Decision Support System Tool Research Articles

Development and implementation of a clinical decision support system tool for the evaluation of suspected monkeypox infection.

Monkeypox virus was historically rare outside of West and Central Africa until the current 2022 global outbreak, which has required clinicians to be alert to identify individuals with possible monkeypox, institute isolation, and take appropriate next steps in evaluation and management. Clinical decision support systems (CDSS), which have been shown to improve adherence to clinical guidelines, can support frontline clinicians in applying the most current evaluation and management guidance in the setting of an emerging infectious disease outbreak when those guidelines are evolving over time. Here, we describe the rapid development and implementation of a CDSS tool embedded in the electronic health record to guide frontline clinicians in the diagnostic evaluation of monkeypox infection and triage patients with potential monkeypox infection to individualized infectious disease physician review. We also present data on the initial performance of this tool in a large integrated healthcare system.

Decision support through risk cost estimation in 30-day hospital unplanned readmission.

Unplanned hospital readmissions mean a significant burden for health systems. Accurately estimating the patient’s readmission risk could help to optimise the discharge decision-making process by smartly ordering patients based on a severity score, thus helping to improve the usage of clinical resources. A great number of heterogeneous factors can influence the readmission risk, which makes it highly difficult to be estimated by a human agent. However, this score could be achieved with the help of AI models, acting as aiding tools for decision support systems. In this paper, we propose a machine learning classification and risk stratification approach to assess the readmission problem and provide a decision support system based on estimated patient risk scores.

Physicians' Perceptions and Expectations of an Artificial Intelligence-Based Clinical Decision Support System in Cancer Care in an Underserved Setting

Abstract Objectives Artificial intelligence (AI) tools are being increasingly incorporated into health care. However, few studies have evaluated users' expectations of such tools, prior to implementation, specifically in an underserved setting. Methods We conducted a qualitative research study employing semistructured interviews of physicians at The Instituto do Câncer do Ceará, Fortaleza, Brazil. The interview guide focused on anticipated, perceived benefits and challenges of using an AI-based clinical decision support system tool, Watson for Oncology. We recruited physician oncologists, working full or part-time, without prior experience with any AI-based tool. The interviews were taped and transcribed in Portuguese and then translated into English. Thematic analysis using the constant comparative approach was performed. Results Eleven oncologists participated in the study. The following overarching themes and subthemes emerged from the analysis of interview transcripts: theme-1, “general context” including (1) current setting, workload, and patient population and (2) existing challenges in cancer treatment, and theme-2, “perceptions around the potential use of an AI-based tool,” including (1) perceived benefits and (2) perceived challenges. Physicians expected that the implementation of an AI-based tool would result in easy access to the latest clinical recommendations, facilitate standardized cancer care, and allow it to be delivered with greater confidence and efficiency. Participants had several concerns such as availability of innovative treatments in resource-poor settings, treatment acceptance, trust, physician autonomy, and workflow disruptions. Conclusion This study provides physicians' anticipated perspectives, both benefits and challenges, about the use of an AI-based tool in cancer treatment in a resource-limited setting.

P-057 Machine learning-based prediction of testicular sperm extraction: comparison of different preprocessing and models, required sample size and relevance of input biomarkers

Abstract Study question Can advanced machine learning applied to the preoperative assessment predict the testicular sperm extraction outcome in azoospermic context and how many patients are required? Summary answer Despite encouraging results (AUC = 92.0%, sensitivity = 83.9% and specificity = 84.2%), integrating new biomarkers would probably be more relevant than enrolling additional patients. What is known already Testicular sperm extraction (TESE) is an essential therapeutic tool for the male infertility management and is often the “last hope” before gamete donation for these patients. However, it is an invasive procedure and is successful in up to 50%. Until now, no model is sufficiently powerful to accurately predict the success of sperm retrieval in TESE. Among the few models already developed, the findings are highly disparate despite having common input data (preoperative assessment). Moreover, only few types of machine learning models and procedures have been investigated. Performances were mostly capped despite the inclusion sometimes of more than 1000 patients. Study design, size, duration Data of 175 patients who underwent TESE between 2012 and 2021 were retrospectively analyzed. The performances of a wide range of preprocessing methods and machine learning models (state-of-the-art methods in machine learning) we explored, evaluated, and compared. The objective was to predict the presence or absence of spermatozoa, using 17 parameters (clinical, hormonal, genetic, history) from the preoperative assessment. The study protocol was approved by a local ethics committee (IRB CER-2021-041). Participants/materials, setting, methods After data preprocessing (standardization…), Machine Learning models (Bayesian Naive Classification, logistic regression, k-nearest neighbor classifier, support vector machine, random forests, GradientBoosting and XGBoost) and Deep Learning models were tested. The validation procedure consisted of splitting the dataset into a training set and test set. Beyond the standard metrics (sensitivity, specificity, AUC-ROC), the identification of the most relevant variables and the learning curve to determine the optimal patient number to be included were performed. Main results and the role of chance At least one live spermatozoon was found in the testicular tissue of 104 (59.4%) patients (positive TESE) out of 175. The best performing model (Random Forest with appropriate preprocessing) obtained the following results on the test set: AUC = 92.0%, sensitivity = 83.9% and specificity = 84.2%, leading to an efficient tool, which gives additional and more relevant information than the different variables taken separately. Inhibin B, FSH and history of cryptorchidism were the variables with the most discriminating power. However, a plateau in the model performance was observed (beyond 110 patients), whatever the approach or the preprocessing used. A trend curve shows that beyond 110 patients, no improvement can be observed and cast doubt about the power of the traditional preoperative parameters assessed before TESE. The classic preoperative assessment can probably not fully predict the TESE outcomes. Further work is needed to be enhance with new hypothesis and the use of new biomarkers to be integrated into the models. Limitations, reasons for caution The main limitation was the monocentric design and the use of retrospective data. Wider implications of the findings Machine learning models can provide the basis for an enhanced decision support system tool in the context of azoospermia. Indefinitely increasing the number of participants is not likely to be the solution: further hypotheses and biomarkers integration into the models will probably be necessary to improve performance. Trial registration number not applicable

