Resource Allocation Decisions Research Articles

Data-driven decision making: Shaping the future of business efficiency and customer engagement

Data-driven decision-making (DDDM) is a critical approach that organizations are adopting to enhance their operational efficiency and customer engagement. This abstract explores the significance of DDDM in shaping the future of businesses. Data-driven decision-making (DDDM) is revolutionizing the way businesses operate and engage with customers. By leveraging data analytics, organizations can extract valuable insights to inform strategic decisions, improve operational efficiency, and enhance customer experiences. This abstract examines the role of DDDM in shaping the future of business efficiency and customer engagement. DDDM enables organizations to optimize their processes and resources through data analysis. By identifying patterns and trends in data, businesses can streamline operations, reduce costs, and improve productivity. For example, predictive analytics can help forecast demand, allowing businesses to adjust their inventory levels accordingly and avoid stockouts or overstock situations. Additionally, data-driven insights can inform resource allocation decisions, ensuring that resources are allocated efficiently to maximize returns. DDDM also plays a crucial role in enhancing customer engagement. By analyzing customer data, businesses can gain a deeper understanding of customer behavior, preferences, and needs. This enables businesses to tailor their products and services to better meet customer expectations, leading to higher customer satisfaction and loyalty. For example, personalized marketing campaigns based on customer data can significantly improve engagement and conversion rates. As the volume and complexity of data continue to grow, DDDM will become even more essential for businesses. Advancements in technology, such as artificial intelligence and machine learning, will further enhance the capabilities of DDDM, allowing businesses to derive even more value from their data. However, organizations must also address challenges such as data privacy and security to ensure that DDDM is implemented ethically and responsibly. In conclusion, DDDM is reshaping the future of business efficiency and customer engagement. By embracing DDDM, organizations can unlock the full potential of their data and gain a competitive edge in today's data-driven world.

Leveraging Emerging Technologies for Enhanced Airport Ground Movement Management Efficiency and Reliability

The Executive summary serves to give the highlights of the research paper and an overview of the objectives, methods used, key findings and implications. It is a brief rundown of the whole research document and provides time-pressed readers with some insights onto the study without having to go into deeper details. Introduction: This research paper examines how blockchain, edge computing and autonomous systems can be integrated inside airports in order to enhance performance and reliability of airport ground movement management. There is need for innovative approaches towards optimizing ground movement in highly complex airports to ensure that they operate seamlessly in a growing air traffic scenario. Objectives: The main aim of this study is to explore how blockchain, edge computing and autonomous systems could change airport ground movement management entirely. These technologies will be exploited for improving data sharing, enhancing real-time processing capabilities as well as enabling automatic decision support services on the ground operations. Methodology: In this case a mixed method approach has been used which involves qualitative and quantitative analysis. Qualitative methods like surveys and questionnaires are done so as researchers get insights from different stakeholders, Integrating various stakeholders, including airlines, airports, and regulators, regarding their perspectives on integrating new technologies into ground movement management!!! Quantitative methods involve data analysis to assess the effectiveness and efficiency of proposed technological solutions. Additionally, simulations and case studies are conducted to evaluate the impact of these technologies on ground movement optimization. Key Findings: The research yields promising results, indicating significant improvements in routing efficiency, reduced taxiing times, and increased operational reliability. The integration of blockchain facilitates secure data sharing, while edge computing enables real-time processing, leading to faster decision-making in ground movement management! Autonomous systems contribute to optimizing resource routing and allocation decisions, further enhancing operational efficiency. Implications and Recommendations: The findings of the research carry both theoretical and practical implications. Theoretical implications include advancing knowledge in the field of airport ground movement management by exploring the potential of emerging technologies. On a practical level, the research provides valuable insights for airport stakeholders seeking to modernize their ground movement control systems?? Recommendations include addressing the complexity of integrating multiple emerging technologies and overcoming challenges related to data security and system interoperability. Conclusion: In conclusion, the research underscores the significance of integrating blockchain, edge computing, and autonomous systems into airport traffic management to enhance efficiency and reliability!!! By addressing key challenges in ground movement management, the study paves the way for more streamlined and resilient airport operations, ultimately benefiting the aviation industry as a whole.

