Make A Decision Research Articles

Prediction Model of Spinal Osteoporosis Using Lumbar Spine X-Ray from Transfer Learning Deep Convolutional Neural Networks

Objective: Osteoporosis is highly prevalent among older adults and women. This condition leads to a deterioration in bone mineral density and microarchitecture, significantly increasing the risk of fractures. Additionally, osteoporosis commonly results in complications such as screw loosening and non-union during spinal surgery. Deep-learning algorithms have now achieved an accuracy comparable to the current human margin of error. Therefore, this study explored the potential of using transfer learning in deep learning algorithms to predict, diagnose, and screen for osteoporosis using commonly obtained sagittal spine X-rays from patients with spinal conditions.Methods: We retrospectively evaluated 2,300 consecutive patients who underwent dual energy X-ray absorptiometry (DXA) and lumbar sagittal plain X-ray exams between 2013 and 2021. The exclusion criteria included: (1) a gap of more than 1 year between the DXA and X-ray exams; (2) vertebrae that had undergone vertebroplasty; (3) lack of spine anterior-posterior DXA; and (4) images that were unassessable. Ultimately, 256 patients (images) were included in the study. Transfer learning was applied using convolutional neural network (CNN) techniques, specifically visual geometry group (VGG) 16, VGG 19, ResNet50, and Xception.Results: The most accurate CNN model in the training group was ResNet50, with an accuracy of 0.95. ResNet50 showed the best performance, with an accuracy of 0.82, precision of 0.80, recall of 0.86, and F1-score of 0.83. Additionally, its area under the curve (0.76) was higher than that other CNN models. The confusion matrix for ResNet50’s performance displayed the outcomes for images predicted as osteoporosis (n=12) among the test data osteoporosis images (n=14)Conclusion: Artificial intelligence (AI) technology employing deep learning techniques is significantly nearing human capabilities in the role of diagnostic assistance. The diagnosis of osteoporosis using bone mineral density is expected to evolve into a comprehensive diagnostic aid or decision-making tool with the integration of AI in the future.

Using simulation for long-term bed modelling in critical care

ABSTRACT A simulation model of the University Hospital of Wales (UHW) Critical Care (CC) Department is presented. This is the first CC model that considers the impact of future demand on capacity, supporting planning decisions to build a new hospital. A combination of long-term demand trajectories and Discrete Event Simulation (DES) are used. The results suggest the unit will need at least 66 Intensive Care beds and 19 Post-Anaesthesia Care beds to fulfil predicted demand in 2040 while being at capacity less than 5% of the time. Non-critical care ward beds impact patient flow in CC, thus must be considered when planning a new hospital. This study’s findings directly impact on decision making at UHW, having informed capacity planning of the planned unit. This paper contributes by presenting an infrastructure planning project using simulation as a decision-making tool, with transferable insights applicable to the planning of other CC units.

Predicting Clinical Outcomes in COVID-19 and Pneumonia Patients: A Machine Learning Approach.

In the clinical diagnosis of pneumonia, particularly during the COVID-19 pandemic, individuals who progress to a critical stage requiring mechanical ventilation are classified as mechanically ventilated critically ill patients. Accurately predicting the discharge outcomes for this specific cohort, especially those with COVID-19, is of paramount clinical importance. Missing data, a common issue in medical research, can significantly impact the validity of analyses. In this work, we address this challenge by employing two missing data imputation techniques: multiple imputation and missForest, to enhance data completeness. Additionally, we utilize the smoothly clipped absolute deviation (SCAD) penalized logistic regression method to select significant features. Our real data analysis compares the predictive performances of extreme learning machines, random forests, support vector machines, and XGBoost using 10-fold cross-validation. The results consistently show that XGBoost outperforms the other methods in predicting discharge outcomes, making it a reliable tool for clinical decision-making in the treatment of severe pneumonia, including COVID-19 cases. Within this context, the random forest imputation method generally enhances performance, underscoring its effectiveness in managing missing data compared to multiple imputation.

