Surgical operations account for a significant proportion of hospital costs. One factor often overlooked in Operating room (OR) scheduling is the management of reusable surgical instruments. Instruments are either owned by the hospital or rented from vendors. Rental instruments incur costs up to 12%-25% of the purchase price. We propose a deterministic mixed-integer programming model that integrates inventory management and OR scheduling to minimize total costs. This model determines the number of open ORs, the surgery schedule, instrument sourcing decisions (owned vs. rented), and instrument assignments for each surgery. We propose and evaluate easy-to-implement solution methods including a construction heuristic and a Lagrangean decomposition-based heuristic. As part of our heuristic solution approach, we also propose two upper-bounding procedures to solve this challenging problem. We compare our integrated approach against a sequential scheduling approach where schedules are created prior to determining the instrument assignment. An extensive sensitivity analysis is also performed to evaluate the effects of various parameters on the total cost of the system and the running time of the algorithms. Numerical experiments show that the integrated approach reduces total system costs by up to 6.65%, driven by an average 72% reduction in instrument rentals. Our decomposition heuristic finds solutions with an average optimality gap below 1% in significantly less time than solving the integrated model with commercial solvers.

This paper addresses latency issues related to publicly available port-level commodity tonnage reports. To predict commodity tonnage at the port-level, near real time vessel tracking data is used with historical Waterborne Commerce Statistics (WCS) with a machine learning model. Currently, commodity throughput is derived from WCS data which is released publicly approximately two years after collection. This latency presents a challenge for short-term planning and other operational uses. To reduce latency, this study leverages near real time vessel tracking data from the Automatic Identification System (AIS) data set. Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Temporal Fusion Transformer (TFT) machine learning models are developed using the features extracted from AIS and the historical WCS data. The output of the model is the prediction of the quarterly volume of commodities (in tons) at the port terminals for four quarters in the future. Two types of models are developed: (i) uncategorized- a single model trained on all port terminals; (ii) categorized- four models (one per dominant vessel type at the port terminal, i.e., cargo, tanker, tug/tow, and mixed). The uncategorized model outperformed the categorized model based on the Mean Absolute Percentage Error (MAPE). The uncategorized LSTM model has the highest accuracy among all model types. Results show that the model has higher accuracy for port terminals that handle a specific type of vessel, compared to the port terminals that handle more than one vessel type. Six of seven commodity groups have a MAPE of less than 30% under the LSTM uncategorized model framework. The application of the model enables port authorities and stakeholders to make short-term capacity expansion and infrastructure investment decisions based on commodity volume.

We propose a novel machine learning (ML)-based approach to significantly reduce the run times of the optimality-based bound tightening (OBBT) algorithm for strengthening the convex relaxations of the non-convex Alternating Current Optimal Power Flow (AC-OPF) problem. While OBBT can yield near-global solutions via tight convex relaxations, its runtime remains a critical bottleneck on large-scale power grids. Our key contribution is a dynamic policy that selects smaller subsets of voltage magnitude and phase-angle difference variables for sequential bound tightening at every iteration of the OBBT algorithm. This ensures that the bound-tightening process remains adaptive, thereby circumventing the stalling in the optimality gap often observed with static, predetermined subsets (like in our previous work (Cengil in Electric Power Syst Res 212: 108275, 2022)). By leveraging historical load profiles to re-evaluate and rank variables dynamically, our proposed framework preserves the benefits of OBBT while significantly reducing computation time. Through a parallel implementation of the proposed OBBT algorithm, we observe an average speed-up of 9.3 × , with maximum improvement up to 20 × – relative to the conventional exhaustive OBBT – on a held-out set of benchmark instances that range in size up to 3,375 buses. To the best of our knowledge, this is the first ML-based OBBT approach to demonstrate such large-scale performance gains on realistic AC-OPF problems, offering a promising pathway toward more efficient global solutions in power system operations.

