Enhanced Decision Support Research Articles

Pilot deployment of a machine-learning enhanced prediction of need for hemorrhage resuscitation after trauma – the ShockMatrix pilot study

ImportanceDecision-making in trauma patients remains challenging and often results in deviation from guidelines. Machine-Learning (ML) enhanced decision-support could improve hemorrhage resuscitation.AimTo develop a ML enhanced decision support tool to predict Need for Hemorrhage Resuscitation (NHR) (part I) and test the collection of the predictor variables in real time in a smartphone app (part II).Design, setting, and participantsDevelopment of a ML model from a registry to predict NHR relying exclusively on prehospital predictors. Several models and imputation techniques were tested. Assess the feasibility to collect the predictors of the model in a customized smartphone app during prealert and generate a prediction in four level-1 trauma centers to compare the predictions to the gestalt of the trauma leader.Main outcomes and measuresPart 1: Model output was NHR defined by 1) at least one RBC transfusion in resuscitation, 2) transfusion ≥ 4 RBC within 6 h, 3) any hemorrhage control procedure within 6 h or 4) death from hemorrhage within 24 h. The performance metric was the F4-score and compared to reference scores (RED FLAG, ABC). In part 2, the model and clinician prediction were compared with Likelihood Ratios (LR).ResultsFrom 36,325 eligible patients in the registry (Nov 2010—May 2022), 28,614 were included in the model development (Part 1). Median age was 36 [25–52], median ISS 13 [5–22], 3249/28614 (11%) corresponded to the definition of NHR. A XGBoost model with nine prehospital variables generated the best predictive performance for NHR according to the F4-score with a score of 0.76 [0.73–0.78]. Over a 3-month period (Aug—Oct 2022), 139 of 391 eligible patients were included in part II (38.5%), 22/139 with NHR. Clinician satisfaction was high, no workflow disruption observed and LRs comparable between the model and the clinicians.Conclusions and relevanceThe ShockMatrix pilot study developed a simple ML-enhanced NHR prediction tool demonstrating a comparable performance to clinical reference scores and clinicians. Collecting the predictor variables in real-time on prealert was feasible and caused no workflow disruption.

Measuring exploration: evaluation of modelling to generate alternatives methods in capacity expansion models

Abstract As decarbonisation agendas mature, macro-energy systems modelling studies have increasingly focused on enhanced decision support methods that move beyond least-cost modelling to improve consideration of additional objectives and tradeoffs. One candidate is modelling to generate alternatives (MGA), which systematically explores new objectives without explicit stakeholder elicitation. This paper provides comparative testing of four existing MGA methodologies and proposes a new Combination vector selection approach. We examine each existing method’s runtime, parallelizability, new solution discovery efficiency, and spatial exploration in lower dimensional (N ⩽ 100) spaces, as well as spatial exploration for all methods in a three-zone, 8760 h capacity expansion model case. To measure convex hull volume expansion, this paper formalizes a computationally tractable high-dimensional volume estimation algorithm. We find random vector provides the broadest exploration of the near-optimal feasible region and variable Min/Max provides the most extreme results, while the two tie on computational speed. The new Combination method provides an advantageous mix of the two. Additional analysis is provided on MGA variable selection, in which we demonstrate MGA problems formulated over generation variables fail to retain cost-optimal dispatch and are thus not reflective of real operations of equivalent hypothetical capacity choices. As such, we recommend future studies utilize a parallelized combined vector approach over the set of capacity variables for best results in computational speed and spatial exploration while retaining optimal dispatch.

A-165 Value Of Monocyte Distribution Width In Bacteremia Assessment In Emergency Department Patients