Deep Learning Approaches for the Segmentation of Glomeruli in Kidney Histopathological Images

Deep learning is widely applied in bioinformatics and biomedical imaging, due to its ability to perform various clinical tasks automatically and accurately. In particular, the application of deep learning techniques for the automatic identification of glomeruli in histopathological kidney images can play a fundamental role, offering a valid decision support system tool for the automatic evaluation of the Karpinski metric. This will help clinicians in detecting the presence of sclerotic glomeruli in order to decide whether the kidney is transplantable or not. In this work, we implemented a deep learning framework to identify and segment sclerotic and non-sclerotic glomeruli from scanned Whole Slide Images (WSIs) of human kidney biopsies. The experiments were conducted on a new dataset collected by both the Siena and Trieste hospitals. The images were segmented using the DeepLab V2 model, with a pre-trained ResNet101 encoder, applied to 512 × 512 patches extracted from the original WSIs. The results obtained are promising and show a good performance in the segmentation task and a good generalization capacity, despite the different coloring and typology of the histopathological images. Moreover, we present a novel use of the CD10 staining procedure, which gives promising results when applied to the segmentation of sclerotic glomeruli in kidney tissues.

A Case Study of a Digital Data Platform for the Agricultural Sector: A Valuable Decision Support System for Small Farmers

New players are entering the new and important digital data market for agriculture, increasing power asymmetries and reinforcing their competitive advantages. Although the farmer remains at the heart of agricultural data collection, to date, only a few farmers participate in data platforms. Despite this, more and more decision support systems (DSSs) tools are used in agriculture, and digital platforms as data aggregators could be useful technologies for helping farmers make better decisions. However, as these systems develop, the efficiency of these platforms becomes more challenging (sharing, ownership, governance, and transparency). In this paper, we conduct a case study for an accessible and scalable digital data platform that is focused on adding value to smallholders. The case study research is based on meta-governance theory and multidimensional multilayered digital platform architecture, to determine platform governance and a data development model for the Andalusian (Spain) fruit and vegetable sector. With the information obtained from the agents of this sector, a digital platform called farmdata was designed, which connects to several regional and national, and public and private databases, aggregating data and providing tools for decision making. Results from the interviews reflect the farmer’s interests in participating in a centralized cloud data platform, preferably one that is managed by a university, but also with attention being paid toward security and transparency, as well as providing added value. As for future directions, we propose further research on how the benefits should be distributed among end users, as well as for the study of a distributed model through blockchain.

LASAM Model: An Important Tool in the Decision Support System for Policymakers and Farmers

Today’s global food system (including production, transportation, processing, packing, storage, retail sale, consumption, losses and waste) provides income to more than a billion people all over the world and makes up a significant part of many countries’ economies. The 21st century’s food systems that bring food from “farm to fork” face various challenges, including a shortage of agricultural land and water, competition with the energy industry, changes in consumption preferences, a rising global population, negative effects of climate change, etc. Therefore, many countries are working on creating various models to function as an important decision support system tool for policymakers, farmers and other stakeholders. Various agricultural sector models see particularly extensive use in the European Union (EU), determining the impact of the Common Agricultural Policy (CAP) and helping to create future development scenarios. This is why a special model adapted to the national conditions, called LASAM (Latvian Agricultural Sector Analysis Model), was created in Latvia, making it possible to use historical data on the development of agricultural sectors, medium-term price projections for agricultural products in the EU, changes in support policy, as well as the necessity for the resources used to project the long-term (up to 2050) development of agriculture. The LASAM model covers the crop sector, the animal sector and the overall socioeconomic development, as well as the growth of organic farming and greenhouse gas (GHG) emissions. This paper discusses the main objectives achieved in developing a decision support tool and presenting the research results: LASAM was used to prepare projections of the possible development of Latvia’s principal sectors of agriculture until 2050, considering the necessity to reduce GHG emissions, made available through the LASAM web application. Given that the projection data obtained by LASAM are public, they can be used (1) for national policy making in rural business development, which affects the development of the economy as a whole; and (2) internationally, to compare the projections made in Latvia with those obtained through various agricultural sector models and projected development trends.