Bulk density is an important material property of biomass feedstocks, influencing handling, storage, transport costs, and conversion efficiency. In this study, predictive regression models for loose and tapped bulk densities of Alamo and Cave-in-Rock switchgrass are developed using a comprehensive dataset generated via calibrated bonded-sphere discrete element method (DEM) simulations. A key contribution of this study is the use of a DEM-based approach, which correlates density with moisture content and particle size distribution parameters and enables analysis across a continuous particle size range, overcoming limitations of purely experimental data. For comparison, regression models are also developed using only experimental data from pilot-scale runs at the Biomass Feedstock National User Facility at Idaho National Laboratory. Validation against pilot-scale data showed reasonable prediction accuracy for both model types, particularly for smaller particle sizes (post-secondary grinding). While the experimental model showed slightly better performance matching the validation data in some cases, the DEM-based model benefits from a much larger dataset, reduced predictor multicollinearity, and continuous parameter coverage, highlighting the utility of validated simulation models for developing robust predictive tools for biomass preprocessing applications.

The focus of this research is to evaluate the use of drones for the delivery of pediatric vaccines in remote areas of low income and low and middle income countries. Delivering vaccines in these regions is challenging because of the inadequate road networks, and long transportation distances that make it difficult to maintain the cold chain integrity during transportation. We propose a mixed integer linear program to determine the location of drone hubs to facilitate the delivery of vaccines. The model considers the operational attributes of drones, vaccine wastage in the supply chain, cold storage and transportation capacities. We develop a case study using data from Niger to determine the impact of drone deliveries in improving vaccine availability in Niger. Our numerical analysis show an 0.71 to 2.21 increase in vaccine availability. These improvements depend on the available budget to build drone hubs and purchase drones, and the population density in the region of study.

Effective and efficient scheduling of vaccine distribution can significantly impact vaccine uptake, which is critical to controlling the spread of infectious diseases. Ineffective scheduling can lead to waste, delays, and low vaccine coverage, potentially weakening the efforts to protect the public. Organizations such as UNICEF (United Nations Children's Fund), PAHO (Pan American Health Organization), and GAVI (Gavi, the Vaccine Alliance) coordinate vaccine tenders to ensure that enough supply is available on the international market at the lowest possible prices. Scheduling vaccine tenders over a planning horizon in a way that is equitable, efficient, and accessible is a complex problem that involves trade-offs between multiple objectives while ensuring that vaccine availability, demand, and logistical constraints are met. The current method for scheduling tenders is generally reactive and over short planning horizons. Vaccine tenders are scheduled when supply is insufficient to cover demand. We propose an optimization model to dynamically and proactively generate vaccine tender schedules over long planning horizons. This model helps us address the following research questions: What should the optimal sequencing and scheduling of vaccine tenders be to enhance affordability and profit over long time horizons? What is the optimal tender procurement schedule for single or multiple antigen scenarios? We use several real-life data sources to validate the model and address our research questions. Results from our analysis show when to schedule vaccine tenders, what volumes manufacturers should commit to, and the optimal tender lengths to satisfy demand. We show that vaccine tenders tend towards maximum lengths, generally converge over long time horizons, and are robust to changes in varying conditions.

