/2522-11}, abstractNote={Forecasting project final duration (i.e., time at completion) is crucial to project risk management and is always sought by project managers during the construction period. Because of a strong correlation between past and future performances in linear projects, past progress data are the best source of information to forecast final duration of this type of project, including tunneling projects constructed by the new Austrian tunneling method (NATM). Bayesian inference is a robust probabilistic approach that can provide accurate forecasts of final duration based on a project's past performance. However, results of research in this field have shown that selecting an appropriate model, which represents the unknown pattern of the project's actual progress well, is the most challenging and subjective part of this approach. Effective risk management necessitates looking for the best model that can forecast project final duration accurately and precisely, especially early in the project. This research was aimed at finding a best progress model for NATM tunneling projects by conducting Bayesian analysis on available data of a massive project, the Niayesh highway tunnel in Iran. The analysis showed that the dual Gompertz function (with flexible lower asymptote) was the most reliable model for this purpose. The results of this research bring advantages to the planning and risk management of NATM tunneling projects, which are discussed in this paper, and can be very useful for future NATM tunnel constructions.}, journal={Transportation Research Record: Journal of the Transportation Research Board}, publisher={SAGE Publications}, author={Hosseinian, Seyedmohammadhossein and Reinschmidt, Kenneth F.}, year={2015}, month={Aug}, pages={113–120} }