Abstract Background Monocyte distribution width (MDW) is an immune response biomarker and part of a CBC differential. MDW is derived from the distribution of monocyte volumes and elevated MDW values correlate with severe infections and sepsis in Emergency Department (ED) adult patients. Neutrophil to lymphocyte ratio (NLR) is predictive of infections and inflammatory stress. Evaluating these biomarkers could be valuable in bacteremia risk assessment. Bacteremia is the presence of viable bacteria in the bloodstream and is present in up to 20% of septic patients. Blood cultures establish pathogen identity but require culture time, potentially delaying appropriate treatment. Our goal was to characterize MDW and NLR clinical performance in ED patients with suspected bacteremia. Methods This was an observational cohort study of ED patients 18 years and older with CBC differential and blood cultures obtained. MDW values ≥20 is the published cut-off for increased infection risk. Clinical literature suggests that NLR ≥3 is abnormal. We assessed the diagnostic performance of MDW and NLR for positive blood cultures using SPSS Version 25. Results From 07/2021-09/2023, 9,400 blood cultures were ordered and 5174 patients had differential CBCs. The overall blood culture positivity rate was 14.4%. MDW and NLR performance for positive blood cultures is shown in Table 1. Conclusions Our analysis provides evidence that MDW and NLR may be useful for early recognition of bacteremia in ED patients. CBC differential results are reported sooner than culture results. MDW is directly reported, NLR can be readily calculated from the differential. Therefore both could contribute to earlier risk stratification and our findings suggest potentially distinct information from MDW and NLR. Combining MDW with other CBC parameters may provide additional diagnostic advantage. Further analysis will incorporate added clinical data for enhanced decision support in interpreting MDW values in the context of pending blood culture results.

Turbidity assessment in coastal regions combining machine learning, numerical modeling, and remote sensing

ABSTRACT Machine learning models for water quality prediction often face challenges due to insufficient data and uneven spatial-temporal distributions. To address these issues, we introduce a framework combining machine learning, numerical modeling, and remote sensing imagery to predict coastal water turbidity, a key water quality proxy. This approach was tested in the Great Lakes region, specifically Cleveland Harbor, Lake Erie. We trained models using observed and synthetic data from 3D numerical models and tested them against in situ and remote sensing data from PlanetLabs' Dove satellites. High-resolution (HR) data improved prediction accuracy, with RMSE values of 0.154 and 0.146 log10(FNU) and R2 values of 0.92 and 0.93 for validation and test datasets, respectively. Our study highlights the importance of unified turbidity measures for data comparability. The machine learning model demonstrated skill in predicting turbidity through transfer learning, indicating applicability in diverse, data-scarce regions. This approach can enhance decision support systems for coastal environments by providing accurate, timely predictions of water quality variables. Our methodology offers robust strategies for turbidity and water quality monitoring and holds significant potential for improving input data quality for numerical models and developing predictive models from remote sensing data.

Comparative analysis of machine learning models for rainfall prediction

Predicting rainfall is essential for many applications, including agriculture, hydrology, and disaster management. In this work, we undertake a comparison examination of various machine learning models to forecast rainfall based on meteorological data. The target variable in this study is rainfall, and the dataset used includes characteristics like temperature, relative humidity, wind speed, and wind direction. The following seven machine learning models were assessed: Support Vector Regression (SVR), Multivariate adaptive regression splines (MARS), Random Forest Regression, and Deep Neural Network with Historical Data (DWFH), Haar Wavelet Function, Decision Tree and Discrete wavelet Transform (DWT). Data preprocessing, which includes standardisation and lagging to capture temporal dependencies, comes first in the analysis phase. A wavelet transformation is also used to capture complex patterns in the data. Each model is tested on a different test set after being trained on a subset of the dataset. The results are assessed using the Root Mean Squared Error (RMSE) and Mean Squared Error (MSE), focusing on the RMSE and MSE values for better comparison across models. Our findings reveal that the DWFH model achieved an RMSE of 0.0138807 mm and MSE of 0.000193 mm2, demonstrating their effectiveness in predicting rainfall. The Random Forest and SVR models also provided competitive results. This study highlights the importance of selecting an appropriate machine learning model for rainfall prediction and the significance of preprocessing techniques in improving model performance. These insights can aid decision-makers in choosing the most suitable model for their specific application, contributing to more accurate rainfall predictions and enhanced decision support systems.

Real-time data warehousing in the big data environment: A comprehensive review of implementation in the internet industry

A real-time data warehouse is a crucial tool for information management and analysis, enabling the capture, processing, and analysis of vast amounts of data from diverse sources in real-time. It offers enterprises enhanced decision support through its efficient processing capabilities and timely data feedback. This paper reviews the technical characteristics and application scenarios of real-time data warehouses, with a particular focus on the Internet sector. It explores the evolution from traditional data warehouses to modern data lake and lakehouse architectures, emphasizing the advancements in data processing capabilities, including the separation of storage and compute functions. Real-time data warehouses, which enable immediate data processing and feedback, are essential for enterprises requiring up-to-the-minute insights. The study compares the Lambda and Kappa architectures, detailing their strengths and weaknesses in terms of data throughput, latency, and scalability. Innovations such as Apache Hudi and lakehouse architectures offer new opportunities for performance optimization and functional expansion. The emergence of hybrid architectures like HTAP (Hybrid Transactional/Analytical Processing) and HSAP (Hybrid Serving/Analytical Processing) represents a significant advancement in integrating transactional and analytical processing. Future research should focus on the impact of artificial intelligence and machine learning on real-time data warehouses to enhance their analytical and predictive capabilities, reduce complexity, and lower operational costs.