Automation of vegetable production analysis in the Russian Federation using a modern information system

The presented study is aimed at solving the problems of information support for making effective management decisions in the field of vegetable growing in Russia based on the use of technologies and tools that automate complex algorithms of statistical analysis, which expands the range of users of up-to-date, reliable and complete information on the factors that shape the volumes and efficiency of production in the vegetable growing industries. The information system proposed by the authors, developed on the basis of the PyCharm2023.1 programming environment using the Python programming language, allows the user to obtain statistical characteristics of the phenomenon under study, apply methods of correlation and regression analysis, ANOVA to identify cause-and-effect relationships, modeling processes and phenomena in order to predict their development. The web application was developed taking into account officially published information on the conditions and results of vegetable production, and its operation has been tested. At the same time, the information system has the potential for development and can be adapted to any data set.

Australian Dentists' Knowledge of the Consequences of Interpretive Errors in Dental Radiographs and Potential Mitigation Measures.

Dental radiographs, typically taken and interpreted by dentists, are essential for diagnosis and effective treatment planning. Interpretive errors in dental radiographs, stemming from failures of visual and cognitive processes, can affect both patients and clinicians. This survey aimed to assess the dental practitioners' perceptions of the consequences of these errors and potential measures to minimize them. This online anonymized survey assessed Australian dental practitioners' perceptions of the consequences of these errors and potential mitigation measures using ranking, Likert scale, and open-ended questions. The data were analyzed using descriptive statistics and bivariate analysis. Participants identified undertreatment (72%) and legal implications (82%) as the most significant consequences of interpretive errors, whereas severe harm to patients was deemed the least likely. Dental practitioners placed a greater emphasis on maintaining a high level of competence and the well-being of their patients. Utilizing high-quality images (63.9%) and appropriate radiographs (59.7%) were identified as the most effective measures to minimize interpretive errors. Participants showed hesitancy regarding the reliance on machine learning as a clinical decision-making tool. The survey provides valuable practical insights into the consequences and targeted measures to minimize the occurrence of interpretive errors. Efforts to minimize interpretive errors should address patient safety and practitioners' concerns about professional reputation and business viability. The study also suggests further research into the role of machine learning algorithms in reducing interpretive errors in dentistry.

Time-frequency comovements between news sentiments, Non-fungible tokens, and DeFi assets: evidence from the wavelet analysis

ABSTRACT Growth in digitalization has created a potential boost for Non-fungible tokens (NFTs) and decentralized finance (DeFis) assets in the modern world. Therefore, this study aims to examine the comovement between the recently developed comprehensive measure of news sentiment index (NSI) and selected digital assets. For this purpose, we have utilized the wavelet transform, wavelet correlation, and wavelet coherence econometric model to assess interdependency in both time and frequency between news sentiments and digital assets. Our wavelet correlation and covariance results suggest that almost all the digital assets exhibit a negative relationship with NSI. Moreover, the wavelet coherence results confirm that there is no significant comovement in the short to medium-term horizon, suggesting that both NFTs and DeFi can be used as hedges against the NSI. Furthermore, we observe small patches of significant negative comovement between NSI and digital assets in the long term, which correspond to the initial days of COVID-19. Our results confirm selected digital assets’ hedging role against news-driven uncertainty. This study finding provides essential information to policymakers, international investors, and investment managers to make effective decisions.

Approximating technology innovation performance with fuzzy approach

Purpose This study aims to construct a framework to evaluate technology innovation performance (TIP) of manufacturing organizations by adopting a fuzzy-based approach. In very short time, the world’s economic order has been reformed by economic globalization, thereby bringing new challenges as well as opportunities for the manufacturing industries. Policy makers encounter different decisions that require the use of various types of data in their decision-making process. These challenges raised the necessity of measuring innovation capability, which is critical issue for decision makers in today’s competitive world. The research results reveal the complexity of the path to technology innovation evaluation, constituting a novel contribution to the literature. Design/methodology/approach It is difficult for decision makers to make appropriate and effective decisions without knowing the innovation capability of companies in a particular sector or a region. As a result, not only on a macro but also on a micro level, an integrated and complete technique of measuring, estimating and even projecting innovation performance is necessary. In light of above mentioned facts, the present study proposes a technology innovation performance evaluation system of manufacturing organizations using fuzzy logic. Findings A model has been developed to be beneficial for any kind of organization where TIP evaluation is important consideration for enhancing manufacturing performance. Fuzzy control is used to determine the overall performance index by combining results of the TIP in selected criteria, which will certainly ensure suitability of the concerned organizations during performance rating calculations. Originality/value This study elaborates a fuzzy model to predict TIP with fuzzy rules. This is the first time a TIP evaluation model is developed using fuzzy approach that will be applicable for any kind of manufacturing industry where TIP evaluation is considered to be significantly important for cooperation’s to sustain competitiveness in the dynamic landscape.