Needs assessment in long-term care: expression of national principles for priority setting in service allocation

BackgroundLong-term care services for older adults are characterised by increasing needs and scarce resources. Political strategies have led to the reorganisation of long-term care services, with an increased focus on “ageing in place” and efficient use of resources. There is currently limited research on the processes by which resource allocation decisions are made by service allocators of long-term care services for older adults. The aim of this study is to explore how three political principles for priority setting in long-term care, resource, severity and benefit, are expressed in service allocation to older adults.MethodsThis qualitative study uses data from semi-structured individual interviews, focus groups and observations of service allocators who assess needs and assign long-term care services to older adults in Norway. The data were supplemented with individual decision letters from the allocation office, granting or denying long-term care services. The data were analysed using reflexive thematic analysis.ResultsThe allocators drew on all three principles for priority setting when assessing older adults’ long-term care needs and allocating services. We found that the three principles pushed in different directions in the allocation process. We identified six themes related to service allocators’ expression of the principles: (1) lowest effective level of care as a criterion for service allocation (resource), (2) blanket allocation of low-cost care services (resource), (3) severity of medical and rehabilitation needs (severity), (4) severity of care needs (severity), (5) benefit of generous service allocation (benefit) and (6) benefit of avoiding services (benefit).ConclusionsThe expressions of the three political principles for priority setting in long-term care allocation are in accordance with broader political trends and discourses regarding “ageing in place”, active ageing, an investment ideology, and prioritising those who are “worse off”. Increasing attention to the rehabilitation potential of older adults and expectations that they will take care of themselves increase the risk of not meeting frail older adults’ care needs. Additionally, difficulties in defining the severity of older adults’ complex needs lead to debates regarding “worse off” versus potentiality in future long-term care services allocation.Trial registrationNot applicable.

Multi-objective comprehensive container scheduling and resource allocation for container cloud using tuna swarm optimization algorithm

The paper addresses the optimization challenges in cloud resource task execution within the container paradigm, introducing the Multi-Objective Comprehensive Container Scheduling and Resource Allocation (MOCCSRA) scheme. It aims to enhance cost-effectiveness and efficiency by utilizing the Tuna Swarm Optimization (TSO) technique to optimize task planning and resource allocation. This novel approach considers various objectives for task scheduling optimization, including energy efficiency, compliance with service level agreements (SLAs), and quality of service (QoS) metrics like CPU utilization, memory usage, data transmission time, container-VM correlation, and container grouping. Resource allocation decisions are guided by the VM cost and task completion period factors. MOCCSRA distinguishes itself by tackling the multi-objective optimization challenge for task scheduling and resource allocation, producing non-dominated Pareto-optimal solutions. It effectively identifies optimal tasks and matches them with the most suitable VMs for deploying containers, thereby streamlining the overall task execution process. Through comprehensive simulations, the results demonstrate MOCCSRA’s superiority over traditional container scheduling methods, showcasing reductions in resource imbalance and notable enhancements in response times. This research introduces an innovative and practical solution that notably advances the optimization field for cloud-based container systems, meeting the increasing demand for efficient resource utilization and enhanced performance in cloud computing environments.

Deep Reinforcement Learning-Based Task Offloading and Load Balancing for Vehicular Edge Computing

Vehicular edge computing (VEC) effectively reduces the computational burden on vehicles by offloading tasks from resource-constrained vehicles to edge nodes. However, non-uniformly distributed vehicles offloading a large number of tasks cause load imbalance problems among edge nodes, resulting in performance degradation. In this paper, we propose a deep reinforcement learning-based decision scheme for task offloading and load balancing with the optimization objective of minimizing the system cost considering the split offloading of tasks and the load dynamics of edge nodes. First, we model the mutual interaction between mobile vehicles and Mobile Edge Computing (MEC) servers using a Markov decision process. Second, the optimal task-offloading and resource allocation decision is obtained by utilizing the twin delayed deep deterministic policy gradient algorithm (TD3), and server load balancing is achieved through edge collaboration using a server selection algorithm based on the technique for order preference by similarity to the ideal solution (TOPSIS). Finally, we have conducted extensive simulation experiments and compared the results with several other baseline schemes. The proposed scheme can more effectively reduce the system cost and increase the system resource utilization.