Clostridioides difficile: A diagnostic intervention

Background:Clostridioides difficile infection (CDI) is a leading cause of healthcare-associated infection and is associated with increased morbidity and mortality. Multiple strategies have been implemented to optimize the diagnostic accuracy of CDI testing algorithms. However, overdiagnosis of C. difficile colonization remains a challenge especially in the era of highly sensitive Nucleic acid amplification testing (NAAT). We implemented 2 interventions to reduce the rates of inappropriate C. difficile orders and tests. Methods: We performed a quasi-experimental retrospective study to examine the rates of all inpatient C. difficile test orders and results relative to 2 interventions between January 2018 and February 2021. We defined 3 periods: preintervention, after the first intervention, and after the second intervention. The first intervention, implemented May 2019, was a clinical decision support system (CDSS) tool to guide clinicians to order testing only if CDI criteria were met. The second intervention, implemented July 2020, was the requirement of mandatory antimicrobial team approval of PCR reflex testing for indeterminate toxin or antigen test results. This intervention included a discussion between clinicians and members of stewardship team prior to approval. To evaluate the impact of interventions on ordering appropriateness, chart review was conducted on a random subsample of 100 orders from each period. Hospital-onset CDI (HO-CDI) was calculated using CDC criteria. Results: In total, 3,004 C. difficile test orders were placed during the study period. The rates of reportable HO-CDI were significantly reduced by 57.1% (P = .003). We detected a significant reduction in the number of tests ordered over time from 11.6 to 7.51 per 1,000 patient days. (p Conclusions: CDSS tools target patients at high pretest probability of CDI. The restriction of PCR-reflex testing to the antimicrobial stewardship team is a novel effective measure to minimize the misdiagnosis of CDI. The incorporation of multiple strategies is necessary to improve the diagnostic accuracy of C. difficile testing.Funding: NoneDisclosures: None

AscotraceR: An R Package Resource to Simulate the Spatiotemporal Spread of Ascochyta Blight in a Chickpea Field Over a Growing Season.

ascotraceR: An R Package Resource to Simulate the Spatiotemporal Spread of Ascochyta Blight in a Chickpea Field Over a Growing Season.

Design of an intelligent support system for fabric quality inspection

Efficient quality management in production process is the key factor for firm’s permanence and prosperity. The rapped globalization development and shortage of resources leading to enhance the efforts toward good raw material exploitation. The present work aims to develop a Decision Support System (DSS) that may provide and facilitate one of the most difficult multi-decision problems that quality managers, in textile manufacturing firm face. In addition, the DSS is developed for a textile manufacturer and it will automate a variety of tasks to improve rolls quality; control the defect distribution on rolls by inventing anew cutting scenarios with respect to inspection results, rolls length, and number of assemblies. The DSS tool, applied for more than 100 fabric lots, will be demonstrated through a short selection of practical case studies.

A Decision-Making Tool for Algorithm Selection Based on a Fuzzy TOPSIS Approach to Solve Replenishment, Production and Distribution Planning Problems

A wide variety of methods and techniques with multiple characteristics are used in solving replenishment, production and distribution planning problems. Selecting a solution method (either a solver or an algorithm) when attempting to solve an optimization problem involves considerable difficulty. Identifying the best solution method among the many available ones is a complex activity that depends partly on human experts or a random trial-and-error procedure. This paper addresses the challenge of recommending a solution method for replenishment, production and distribution planning problems by proposing a decision-making tool for algorithm selection based on the fuzzy TOPSIS approach. This approach considers a collection of the different most commonly used solution methods in the literature, including distinct types of algorithms and solvers. To evaluate a solution method, 13 criteria were defined that all address several important dimensions when solving a planning problem, such as the computational difficulty, scheduling knowledge, mathematical knowledge, algorithm knowledge, mathematical modeling software knowledge and expected computational performance of the solution methods. An illustrative example is provided to demonstrate how planners apply the approach to select a solution method. A sensitivity analysis is also performed to examine the effect of decision maker biases on criteria ratings and how it may affect the final selection. The outcome of the approach provides planners with an effective and systematic decision support tool to follow the process of selecting a solution method.