Methodology of Multiple-Criteria Decision Making for Selecting a Refrigerant to Be Used in Commercial Refrigeration Equipment

This paper presents the application of the multiple-criteria decision-making (SAW) method for selecting the optimum refrigerant for the refrigeration systems of commercial cooling equipment used in gastronomy furniture, which is paramount in storing food under optimal conditions. The analysis focused on comparing different refrigerants, including natural refrigerants such as R744 (carbon dioxide) and R290 (propane) and synthetic refrigerants such as R455A, R449A, and R452A. As a result of the analysis using the SAW method, the refrigerant R455A was found to be the best solution. This choice resulted from the consideration of various decision criteria, such as energy efficiency, environmental impact, operating costs, and technology availability. R455A stands out as a synthetic refrigerant that provides high energy efficiency with minimal environmental impact. Its use supports sustainability goals by reducing greenhouse gas emissions and electricity consumption, which is crucial given the modern regulatory requirements and environmental standards. This study offers a practical decision-making tool for commercial refrigeration equipment designers and manufacturers, supporting them while selecting the optimal technological solutions. The choice of refrigerant R455A addresses the need to integrate energy efficiency, environmental protection, and cost-effectiveness in the process of designing modern refrigeration systems for catering furniture.

A IMPORTÂNCIA DA FORMAÇÃO CONTINUADA PARA PROFESSORES NA EDUCAÇÃO BÁSICA

This study addresses continuing education for teachers, which is highlighted as an essential process for improving knowledge. Continuing education for teachers is currently seen as a process for improving knowledge, involving actions directed at professionals who educate, teach, learn, research, and evaluate. This study aimed to discuss continuing education for teachers within educational policies in Brazil, emphasizing its importance and analyzing the current Brazilian educational context. The methodology was based on bibliographic research, using Google Scholar as the main source. The results make it clear that this review article can intensify the reflection on the importance of continuing education in Brazil, exposing its relevance for a deeper understanding of the educational reality and the teaching-learning process. Continuing education appears as a decisive tool, supporting the work of teachers and driving the evolution of teaching and learning. It is known that the teacher is not a finished product, but a subject in constant transformation, requiring continuous improvement to face the challenges of modern education. Therefore, each teacher must be an eternal learner, breaking with stagnant traditions and embracing a journey of continuous innovation, as only in this way will we be able to transform the Brazilian educational scenario, propelling it towards new spheres of excellence and relevance.

Considerations regarding the use of mission command at the tactical level

Mission Command is a specific component of the command and control system of military structures at all levels of leadership. Implementing the concept allows the commanders to encourage their subordinates to make quick and effective decisions. It also allows them to show their initiative and freedom of decision within the limits of the intention of the superior commander. In this article, a doctrinal-comparative introspection will be carried out to facilitate the identification of some advantages and disadvantages of using the Mission Command concept in the process of planning, leading, and evaluating operations at the tactical level. The research is based on the assumption that adapting the act of command and control to the particularities of the operation aims to maximize the effect of the action. Taking into account the aforementioned and not limiting ourselves to the principles of leadership, we can assert that this concept, which uses principles of military art and operational art, will become a tool at the disposal of future generations of military leaders to facilitate leading of forces with efficiency and effectiveness based on doctrinal foundations, within the limits of acceptable risks.

Creating Sustainable Flood Maps Using Machine Learning and Free Remote Sensing Data in Unmapped Areas

This study leverages a Random Forest model to predict flood hazard in Arizona, New Mexico, Colorado, and Utah, focusing on enhancing sustainability in flood management. Utilizing the National Flood Hazard Layer (NFHL), an intricate flood map of Arizona was generated, with the Random Forest Classification algorithm assessing flood hazard for each grid cell. Weather variable predictions from TerraClimate were integrated with NFHL classifications and Digital Elevation Model (DEM) analyses, providing a comprehensive understanding of flood dynamics. The research highlights the model’s capability to predict flood hazard in areas lacking NFHL classifications, thereby supporting sustainable flood management by elucidating weather’s influence on flood hazard. This approach aligns with sustainable development goals by aiding in resilient infrastructure design and informed urban planning, reducing the impact of floods on communities. Despite recognizing constraints such as input data precision and the model’s potential limitations in capturing complex variable interactions, the methodology offers a robust framework for flood hazard evaluation in other regions. Integrating diverse data sources, this study presents a valuable tool for decision-makers, supporting sustainable practices, and enhancing the resilience of vulnerable regions against flood hazards. This integrated approach underscores the potential of advanced modeling techniques in promoting sustainability in environmental hazard management.