Verification report: Egalitarianism in young children

AbstractThe present study sought to evaluate the reproducibility of prominent findings stated by Fehr et al. in their developmental resource allocation experiment "Egalitarianism in Young Children", published in 2008. The experiment involved children making decisions about distributing sweets between themselves and either an in‐group or an out‐group recipient. Fehr et al. found that (1) inequity aversion develops with age; (2) 3‐ to 4‐year‐old children are inclined toward self‐advantageous allocations, whereas 7‐ to 8‐year‐olds distribute sweets more evenly in divisions, and (3) the influence of group status increases as children age. The original article stated that 229 Swiss school students aged 3 to 8 years (102 boys, 127 girls) participated in the study. However, no further demographics were reported. In our attempts to reproduce Fehr et al.'s original analyses and reanalyse the raw dataset, we found that one of the key variables was miscoded. After rectifying the miscoded variable, the reproduction results revealed only one ambiguously irreproducible result regarding a group status main effect in the sharing mini‐game—with three other tests exhibiting either strong reproducibility or ambiguous reproducibility. Reanalysis results indicated that Fehr et al.'s conclusions are robust when tested with alternative analytical tests.Highlights We evaluated the reproducibility of Fehr et al.'s (2008) highly cited developmental resource allocation findings. After identifying an inversely coded variable, we found all tests—bar one probit regression not related to major findings—to be reproducible. Reanalysis confirmed the robustness of Fehr et al.'s conclusions when using alternate analytical methods. Fehr et al.'s developmental resource allocation findings are reproducible and have theoretical implications for understanding inequity aversion and group status effects on resource allocation decisions in young children.

A Review: A Comparative Study of Branded and Generic Anti- Diabetic Drugs

This comprehensive review investigates the market landscape of antihypertensive medications, undertaking a detailed comparative analysis of branded and generic options. In the face of rising global prevalence of hypertension, the study aims to provide a holistic perspective on the efficacy, safety, and market dynamics shaping the use of branded and generic drugs in the management of these chronic conditions. Utilizing data derived from market trends, sales analytics, and consumer preferences, the review scrutinizes the market behaviors and forces influencing the adoption of branded and generic antihypertensive drugs. Factors such as cost-effectiveness, patient adherence, and healthcare provider preferences are explored to shed light on the complexities associated with medication selection in the context of chronic disease management. Through an in-depth examination of industry strategies, regulatory frameworks, and the role of healthcare policies, the review aims to uncover the interplay between market dynamics and clinical considerations. It seeks to inform healthcare professionals, policymakers, and industry stakeholders about the evolving landscape of choices in antihypertensive therapies, fostering a nuanced understanding that can guide optimal decision-making in patient care and resource allocation.

A Review: A Comparative Study of Branded and Generic Anti-Hypertensive Drugs

This comprehensive review investigates the market landscape of antihypertensive medications, undertaking a detailed comparative analysis of branded and generic options. In the face of rising global prevalence of hypertension, the study aims to provide a holistic perspective on the efficacy, safety, and market dynamics shaping the use of branded and generic drugs in the management of these chronic conditions. Utilizing data derived from market trends, sales analytics, and consumer preferences, the review scrutinizes the market behaviors and forces influencing the adoption of branded and generic antihypertensive drugs. Factors such as cost-effectiveness, patient adherence, and healthcare provider preferences are explored to shed light on the complexities associated with medication selection in the context of chronic disease management. Through an in-depth examination of industry strategies, regulatory frameworks, and the role of healthcare policies, the review aims to uncover the interplay between market dynamics and clinical considerations. It seeks to inform healthcare professionals, policymakers, and industry stakeholders about the evolving landscape of choices in antihypertensive therapies, fostering a nuanced understanding that can guide optimal decision-making in patient care and resource allocation.

A Blueprint for Multi-use Disease Modeling in Health Economics: Results from Two Expert-Panel Consultations.