Background: The COVID-19 pandemic triggered policy changes in 2020 that allowed insurance companies to reimbursetelehealth services, leading to increased telehealth use, especially in rural and underserved areas. However, with many emergencyrules ending in 2022, patients and health care providers face potential challenges in accessing these services. Objective: This study analyzed telehealth use across specialties in Arkansas before and after the pandemic (2017-2022) usingdata from electronic medical records from the University of Arkansas for Medical Sciences Medical Center. We explored trendsin insurance coverage for telehealth visits and developed metrics to compare the performance of telehealth versus in-person visitsacross various specialties. The results inform insurance coverage decisions for telehealth services. Methods: We used pre- and postpandemic data to determine the impacts of the COVID-19 pandemic and changes inreimbursement policies on telehealth visits. We proposed a framework to calculate 3 appointment metrics: indirect waiting time,direct waiting time, and appointment length. Statistical analysis tools were used to compare the performance of telehealth andin-person visits across the following specialties: obstetrics and gynecology, psychiatry, family medicine, gerontology, internalmedicine, neurology, and neurosurgery. We used data from approximately 4 million in-person visits and 300,000 telehealth visitscollected from 2017 to 2022. Results: Our analysis revealed a statistically significant increase in telehealth visits across all specialties (P<.001), showing an89% increase from 51,589 visits in 2019 to 97,461 visits in 2020, followed by a 21% increase to 117,730 visits in 2021. Around92.57% (134,221/145,001) of telehealth patients from 2020 to 2022 were covered by Medicare, Blue Crossand Blue Shield,commercial and managed care, Medicaid, and Medicare Managed Care. In-person visits covered by Medicareand Medicaiddecreased by 15%, from 313,196 in 2019 to 264,696 in 2022. During 2020 to 2022, about 22.84% (33,123/145,001) of totaltelehealth visits during this period were covered by Medicareand 53.58% (86,317/161,092) were in psychiatry, obstetrics andgynecology, and family medicine. We noticed a statistically significant decrease (P<.001) in the average indirect waiting time fortelehealth visits, from 48.4 to 27.7 days, and a statistically significant reduction in appointment length, from 93.2 minutes in 2020to 39.59 minutes in 2022. The indirect waiting time for psychiatrytelehealth visits was almost 50% shorter than that for in-personvisits. These findings highlight the potential benefits of telehealth in providing access to health care, particularly for patientsneeding psychiatric care. Conclusions: Reverting to prepandemic regulations could negatively affect Arkansas, where many live in underserved areas.Our analysis shows that telehealth use remained stable beyond 2020, with psychiatryvisits continuing to grow. These findingsmay guide insurance and policy decisions in Arkansas and other regions facing similar access challenges.

Vaccines have proven effective in mitigating the threat of severe infections and deaths during outbreaks of infectious diseases. However, vaccine hesitancy (VH) complicates disease spread prediction and healthcare resource assessment across regions and populations. We propose a modeling framework that integrates an epidemiological compartmental model that captures the spread of an infectious disease within a multi-stage stochastic program (MSP) that determines the allocation of critical resources under uncertainty. The proposed compartmental MSP model adaptively manages the allocation of resources to account for changes in population behavior toward vaccines (i.e., variability in VH), the unique patterns of disease spread, and the availability of healthcare resources over time and space. The compartmental MSP model allowed us to analyze the price of fairness in resource allocation. Using real COVID-19 vaccination and healthcare resource data from Arkansas, U.S. (January-May 2021), our findings include: (i) delaying the initial deployment of additional ventilators by one month could lead to an average increase in the expected number of deaths by 285.41/month, highlighting the importance of prompt action; (ii) each additional ventilator in the initial stockpile and in supply leads to a decrease in the expected number of deaths by 1.09/month and 0.962/month, respectively, emphasizing the importance of maintaining a large stockpile and scalable production response; (iii) the cost of ensuring equitable resource allocation varies over time and location, peaking during the peak of a disease outbreak and in densely populated areas. This study emphasizes the importance of flexible, informed public health decision-making and preparedness, providing a model for effective resource allocation in public health emergencies.

INTRODUCTION:Many patients used telehealth services during the COVID-19 pandemic. In this study, we evaluate how different factors have affected telehealth utilization in recent years. Decision makers at the federal and state levels can use the results of this study to inform their healthcare-related policy decisions. METHODS:We implemented data analytics techniques to determine the factors that explain the use of telehealth by developing a case study using data from Arkansas. Specifically, we built a random forest regression model which helps us identify the important factors in telehealth utilization. We evaluated how each factor impacts the number of telehealth patients in Arkansas counties. RESULTS:Of the 11 factors evaluated, five are demographic, and six are socioeconomic factors. Socioeconomic factors are relatively easier to influence in the short term. Based on our results, broadband subscription is the most important socioeconomic factor and population density is the most important demographic factor. These two factors were followed by education level, computer use, and disability in terms of their importance as it relates to telehealth use. DISCUSSION:Based on studies in the literature, telehealth has the potential to improve healthcare services by improving doctor utilization, reducing direct and indirect waiting times, and reducing costs. Thus, federal and state decision makers can influence the utilization of telehealth in specific locations by focusing on important factors. For example, investments can be made to increase broadband subscriptions, education levels, and computer use in targeted locations.