Climate-induced risk assessment of the quarantine room in a University Library

Microclimate conditions in conservation spaces such as museums, galleries, storages, archives, and libraries significantly impact the preservation of cultural materials, potentially leading to permanent damage. This study focuses on quarantine rooms, essential for isolating and inspecting incoming collections for infestations or contamination. Despite their importance, systematic microclimate investigations in such spaces have not been conducted until now. In this research, temperature and relative humidity monitoring has been conducted over the past 3 years (i.e., 2021-2022-2023) within the quarantine room of the Norwegian University of Science and Technology (NTNU) University Library (located within the DORA I concrete bunker, Trondheim, Norway). Data analysis revealed stable indoor conditions due to the buffering capacity of the massive building envelope together with climate control system. Specific metrics for the estimation of climate-induced chemical and biological risks on vulnerable artifacts were applied to compute the percentage of time for which thermohygrometric conditions could favour cellulose hydrolysis and biodeteriogens proliferation on a yearly basis. In this way, the study provided a decision-making tool useful to evaluate the best time (in terms of safest temperature and relative humidity conditions) when to introduce incoming collections into the quarantine room, depending on the material they are made of and on the timeframe selected for their isolation.

Decision making techniques in mass gathering medicine during the COVID-19 pandemia: a scoping review.

The COVID-19 pandemic has profoundly affected mass gatherings (MGs) worldwide, necessitating the implementation of advanced decision support techniques. These techniques, including mathematical models and risk assessment tools, have played a critical role in ensuring the safe conduct of events by mitigating the spread of SARS-CoV-2. This mini-review aims to explore and synthesize the decision support methodologies employed in managing MGs during the COVID-19 pandemic. A scoping review was conducted following the PRISMA guidelines covering the period from 2020 to 2024. Studies were categorized by event type (e.g., academic, religious, political, sports) and decision-making tools applied. The review identified a range of decision support techniques, with risk assessment and simulation tools being the most commonly employed across various event types. A total of 199 studies were initially identified, with 10 selected finally for inclusion based on relevance to decision support techniques. Case studies included the successful risk mitigation strategies during the 2020 Hajj, the 2021 Tokyo Olympics, and the 2022 FIFA World Cup in Qatar. Techniques such as fuzzy logic, Bayesian analysis, and multi-criteria decision-making were also highlighted, particularly in complex scenarios. These tools significantly contributed to reducing COVID-19 transmission risks at large-scale events. The review underscores the importance of decision support systems in the safe management of MGs during the pandemic. Further research should focus on the integration of emerging technologies and the long-term impacts of decision support tools on public health management.

Evaluating the contributions and economic costs for Walleye fry and fingerling stocking in a large midwestern reservoir

Stocking is a common management practice to maintain Walleye populations where natural recruitment is low or to introduce and sustain Walleye populations outside of their native range. Walleye can be stocked at multiple lengths (e.g., fry and fingerling) and different sizes of stocked Walleye may contribute differently to Walleye year class strength, depending on the system into which they are stocked. The cost associated with stocking also varies by product. Therefore, it is important to determine the contributions from different stocked products within a region or for an individual waterbody. The objectives of our research were to 1) compare the relative contribution of and total length and body condition at the time of capture at age-0 between stocked Walleye fry and fingerlings and naturally produced individuals; and 2) estimate and compare the economic costs of Walleye fry and fingerling production relative to their contribution to the age-0 catch in Lake McConaughy during 2022 and 2023.We collected 178 and 263 age-0 Walleyes from Lake McConaughy during the summer and fall of 2022 and 2023, respectively. Fingerling-stocked Walleye contributed 2.12 times in 2022 and 2.92 times more in 2023 than fry-stocked Walleye. Production cost estimates revealed that fry cost 1.08 and 1.35 times greater than fingerlings per stocking unit in 2022 and 2023, thus fingerlings were deemed the most cost-effective product in this study. Walleye stocked as fry were significantly longer at the time of collection in 2022 and were in significantly better condition in both years compared to fingerling stocked Walleye. Our results provide valuable insights for fisheries managers by offering a case study example as well as offering a practical approach to guide effective management decisions on which stocked product is most appropriate for other systems. Overall, this research enhances the existing literature on Walleye stocking in large reservoir systems, offering practical and useful information for effective management decisions.