The current use of health economic decision models in HTA is mostly confined to single use cases, which may be inefficient and result in little consistency over different treatment comparisons, and consequently inconsistent health policy decisions, for the same disorder. Multi-use disease models (MUDMs) (other terms: generic models, whole disease models, disease models) may offer a solution. However, much is uncertain about their definition and application. The current research aimed to develop a blueprint for the application of MUDMs. We elicited expert opinion using a two-round modified Delphi process. The panel consisted of experts and stakeholders in health economic modelling from various professional backgrounds. The first questionnaire concerned definition, terminology, potential applications, issues and recommendations for MUDMs and was based on an exploratory scoping review. In the second round, the panel members were asked to reconsider their input, based on feedback regarding first-round results, and to score issues and recommendations for priority. Finally, adding input from external advisors and policy makers in a structured way, an overview of issues and challenges was developed during two team consensus meetings. In total, 54 respondents contributed to the panel results. The term 'multi-use disease models' was proposed and agreed upon, and a definition was provided. The panel prioritized 10 potential applications (with comparing alternative policies and supporting resource allocation decisions as the top 2), while 20 issues (with model transparency and stakeholders' roles as the top 2) were identified as challenges. Opinions on potential features concerning operationalization of multi-use models were given, with 11 of these subsequently receiving high priority scores (regular updates and revalidation after updates were the top 2). MUDMs would improve on current decision support regarding cost-effectiveness information. Given feasibility challenges, this would be most relevant for diseases with multiple treatments, large burden of disease and requiring more complex models. The current overview offers policy makers a starting point to organize the development, use, and maintenance of MUDMs and to support choices concerningwhich diseases and policy decisions they will be helpful for.

Energy-Delay Joint Optimization for Task Offloading in Digital Twin-Assisted Internet of Vehicles

Vehicle edge computing (VEC) provides efficient services for vehicles by offloading tasks to edge servers. Notably, extant research mainly employs methods such as deep learning and reinforcement learning to make resource allocation decisions, without adequately accounting for the ramifications of high-speed mobility of vehicles and the dynamic nature of the Internet of Vehicles (IoV) on the decision-making process. This paper endeavours to tackle the aforementioned issue through the introduction of a novel concept, namely, a digital twin-assisted IoV. Among them, the digital twin of IoV offers training data for computational offloading and content caching decisions, which allows edge servers to directly interact with the dynamic environment while capturing its dynamic changes in real-time. Through this collaborative endeavour, edge intelligent servers can promptly respond to vehicular requests and return results. We transform the dynamic edge computing problem into a Markov decision process (MDP), and then solve it with the twin delayed deep deterministic policy gradient (TD3) algorithm. Simulation experiments demonstrate the adaptability of our proposed approach in the dynamic environment while successfully enhancing the Quality of Service, that is, decreasing total delay and energy consumption.

Dynamic Management of Flexibility in Distribution Networks through Sensitivity Coefficients

Due to a rising share of renewable energy sources on the production side and electrification of transport and heating on the consumption side, the efficient management of flexibility in distribution networks is crucial for ensuring optimal operation and utilization of resources. Nowadays, the sensitivity-based approach is mainly used in medium-voltage (MV) networks for regulating voltage profiles with reactive power of distributed energy resources (DER). The main disadvantage of the simplified sensitivity-based method is its inaccuracy in case of a high deviation of the network voltage from the nominal values. Furthermore, it was also noted that despite the fact that the method is well described in the literature, there is a lack of systematic approach to its implementation in real-life applications. Thus, the main objective of this paper is to address this disadvantage and to propose an algorithm designed to calculate required consumer flexibility in near real-time to ensure distribution grid operation within operational criteria. In the first part of the paper, network state, including line loading and node voltages, is assessed to determine distribution network node capacity. By analyzing the sensitivity of network busbars to changes in consumption and production, our algorithm effectively identifies the most efficient nodes and facilitates strategic decision-making for resource allocation. We demonstrate the effectiveness of our approach through simulations of real-world distribution network data, highlighting its ability to enhance network flexibility and improve resource utilization. Leveraging sensitivity coefficients, the algorithm enables flexible consumption and production management across various scenarios, supporting the transition to a more dynamic and efficient power system.

The influence of farm resources and management decisions on the severity of Striga infestation and maize productivity in western Kenya