BackgroundThe COVID-19 pandemic triggered policy changes in 2020 that allowed insurance companies to reimburse telehealth services, leading to increased telehealth use, especially in rural and underserved areas. However, with many emergency rules ending in 2022, patients and health care providers face potential challenges in accessing these services. ObjectiveThis study analyzed telehealth use across specialties in Arkansas before and after the pandemic (2017-2022) using data from electronic medical records from the University of Arkansas for Medical Sciences Medical Center. We explored trends in insurance coverage for telehealth visits and developed metrics to compare the performance of telehealth versus in-person visits across various specialties. The results inform insurance coverage decisions for telehealth services. MethodsWe used pre- and postpandemic data to determine the impacts of the COVID-19 pandemic and changes in reimbursement policies on telehealth visits. We proposed a framework to calculate 3 appointment metrics: indirect waiting time, direct waiting time, and appointment length. Statistical analysis tools were used to compare the performance of telehealth and in-person visits across the following specialties: obstetrics and gynecology, psychiatry, family medicine, gerontology, internal medicine, neurology, and neurosurgery. We used data from approximately 4 million in-person visits and 300,000 telehealth visits collected from 2017 to 2022. ResultsOur analysis revealed a statistically significant increase in telehealth visits across all specialties (P<.001), showing an 89% increase from 51,589 visits in 2019 to 97,461 visits in 2020, followed by a 21% increase to 117,730 visits in 2021. Around 92.57% (134,221/145,001) of telehealth patients from 2020 to 2022 were covered by Medicare, Blue Cross and Blue Shield, commercial and managed care, Medicaid, and Medicare Managed Care. In-person visits covered by Medicare and Medicaid decreased by 15%, from 313,196 in 2019 to 264,696 in 2022. During 2020 to 2022, about 22.84% (33,123/145,001) of total telehealth visits during this period were covered by Medicare and 53.58% (86,317/161,092) were in psychiatry, obstetrics and gynecology, and family medicine. We noticed a statistically significant decrease (P<.001) in the average indirect waiting time for telehealth visits, from 48.4 to 27.7 days, and a statistically significant reduction in appointment length, from 93.2 minutes in 2020 to 39.59 minutes in 2022. The indirect waiting time for psychiatry telehealth visits was almost 50% shorter than that for in-person visits. These findings highlight the potential benefits of telehealth in providing access to health care, particularly for patients needing psychiatric care. ConclusionsReverting to prepandemic regulations could negatively affect Arkansas, where many live in underserved areas. Our analysis shows that telehealth use remained stable beyond 2020, with psychiatry visits continuing to grow. These findings may guide insurance and policy decisions in Arkansas and other regions facing similar access challenges.

Reluctance or refusal to get vaccinated, commonly known as Vaccine Hesitancy (VH), poses a significant challenge to COVID-19 vaccination campaigns. Understanding the factors contributing to VH is essential for shaping effective public health strategies. This study proposes a novel framework for combining machine learning with publicly available data to generate a proxy metric that evaluates the dynamics of VH faster than the currently used survey methods. The metric is input to descriptive classification models that analyze a wide array of data, aiming to identify key factors associated with VH at the county level in the U.S. during the COVID-19 pandemic (i.e., January to October 2021). Both static and dynamic factors are considered. We use a Random Forest classifier that identifies political affiliation and Google search trends as the most significant factors influencing VH behavior. The model categorizes U.S. counties into five distinct clusters based on VH behavior. Cluster 1, with low VH, consists mainly of Democratic-leaning residents who, have the longest life expectancy, have a college degree, have the highest income per capita, and live in metropolitan areas. Cluster 5, with high VH, is predominantly Republican-leaning individuals in non-metropolitan areas. Individuals in Cluster 1 is more responsive to vaccination policies.