Development and validation of survival prediction models for patients with hepatocellular carcinoma treated with transcatheter arterial chemoembolization plus tyrosine kinase inhibitors.

Due to heterogeneity of molecular biology and microenvironment, therapeutic efficacy varies among hepatocellular carcinoma (HCC) patients treated with transcatheter arterial chemoembolization (TACE) and tyrosine kinase inhibitors (TKIs). We examined combined models using clinicoradiological characteristics, mutational burden of signaling pathways, and radiomics features to predict survival prognosis. Two cohorts comprising 111 patients with HCC were used to build prognostic models. The training and test cohorts included 78 and 33 individuals, respectively. Mutational burden was calculated based on 17 cancer-associated signaling pathways. Radiomic features were extracted and selected from computed tomography images using a pyradiomics system. Models based on clinicoradiological indicators, mutational burden, and radiomics score (rad-score) were built to predict overall survival (OS) and progression-free survival (PFS). Eastern Cooperative Oncology Group performance status, Child-Pugh class, peritumoral enhancement, PI3K_AKT and hypoxia mutational burden, and rad-score were used to create a combined model predicting OS. C-indices were 0.805 (training cohort) and 0.768 (test cohort). The areas under the curve (AUCs) were 0.889, 0.900, and 0.917 for 1-year, 2-year, and 3-year OS, respectively. To predict PFS, alpha-fetoprotein level, tumor enhancement pattern, hypoxia and receptor tyrosine kinase mutational burden, and rad-score were used. C-indices were 0.782 (training cohort) and 0.766 (test cohort). AUCs were 0.885 and 0.925 for 6-month and 12-month PFS, respectively. Calibration and decision curve analyses supported the model's accuracy and clinical potential. The nomogram models are hopeful to predict OS and PFS in patients with intermediate-advanced HCC treated with TACE plus TKIs, offering a promising tool for treatment decisions and monitoring patient progress.

Validation study of risk-reduction activities after personalized breast cancer education tool in the WISDOM study

Breast cancer risk reduction strategies have been well-validated, but barriers remain for high-risk individuals to adopt them. We performed a study among participants with high risk of breast cancer to validate whether a virtual breast health decision tool impacted a participant’s willingness to start risk-reducing activities, identify barriers to adopting these strategies, and understand if it affects breast cancer anxiety. The study sample was 318 participants in the personalized (investigational) arm of the Women Informed to Screen Depending on Measures of risk (WISDOM) clinical trial. After reviewing the tool, these participants completed a feedback survey. We demonstrated that 15 (4.7%) women were taking endocrine risk reduction, 123 (38.7%) were reducing alcohol intake, and 199 (62.6%) were exercising. In the three-month follow-up survey of 109 respondents, only 8 of 61 (13.1%) women who considered endocrine risk reduction pursued it. In contrast, 11 of 16 (68%) participants who considered alcohol reduction pursued the activity, and 14 of 24 (58%) women who considered exercise followed through. Participants listed fear of side effects as the most common barrier to endocrine risk reduction. We also present further steps to be taken to improve the effectiveness of the Breast Health Decisions tool.

The continuous improvement of digital assistance in the radiation oncologist's work: from web-based nomograms to the adoption of large-language models (LLMs). A systematic review by the young group of the Italian association of radiotherapy and clinical oncology (AIRO).

Recently, the availability of online medical resources for radiation oncologists and trainees has significantly expanded, alongside the development of numerous artificial intelligence (AI)-based tools. This review evaluates the impact of web-based clinical decision-making tools in the clinical practice of radiation oncology. We searched databases, including PubMed, EMBASE, and Scopus, using keywords related to web-based clinical decision-making tools and radiation oncology, adhering to PRISMA guidelines. Out of 2161 identified manuscripts, 70 were ultimately included in our study. These papers all supported the evidence that web-based tools can be transversally integrated into multiple radiation oncology fields, with online applications available for dose and clinical calculations, staging and other multipurpose intents. Specifically, the possible benefit of web-based nomograms for educational purposes was investigated in 35 of the evaluated manuscripts. As regards to the applications of digital and AI-based tools to treatment planning, diagnosis, treatment strategy selection and follow-up adoption, a total of 35 articles were selected. More specifically, 19 articles investigated the role of these tools in heterogeneous cancer types, while nine and seven articles were related to breast and head & neck cancers, respectively. Our analysis suggests that employing web-based and AI tools offers promising potential to enhance the personalization of cancer treatment.