AbstractThe control of Striga is of critical importance for smallholder farmers cultivating maize and other cereals in the western region of Kenya. Therefore, advanced knowledge and analysis is needed to understand farmers' resource endowment and decision making with regards to crop management, and the possible effect on Striga infestation and crop productivity. The overall objective of the study was to understand the role of resource endowment and allocation decisions on Striga infestation and maize productivity and offer effective and locally adapted options in western Kenya. The study used semi‐structured questionnaires, focus group discussions and resource flow mapping to identify farm resources and key management decisions that are critical in management of Striga on smallholder farms. Soil was sampled from fields of selected farms and taken to the laboratory for analysis including Striga seed counts. In the fields, Striga shoots counts, and maize yield were recorded. Socio‐economic variables such as land size, household income, labour availability, were used to construct a farm typology and assign farmers to different resource groups (RGs). Our results showed that household diversity leads to different land‐use patterns, resource‐use intensity and agricultural management practices which affect soil fertility and Striga infestation. Poor‐resourced farmers tend to be associated with poor crop and soil management which results in maize fields with low soil fertility and high level of Striga infestation. Soil organic carbon showed a strong negative association with Striga infestation. Improving soil fertility is, therefore, the central component of any integrated and sustainable Striga management approaches, and technological solutions to address Striga and soil fertility issues, and they must be tailored to the farm and field diversity. The inclusion of legumes is highly recommended either as rotation or intercropping depending on land availability. Where possible, farmers may use mulch from previous crop residues to suppress weed emergence and prevent flowering and seed setting. Hand weeding though tiresome, remains a low‐cost effective method to control Striga especially in areas where fields are small as in western Kenya.

Joint Service Caching, Resource Allocation and Task Offloading for MEC-Based Networks: A Multi-Layer Optimization Approach

To provide reliable and elastic Multi-access edge computing services, one feasible solution is to federate geographically proximate edge servers to form a logically centralized resource pool. Optimization of such systems, however, becomes challenging. In this paper, we study the problem of maximizing users' QoE in a MEC-based network, through jointly optimizing service caching, resource allocation and task offloading decisions. We formulate a mixed-integer nonlinear programming (MINLP) problem for the task and establish its NP-hardness. To tackle it efficiently, we propose a novel two-stage algorithmic solution based on approximation and decomposition theory. The proposed algorithm achieves high system performance while at the same time, ensures all constraints from different layers are satisfied. Meanwhile, the structure of the algorithm also fits the multi-layer optimizing feature, making it suitable to be implemented at different layers. In addition, we propose a distributed and online version of our mechanism with very limited information exchange between MEC servers, and further demonstrate how the cost of service switches from real MEC systems can be incorporated into our framework. We evaluate our mechanisms through simulations with both synthetic and real-world traces, and results indicate they are effective as compared to representative baseline algorithms.

Isolated Forest-Based Prediction of Container Resource Load Extremes

Given the wide application of container technology, the accurate prediction of container CPU usage has become a core aspect of optimizing resource allocation and improving system performance. The high volatility of container CPU utilization, especially the uncertainty of extreme values of CPU utilization, is challenging to accurately predict, which affects the accuracy of the overall prediction model. To address this problem, a container CPU utilization prediction model, called ExtremoNet, which integrates the isolated forest algorithm, and classification sub-models are proposed. To ensure that the prediction model adequately takes into account critical information on the CPU utilization’s extreme values, the isolated forest algorithm is introduced to compute these anomalous extreme values and integrate them as features into the training data. In order to improve the recognition accuracy of normal and extreme CPU utilization values, a classification sub-model is used. The experimental results show that, on the AliCloud dataset, the model has an R2 of 96.51% and an MSE of 7.79. Compared with the single prediction models TCN, LSTM, and GRU, as well as the existing combination models CNN-BiGRU-Attention and CNN-LSTM, the model achieves average reductions in the MSE and MAE of about 38.26% and 23.12%, proving the effectiveness of the model at predicting container CPU utilization, and provides a more accurate basis for resource allocation decisions.

Fast multi-type resource allocation in local-edge-cloud computing for energy-efficient service provision

With the advancement of information technology, the concept of local-edge-cloud computing has gained prominence. Operating on a collaborative model, heterogeneous computing nodes converge to deliver a spectrum of multi-type services, including calculation-intensive, latency-sensitive, and privacy-requiring services. This collaborative approach fosters high-quality development in power economy. However, the proliferation of heterogeneous computing nodes, while beneficial, introduces challenges. The intricate connections and limited energy supply may lead to interruptions in the service processes of nodes. In this study, we present an energy-efficient resource allocation scheme designed for low-latency multi-type service provision within a local-edge-cloud collaboration. Our methodology focuses on optimizing the performance of multi-type service provision in a local-edge-cloud network, taking into account considerations such as latency, resource allocation, and energy consumption. To accomplish this, we employ the Alopex-based Differential Evolution algorithm. Initially, we construct three sub-models to analyze latency and energy aspects across various computing modes. Subsequently, we formulate a constrained optimization problem aimed at minimizing both latency and energy consumption in multi-type service provisioning. These models seek to derive optimal resource allocation decisions for the given scenario. To address this optimization problem, we introduce the hybrid differential evolution algorithm, Alopex-DE. A formal analysis is conducted to showcase its near-optimal performance in comparison to three state-of-the-art algorithms. Additionally, extensive simulations are carried out to validate the superior effectiveness of our proposed approach.