The COVID-19 pandemic highlighted significant challenges in the allocation of vital healthcare resources. Existing epidemiological models, specifically compartmental models, aimed to predict the spread of the COVID-19 virus and its impact on the population, but they overlooked the influence of VH on disease dynamics, including the expected number of hospitalizations and fatalities. We propose improvements to the SEIR model for COVID-19 by incorporating the influence of vaccination, VH, and resource availability on the disease dynamics. We collect publicly available data and perform data analysis to capture VH dynamic changes over time and develop scenario paths for VH. We simulate the proposed compartmental model for each VH path to explain the impacts of public attitudes toward vaccination, the impacts of healthcare resources on patient outcomes, and the timing of vaccination rollout on the progression and severity of the epidemic. Our analysis demonstrates that reducing VH improves health outcomes, reinforcing the importance of addressing VH to curb the spread of infectious diseases. Our results show that adequate levels of critical healthcare resources are crucial for minimizing fatalities and also highlight the life-saving impact of timely and effective vaccination programs.

Millions of young people are not immunized in low income (LI) and lower middle income (LMI) countries because of low vaccine availability resulting from inefficiencies in cold supply chains. We create supply chain network design and distribution models to address the unique characteristics and challenges facing vaccine supply chains in LI and LMI countries. The models capture the uncertainties of demand for vaccinations and the resulting impacts on immunization, the unique challenges of vaccine administration (such as open vial wastage), the interactions between technological improvements of vaccines and immunizations, and the trade-offs between immunization coverage rates and available resources. The objective is to maximize both the percentage of fully immunized children and the vaccine availability in clinics. Our research examines how these two metrics are affected by three factors: number of tiers in the supply chain, vaccine vial size, and new vaccine technologies. We tested the model using Niger’s Expanded Program on Immunization, which is sponsored by the World Health Organization. We make many observations and recommendations to help LMI countries increase their immunization coverage.

This paper investigates inland port infrastructure investment planning under uncertain commodity demand conditions. A two-stage stochastic optimization is developed to model the impact of demand uncertainty on infrastructure planning and transportation decisions. The two-stage stochastic model minimizes the total expected costs, including the capacity expansion investment costs associated with handling equipment and storage, and the expected transportation costs. To solve the problem, an accelerated Benders decomposition algorithm is implemented. The Arkansas section of the McCllean-Kerr Arkansas River Navigation System (MKARNS) is used as a testing ground for the model. Results show that commodity volume and, as expected, the percent of that volume that moves via waterways (in ton-miles) increases with increasing investment in port infrastructure. The model is able to identify a cluster of ports that should receive investment in port capacity under any investment scenario. The use of a stochastic approach is justified by calculating the value of the stochastic solution (VSS).

This research is motivated by the challenges faced during biomass processing in bioenergy plants. It has been observed that variations in biomass characteristics, such as moisture, ash, and carbohydrate contents cause variations in feeding of the system which led to underutilization of equipment and the reactor. The objective of this research is to ensure a continuous flow of biomass to the reactor in plants that use the biochemical conversion process to generate liquid fuels. The overall goal is to lower the cost of producing biofuels, which could lead to improving US’s energy independency and growing US’s rural economy. The research team developed analytical models, such as discrete element method (DEM) models and mathematical models. The DEM models are unit-level models that explicitly capture biomass characteristics and quantify the impacts of biomass characteristics on bulk material properties and the performance of specific equipment. The mathematical models are system-level models that capture the impacts of system infeed rate, equipment processing rate, storage location and capacity, and biomass characteristics on system throughput. The functional relations predicting the bulk material properties from DEM models are incorporated to the mathematical models. The models developed were validated and evaluated using data collected at Idaho National Laboratory’s biomass processing facility. Via these models, we identified process control strategies that ensure a continuous flow of biomass to the reactor, while meeting the requirements of biochemical conversion process. Our analysis indicates that sequencing of biomass bales based on moisture level, and carbohydrate contents could have a positive impact on reducing processing time and inventory level and increasing throughput rate. Short bale sequences that repeat frequently, seem to have the greatest impact on improving system’s performance. Based on our experiments, the total annual system operating costs reduced by 20-30%, and the maximum inventory level reduced by 3 to 4 times. The operating costs include the annual equipment amortization cost and processing cost. The implementation of the models developed requires the use of standardized bale format, Radio Frequency Identification technology, sensing and real time monitoring of material attributes, automated material handling equipment, and automated process control. The scope of the model proposed can be extended to include the whole supply chain. The supply chain models help identify how many bales of different biomass feedstock to purchase given biomass availability in the region, biomass price and quality, and the biomass processing capabilities of the biorefinery. Thus, the outcomes of supply chain models can be used to inform the design of long-term contracts among farmers and the biorefinery.