Estimation of Reservoir Storage Capacity Using the Gould-Dincer Formula with the Aid of Possibility Theory

This paper presents a method for estimating reservoir storage capacity using the Gould–Dincer normal formula (G-DN), enhanced by the possibility theory. The G-DN equation is valuable for regional studies of reservoir reliability, particularly under climate change scenarios, using regional statistics. However, because the G-DN formula deals with measured data, it introduces a degree of uncertainty and fuzziness that traditional probability theory struggles to address. Possibility theory, an extension of fuzzy set theory, offers a suitable framework for managing this uncertainty and fuzziness. In this study, the G-DN formula is adapted to incorporate fuzzy logic, and the possibilistic nature of reservoir capacity is translated into a probabilistic framework using α-cuts from the possibility theory. These α-cuts approximate probability confidence intervals with high confidence. Applying the proposed methodology, in the present crisp case with the storage capacity D = 0.75, the value of the capacity C was found to be 1271×106 m3, and that for D = 0.5 was 634.5×106 m3. On the other hand, in the fuzzy case using the possibility theory, the value of the capacity for D = 0.75 is the internal [315,5679]×106 m3 and for D = 0.5 the value is interval [158,2839]×106 m3, with a probability of ≥95% and a risk level of α = 5% for both cases. The proposed approach could be used as a robust tool in the toolkit of engineers working on irrigation, drainage, and water resource projects, supporting informed and effective engineering decisions.

Adaptive metamodeling-based simulation optimisation

Simulation Optimisation is a powerful decision-making tool, but it can be challenging for complex, time-intensive models. This paper introduces Adaptive Metamodeling-based Simulation Optimisation (AMSO), a novel framework that enhances solution quality by integrating machine learning and metaheuristic techniques. AMSO combines Bagged-gradient Boosted Trees, Genetic Algorithms, Hyperparameter Optimisation, and Design of Experiments to efficiently explore promising solution areas. The study demonstrates AMSO’s application in two real-world scenarios: a resource allocation problem in a manufacturing digital twin model and a capacity expansion project at a mining plant. AMSO outperformed the Efficient Global Optimisation method, achieving solutions 8.1% and 9.7% better on average for the first and second case studies, respectively, with no significant increase in computational time. Additionally, AMSO matched the Genetic Algorithm method’s solution quality but reduced computational time by 83.6% and 90.6% in the first and second cases, respectively. AMSO is presented as a robust alternative for solving complex simulation models, complementing existing metamodeling-based methods and opening new research avenues with other machine learning models for faster, more accurate decision-making.

Socio-Economical Analysis of a Green Reverse Logistics Network under Uncertainty: A Case Study of Hospital Constructions

This study addresses the critical issue of managing construction and demolition waste in urban environments. Effective waste management is not only essential for minimizing costs but also for enhancing sustainability and reducing environmental impact. In this context, the research introduces a green reverse logistics model designed for C&D waste management, integrating both sustainability considerations and current regulatory frameworks, such as LEED. A key innovation of this model is the incorporation of electric vehicles for waste collection, compared to traditional diesel vehicles, as part of the logistical process, as carbon emission is a significant concern. By evaluating the limitations and opportunities associated with electric vehicles, alongside robust optimization to manage uncertainties in waste collection, the model seeks to balance environmental, social, and economic objectives. It further incorporates decision-making tools like fuzzy logic to optimize multi-objective outcomes across various waste facilities, including separation labs, incineration centers, recycling centers, and landfills. A case study conducted in Tehran validates the model, highlighting the socio-economic and environmental benefits of using electric vehicles in waste collection. Sensitivity analysis indicates that hybrid and socially focused policies perform best under high-impact scenarios, although results can differ with varying data sets. Despite the complexity of managing reverse logistics networks, this research provides valuable insights for supply chain planners. It suggests potential future directions, such as the application of metaheuristic algorithms and improved stochastic planning methods.