Retraction Note: Enhanced decision support system to predict and prevent hypertension using computational intelligence techniques

Retraction Note: Enhanced decision support system to predict and prevent hypertension using computational intelligence techniques

An integrated MCDM model with enhanced decision support in transport safety using machine learning optimization

Having the capacity to effectively manage multi-criteria decision-making (MCDM) issues with considerable reliability is a crucial prerequisite for any MCDM model. This study introduces an advanced MCDM model that integrates logarithmic percentage change-driven objective weighting (LOPCOW), multi-objective optimization on the basis of a ratio analysis plus the full multiplicative form (MULTIMOORA), and density-based spatial clustering of applications with noise (DBSCAN). The goal is to provide robust decision support. Specifically, the model incorporates a machine learning tool, namely, grid search, to optimize the parameters of neighborhood radius (ε) and the minimum number of points, which significantly influence the clustering quality of DBSCAN. Subsequently, the cluster centers determined by DBSCAN serve as initial points for k-means clustering to negate the impact of outliers. This approach addresses the failures of DBSCAN in nearest neighbor search and parameter selection, and it also resolves the limitations of k-means related to the uncertainty in cluster outcomes due to varying initial centroid selections. Utilizing a real case study from the European Union, comprehensive comparisons of the model results demonstrate the adaptability, reliability, and stability of the proposed model, affirming its effectiveness in providing credible policy recommendations and practical decisions. Overall, this study presents policymakers, professionals, and administrators with a reliable decision-making system for conducting real-world MCDM tasks with enhanced confidence and robustness.

Causal Machine Learning in Marketing

This study reviews three primary purposes of causal machine learning (CML) in marketing, merging impact evaluation of marketing interventions with machine learning algorithms for learning statistical patterns from data. Firstly, CML enables more credible impact evaluation by considering important control variables that simultaneously influence the intervention and business outcomes (such as sales) in a data-driven manner. Secondly, it facilitates the data-driven detection of customer segments for which a marketing intervention is particularly effective or ineffective, a process known as effect moderation or heterogeneity analysis. Thirdly, closely related to the second point, it allows for optimal customer segmentation into groups that should and should not be targeted by the intervention to maximize overall effectiveness. The discussion is grounded in recent empirical applications, all of which aim to enhance decision support in marketing by leveraging data-driven evaluation and optimization of interventions across different customer groups.

A Bayesian Hierarchical Model to create synthetic Power Distribution Systems

The growing complexity of Power Distribution Systems, driven by distributed generation, renewable energy integration, and increasing demand, has led to restricted access to DS data due to security and privacy concerns. This study addresses limited data accessibility by proposing a hybrid approach for crafting synthetic power distribution systems tailored for power system analysis and control. Synthetic power distribution systems refer to artificially generated models that faithfully replicate real-world DS features while upholding security and privacy constraints. This innovative methodology merges a Bayesian Hierarchical Model with Markov Chain Monte Carlo techniques, utilizing georeferenced data to capture intricate system dependencies, feeder configurations, switch statuses, and load node distributions. Leveraging OpenStreetMaps for DS topology, the approach incorporates expert knowledge and real-world data. Results highlight the methodology’s ability to evaluate credible intervals for parameters, facilitating a probabilistic assessment of uncertainties and enhancing decision support in power system analysis and control. Findings affirm the hybrid approach’s efficacy in generating realistic synthetic DSs, bridging the gap between statistical and georeferenced methodologies for advanced power system analysis and control. The capacity to generate synthetic DSs provides valuable insights into power system dynamics, addressing security, privacy, and data accessibility concerns for a more informed decision-making process.