Cost-effectiveness analysis of minimally invasive surgical treatments for benign prostatic hyperplasia: implications for Japan’s public healthcare system

Aims Benign prostatic hyperplasia (BPH) represents a significant public health issue in Japan. This study evaluated the lifetime cost-effectiveness of water vapor energy therapy (WAVE) versus prostatic urethral lift (PUL) for men with moderate-to-severe BPH from a public healthcare payer’s perspective in Japan. Materials and methods A decision analytic model compared WAVE to PUL among males in Japan. Clinical effectiveness and adverse event (AE) inputs were obtained from a systematic literature review. Resource utilization and cost inputs were derived from the Medical Data Vision database and medical service fee national data in Japan. Experts reviewed and validated model input parameters. One-way and probabilistic sensitivity analyses were conducted to determine how changes in the values of uncertain parameters affect the model results. Results Throughout patients’ lifetimes, WAVE was associated with higher quality-adjusted life years (0.920 vs. 0.911 year 1; 15.564 vs. 15.388 lifetime) and lower total costs (¥734,134 vs. ¥888,110 year 1; ¥961,595 vs. ¥1,429,458 lifetime) compared to PUL, indicating that WAVE is a more effective and less costly (i.e. dominant) treatment strategy across all time horizons. Lifetime cost-savings for the Japanese healthcare system per patient treated with WAVE instead of PUL were ¥467,863. The 32.7% cost difference between WAVE and PUL was predominantly driven by lower WAVE surgical retreatment rates (4.9% vs. 19.2% for WAVE vs PUL, respectively, at 5 years) and AE rates (hematuria 11.8% vs. 25.7%, dysuria 16.9% vs. 34.3%, pelvic pain 2.9% vs. 17.9%, and urinary incontinence 0.4% vs. 1.3% for WAVE vs PUL, respectively, at 3 months). Model findings were robust to changes in parameter input values. Limitations The model represents a simplification of complex factors involved in resource allocation decision-making. Conclusions Driven by lower retreatment and AE rates, WAVE was a cost-effective and cost-saving treatment for moderate-to-severe BPH in Japan compared to PUL, providing better outcomes at lower costs to the healthcare system.

An Interactive Modeling Tool for Projecting the Health and Direct Medical Cost Impact of Changes in the Sexually Transmitted Diseases Prevention Program Budgets.

Estimating the return on investment for public health services, tailored to the state level, is critical for demonstrating their value and making resource allocation decisions. However, many health departments have limited staff capacity and expertise to conduct economic analyses in-house. We developed a user-friendly, interactive Excel-based spreadsheet model that health departments can use to estimate the impact of increases or decreases in sexually transmitted infection (STI) prevention funding on the incidence and direct medical costs of chlamydia, gonorrhea, syphilis, and STI-attributable HIV infections. Users tailor results to their jurisdictions by entering the size of their population served; the number of annual STI diagnoses; their prior annual funding amount; and their anticipated new funding amount. The interface was developed using human-centered design principles, including focus groups with 15 model users to collect feedback on an earlier model version and a usability study on the prototype with 6 model users to finalize the interface. The STI Prevention Allocation Consequences Estimator ("SPACE Monkey 2.0") model will be publicly available as a free downloadable tool. In the usability testing of the prototype, participants provided overall positive feedback. They appreciated the clear interpretations, outcomes expressed as direct medical costs, functionalities to interact with the output and copy charts into external applications, visualization designs, and accessible information about the model's assumptions and limitations. Participants provided positive responses to a 10-item usability evaluation survey regarding their experiences with the prototype. Modeling tools that synthesize literature-based estimates and are developed with human-centered design principles have the potential to make evidence-based estimates of budget changes widely accessible to health departments.

Is it possible to estimate the number of patients with COVID-19 admitted to intensive care units and general wards using clinical and telemedicine data?