Surgical procedures are the primary source of expenditures and revenues for hospitals. Accurate forecasts of the volume of surgical cases enable hospitals to efficiently deliver high-quality care to patients. We propose an algorithm to forecast the expected volume of surgical procedures using multivariate time-series data. This algorithm uses feature engineering techniques to determine factors that affect the volume of surgical cases, such as the number of available providers, federal holidays, weather conditions, etc. These features are incorporated in a long short-term memory (LSTM) network to predict the number of surgical procedures in the upcoming week. The hyperparameters of this model are tuned via grid search and Bayesian optimization techniques. We develop and verify the model using historical data of daily case volume from 2014 to 2020 at an academic hospital in North America. The proposed model is validated using data from 2021. The results show that the proposed model can make accurate predictions six weeks in advance, and the average R2 = 0.855, RMSE = 2.017, MAE = 1.104. These results demonstrate the benefits of incorporating additional features to improve the model’s predictive power for time series forecasting.

The focus of this special issue of Optimization Letters is to highlight recent advances in operations research, systems analysis, and management science to the study of natural resources, environment, and sustainability.The goal is to share best practices that lead to sustainable management of natural resources, such as, forest, land, and agricultural products, which are vital for the wellbeing of humanity.This special issue contains 7 papers.The topics covered in these papers are forest planning and wildlife corridors (Yemshanov et al.), wildfire burn scar encapsulation (Durante et al.), planning for biomass cofiring (Dundar et al.), contract design for cellulosic biofuel enterprise (Tokcaer et al.), siting of renewable power generation assets (Berger et al.), process optimization in integrated biorefinery (Gulcan et al.), and refueling station location problem (Abbaas and Ventura).We would like to thank the authors for their submissions, and the reviewers for their timely and constructive feedback during the editing process.We also would like to thank the Editors-in-Chief of Optimization Letters, Dr. O. Prokopyev and Dr. Krokhmal for their continuous support.We hope that this special issue will lead to an improved understanding of pressing issues related to natural resources, and environment; and the development of sustainable solutions complex problems faced by our society.

We propose machine learning-based (ML) methods to accelerate convergence to global solutions for the AC Optimal Power Flow (AC-OPF) problem. In particular, for the non-convex AC-OPF problem, optimality-based bound tightening (OBBT) has been observed to be a very effective approach for tightening the variable domains, thus leading to tight convex relaxations that are nearly global optimum solutions. However, by construction, OBBT is computationally expensive even on medium-scaled power networks. To address this issue, we propose a novel ML-based policy to replace the exhaustive algorithm of OBBT by choosing a subset of variables whose tightening of bounds can still contribute to the best improvement of the convex relaxation of the AC-OPF problem. To this end, we leverage historical data of load profiles for a test system to learn a map between the system loading and subset selection of variables which will need to participate in the OBBT algorithm, thus enabling us to find near-global optimal solutions at faster run-times. Finally, we present detailed numerical studies on a few medium-sized benchmark instances, on which we observe up to 6.3x speed-up in OBBT run times.