Assessing the Impact of Seasonal Decomposition on the Time Series Analysis Accuracy: A Comprehensive Study

Abstract: Time series forecasting plays a pivotal role in decision-making across various domains, ranging from finance to healthcare and weather prediction. The accurate prediction of future values in a time series is vital for informed planning and resource allocation. The aim of this study is to explore whether the utilization of seasonal decomposition techniques, such as classical decomposition, X-12-ARIMA, and seasonal decomposition of time series (STL), can improve the effectiveness of time series forecasting models by separating the data into its distinct components, including trend and seasonality. We conduct a comprehensive analysis using real-world time series data, employing popular forecasting models like ARIMA, exponential smoothing, and machine learning-based approaches. By comparing the forecasting accuracy of these models with and without the application of seasonal decomposition techniques, we provide empirical evidence to support the hypothesis. Our research results provide valuable insights into the tangible ad- vantages of integrating seasonal decomposition techniques in time series forecasting, potentially contributing to enhanced decision support systems across diverse application domains.

Research on the Path of Financial Accounting Transformation to Management Accounting in the Big Data Era

This paper explores the significance, existing problems, and strategies for addressing the transformation of financial accounting to management accounting in the era of big data. It first elucidates the importance of the transformation, including enhancing decision support, conducting cost-benefit analysis, and improving performance. Subsequently, it analyzes the problems encountered during the transformation process, such as lack of skills and knowledge, low utilization of data resources, and difficulties in system integration. It then proposes countermeasures to address these issues, including technological capacity building, talent training and recruitment, system integration coordination, and enhancement of management accounting decision analysis capabilities. Finally, it points out that as technology and market environments evolve, this transformation will continue to deepen, necessitating continuous skill enhancement for professionals in the financial accounting field and proactive adaptation by enterprises to enhance competitiveness.

Opportunities and Challenges in Health Insurance Statistics in the Era of Big Data

With the rapid advancement of big data technology, health insurance statistics are undergoing unprecedented transformations. This study explores the opportunities and challenges of health insurance statistics in the context of big data, offering theoretical frameworks and strategic recommendations. Through a comprehensive literature review and theoretical analysis, the study systematically examines related research on the application of big data in health insurance statistics globally. It analyzes how big data technology enhances the efficiency of data collection, processing, and analysis in health insurance, while also addressing issues like data security, privacy protection, and talent shortages. The research involves an in-depth analysis of big data technology characteristics and a reevaluation of health insurance statistical workflows. The findings indicate that big data offers opportunities for improved data processing capabilities and enhanced decision support in health insurance statistics, while simultaneously posing challenges in data governance, privacy protection, and talent development. To fully leverage the advantages of big data, an improved data management system, strengthened data security and privacy measures, and the cultivation of professionals skilled in big data analysis are necessary. This study provides theoretical support and practical guidance for the development of health insurance statistics in the big data context.

Determination of Relationship Between the Application of ICT and Decision-Making Federal Universities of Northern Nigeria

This study examines how Federal Universities of Northern Nigeria use ICT to make decisions. Technology in data storage, analytics, and decision support systems has transformed decision-making, according to the introduction. We examine how ICT improves decision-making through data gathering, analysis, and communication. The hypothesis is that ICT use does not affect decision-making in these universities. The correlational study included 2,114 workers from all Northern Nigerian Federal Universities. The sample procedure selected states from each geopolitical zone and seven federal institutions from each state. Data was collected using a questionnaire on ICT in Effective Planning (QAICTEP). The null hypothesis was tested using Pearson's Product Moment Correlation coefficient (PPMCC). The respondents' age, experience, and qualifications were diverse. Male respondents outnumbered female respondents 75% to 25%. The null hypothesis was rejected since the PPMCC analysis showed a positive correlation (r = 0.609) between ICT application and decision-making. The conclusion shows that ICT use improves decision-making. ICT infrastructure investments, training, enhanced Decision Support System integration, and strong data governance regulations are recommended. at conclusion, this study sheds light on strategic ICT integration and decision-making at Federal Universities in Northern Nigeria, emphasising the need to improve decision-making quality and efficiency.

Decision-guidance method for knowledge discovery and reuse in multi-goal engineering design problems