Gabaldi et al. utilized telemedicine data, web search trends, hospitalized patient characteristics, and resource usage data to estimate bed occupancy during the COVID-19 pandemic. The results showcase the potential of data-driven strategies to enhance resource allocation decisions for an effective pandemic response. To develop and validate predictive models to estimate the number of COVID-19 patients hospitalized in the intensive care units and general wards of a private not-for-profit hospital in São Paulo, Brazil. Two main models were developed. The first model calculated hospital occupation as the difference between predicted COVID-19 patient admissions, transfers between departments, and discharges, estimating admissions based on their weekly moving averages, segmented by general wards and intensive care units. Patient discharge predictions were based on a length of stay predictive model, assessing the clinical characteristics of patients hospitalized with COVID-19, including age group and usage of mechanical ventilation devices. The second model estimated hospital occupation based on the correlation with the number of telemedicine visits by patients diagnosed with COVID-19, utilizing correlational analysis to define the lag that maximized the correlation between the studied series. Both models were monitored for 365 days, from May 20th, 2021, to May 20th, 2022. The first model predicted the number of hospitalized patients by department within an interval of up to 14 days. The second model estimated the total number of hospitalized patients for the following 8 days, considering calls attended by Hospital Israelita Albert Einstein's telemedicine department. Considering the average daily predicted values for the intensive care unit and general ward across a forecast horizon of 8 days, as limited by the second model, the first and second models obtained R² values of 0.900 and 0.996, respectively and mean absolute errors of 8.885 and 2.524 beds, respectively. The performances of both models were monitored using the mean error, mean absolute error, and root mean squared error as a function of the forecast horizon in days. The model based on telemedicine use was the most accurate in the current analysis and was used to estimate COVID-19 hospital occupancy 8 days in advance, validating predictions of this nature in similar clinical contexts. The results encourage the expansion of this method to other pathologies, aiming to guarantee the standards of hospital care and conscious consumption of resources. Developed models to forecast bed occupancy for up to 14 days and monitored errors for 365 days. Telemedicine calls from COVID-19 patients correlated with the number of patients hospitalized in the next 8 days.

Corporate venturing in times of crisis: securing resources through legitimacy

AbstractAccelerating innovation and creating new businesses have become a top priority for today’s firms. Various corporate venturing (CV) modes have helped them achieve this goal. Yet, scholars and practitioners have noted the dynamic nature of CV initiatives that compete with other strategic initiatives for organizational resources and top management support. The fear that CV units face drastic cuts in times of crisis seems reasonable. To shed light on the resource dynamics and the CV units’ responsive actions, we conducted an abductive study with 16 CV units to analyze the CV units' response to the COVID-19 crisis that transformed the world in the spring of 2020. Our findings show that an external crisis can unsettle a CV unit’s internal legitimacy. In the adaption processes observed, we identify four different legitimacy-seeking mechanisms–adjusting, sensing, focusing, and mobilizing–used by the CV units to secure resources, support, and goodwill from relevant internal stakeholders. The mechanisms uncovered differ from previously studied strategies as they emphasize the dynamic nature of legitimation efforts. The mechanisms used are affected by the perceived organizational distress caused by the crisis and the CV unit’s pre-crisis legitimacy. Drawing on the critical role played by legitimacy in resource allocation decisions, this study allows us to better understand theoretically and practically how CV is embedded in organizational settings and how CV units can preserve internal (financial) resources.

A Unified Spatio-Temporal Inference Network for Car-Sharing Serial Prediction.

Car-sharing systems require accurate demand prediction to ensure efficient resource allocation and scheduling decisions. However, developing precise predictive models for vehicle demand remains a challenging problem due to the complex spatio-temporal relationships. This paper introduces USTIN, the Unified Spatio-Temporal Inference Prediction Network, a novel neural network architecture for demand prediction. The model consists of three key components: a temporal feature unit, a spatial feature unit, and a spatio-temporal feature unit. The temporal unit utilizes historical demand data and comprises four layers, each corresponding to a different time scale (hourly, daily, weekly, and monthly). Meanwhile, the spatial unit incorporates contextual points of interest data to capture geographic demand factors around parking stations. Additionally, the spatio-temporal unit incorporates weather data to model the meteorological impacts across locations and time. We conducted extensive experiments on real-world car-sharing data. The proposed USTIN model demonstrated its ability to effectively learn intricate temporal, spatial, and spatiotemporal relationships, and outperformed existing state-of-the-art approaches. Moreover, we employed negative binomial regression with uncertainty to identify the most influential factors affecting car usage.