When designing complex engineered systems, designers typically encounter different types of complexity in decision-making, such as learning trade-offs among conflicting system goals and concurrently meeting specifications of subsystems while complying with all constraints. Therefore, when managing knowledge of the concurrent design of multi-component systems, one must consider the decision interactions among designers with different interests and the coupling effects of subsystems. Conventional multi-objective optimization methods are inadequate in providing decision support on compromising the achievement of conflicting goals under various design circumstances; they are incompetent to provide knowledge from the supply side. They may also fail to solve the problems endorsed by decision-makers' evolving preferences; that is, they are incompetent in gaining knowledge from the demand side. Enhancing decision support and managing various stakeholders’ preferences is essential for engineering design problems. To address this issue, we propose a method to give systematic guidance for knowledge discovery and reuse in learning the trade-offs among conflicting goals with various preferences. Using the proposed method, a designer can (1) select appropriate design scenarios to compromise the achievement of system goals while maintaining an acceptable level of fidelity and (2) explore and refine the subsystems coupling in a structured and computable manner. We made the contributions above through (1) reusable knowledge identification and ontology development for creating and archiving the knowledge associated with the problem-solving process, (2) implementing interactive decision-making by adopting different guiding strategies, (3) working on satisfying solutions, and (4) developing icon-based knowledge representation and execution of decision workflows in the knowledge-based design guidance system. The whole process forms a loop, namely, the formulation-refinement-exploration-improvement loop. We demonstrate the efficacy of our method using a test problem, the design of a small-scale thermal system that is widely applied in freshwater production and agricultural irrigation.

Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data.

We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.

Blockchain and explainable AI for enhanced decision making in cyber threat detection

SummaryArtificial Intelligence (AI) based cyber threat detection tools are widely used to process and analyze a large amount of data for improved intrusion detection performance. However, these models are often considered as black box by the cybersecurity experts due to their inability to comprehend or interpret the reasoning behind the decisions. Moreover, AI‐based threat hunting is data‐driven and is usually modeled using the data provided by multiple cloud vendors. This is another critical challenge, as a malicious cloud can provide false information (i.e., insider attacks) and can degrade the threat‐hunting capability. In this paper, we present a blockchain‐enabled eXplainable AI (XAI) for enhancing the decision‐making capability of cyber threat detection in the context of Smart Healthcare Systems. Specifically, first, we use blockchain to validate and store data between multiple cloud vendors by implementing a Clique Proof‐of‐Authority (C‐PoA) consensus. Second, a novel deep learning‐based threat‐hunting model is built by combining Parallel Stacked Long Short Term Memory (PSLSTM) networks with a multi‐head attention mechanism for improved attack detection. The extensive experiment confirms its potential to be used as an enhanced decision support system by cybersecurity analysts.

Data-Driven Decision Support for Equipment Selection and Maintenance Issues for Buildings

Equipment costs play a critical role in decision making during design and construction, which requires up-to-date information and data. The design of this study incorporates the inputs from the literature review on the influencing factors of equipment costs and major targeted equipment types to enhance decision support for equipment selection, project construction, and maintenance issues. Two traditional cost estimation methods and five machine-learning methods were compared in this study to identify significant attributes related to the predictions of the costs and residual values of each targeted equipment type. The novelty of this study is that the developed method improves prediction accuracy by establishing a comprehensive and well-structured database framework. A comparison of this method with the existing prediction models reveals that the results and the accuracy of multiple regression analysis are improved in the range of (3% to 33.97%) with the use of a modified decision-tree model combined with support vector machines. The major contribution of this research is the design, implementation, and validation of a machine-learning-based modified decision tree with a support vector machine model for improved accuracy and decision support in construction management. Future research should consider the relationship between geographical variations and value changes.

AI-Driven Intraday Trading: Applying Machine Learning and Market Activity for Enhanced Decision Support in Financial Markets

AI-Driven Intraday Trading: Applying Machine Learning and Market Activity for Enhanced Decision Support in Financial Markets

An innovative algorithm based on weighted fuzzy soft multisets and its application in selecting optimal construction materials

<p>Effective decision-making is critical across various domains, including technology, medicine, and engineering. To address the complexities of decision-making, particularly in scenarios involving both positive and negative parameters, this paper introduces an innovative algorithm based on weighted fuzzy soft multisets. This algorithm mitigates the issue of counterintuitive results often encountered in existing methods. By incorporating the concept of uniform fuzzy soft multisets and considering the conditional structure of these sets, our approach advances the theoretical framework of decision-making while providing a practical tool for complex scenarios. To demonstrate its practical applicability, we conduct a case study focused on selecting optimal construction materials for a building project, utilizing data from established engineering standards and a comprehensive wood properties database. The key findings of our sensitivity analysis highlight the algorithm's robustness to weight changes and adaptability to different decision sequences. These findings highlight the algorithm's potential to enhance decision support systems across various fields, such as engineering, healthcare, and environmental management. This potential is particularly valuable in complex, multi-criteria scenarios that demand nuanced, context-aware solutions.</p>