The impact of diagnostic stewardship interventions on Clostridiodes difficile test ordering practices and results

Clostridiodes difficile infection (CDI) is a leading cause of healthcare associated infection and is associated with increased morbidity and mortality. Diagnostic stewardship is critical in optimizing testing accuracy for CDI. Multiple algorithms have been used for testing combining toxin A/B, glutamate dehydrogenase antigen and nucleic acid amplification test (NAAT) to enhance sensitivity. This study evaluated the effectiveness of two interventions on the rates and appropriateness of Clostridiodes difficile test orders and hospital-onset (HO) CDI. All Clostridiodes difficile orders and results in the study period (1/2018–2/2021) were included. To evaluate ordering appropriateness, we reviewed the medical charts of a random subsample of 100 orders that were collected from three periods within the study: pre-intervention and following each intervention. The first intervention was a clinical decision support system (CDSS) tool guiding providers to order testing only if CDI clinical criteria were met. The second intervention eliminated automatic NAAT reflex for indeterminate results and required antimicrobial stewardship team approval. A total of 3004 orders were registered during the study period. There was a 33% reduction in the rates of Clostridiodes difficile orders by the end of the study period (p < 0.001). The rates of reportable HO-CDI were significantly reduced by 57.1% (p = 0.003). We also noted a trend of increased appropriateness of testing overtime. In conclusion, combining CDSS intervention with NAAT reflex restriction was an effective tool to reduce inappropriate Clostridiodes difficile orders and decrease the rates of reportable HO-CDI.

A Fuzzy Decision-Making Framework for Route Selection in Multimodal Transportation Networks

This study presents a novel decision-making framework for route selection in multimodal transportation networks under fuzzy environments. The proposed framework integrates the fuzzy group decision-making technique, the fuzzy deliberate process, and fuzzy multiple criteria decision-making approaches. Hence, the fuzzy Delphi method, fuzzy risk assessment, the fuzzy analytic hierarchy process, and the fuzzy technique for order of preference by similarity to ideal solution are first combined to select the most appropriate multimodal route. An empirical study demonstrates that the proposed framework is an outstanding and systematic decision support tool to aid decision makers in transportation decision-making processes of freight route selections.

Spatial Data Mining- A tool for Spatial Decision Support System in Agriculture Management

Spatial Data Mining- A tool for Spatial Decision Support System in Agriculture Management

Airport Efficiency Analysis in Europe Including User Satisfaction: A Non-Parametric Analysis with DEA Approach

In recent years, the air transport sector has played a significant role in the economy of the areas served. The demand for air travel has doubled every fifteen years and has grown faster with respect to other industries. This is also due to the introduction of low-cost airlines (LCA). In the coming decades, more efficient management of airports will become an essential aspect to address. A clear understanding of the current airport structure based on the analysis of the operational efficiency will therefore be necessary. All air carriers seek to expand their operations at airports, which tend to operate efficiently in order to reduce costs. However, in carrying out their activities and maximizing operational efficiency, airports should simultaneously manage to increase their passengers’ satisfaction. All over the world, passengers are demanding higher levels of service and regulators are paying increasing attention to the provision of airport services and the quality of the services supplied. Starting from these considerations, the aim of this paper is to study the efficiency of an airport through joint analysis of the operational efficiency (with the Data Envelopment Analysis -DEA-model) for the airport manager (by maximizing the exploitation of existing infrastructures), taking into consideration the quality of airport services as perceived by the user. The original and added value of this work lies in the quantitative analysis of the main characteristics that determine the efficiency of main European airports, also taking into account the quality perceived by the users during their trips with the air mode. Thus, the efficiency of 103 European airports in 37 different countries, for the year 2018, were compared, highlighting the effect of low-cost airlines. This aspect, as far as the authors know, has not been treated in the literature. Indeed, this study represents a decision support system (DSS) tool for operational managers in the air sector for the identification of the characteristics that improve airport efficiency. This paper refers to the pre-COVID-19 period because it would not be useful to make an efficiency analysis influenced by the pandemic, since the latter represents a specific event. Therefore, this analysis provides interesting inputs for both researchers and practitioners to manage the issue of efficiency in ordinary contexts. Moreover, the airline industry is characterized by cut-throat competition, and it may be very useful in the close future to examine this issue to improve firms’ management in the industry.

Implementation of Simple Additive Weighting Method in Evaluating Employee Performance for Job Promotion Recommendations

The implementation of decision support system tools in providing decision support for management is absolutely necessary. In its application, this aims to make the decision effective so that the decisions produced can be objective. This research discusses employee performance appraisal by implementing a decision support system. Many methods of decision support systems that can be used to rank, but in this study, the authors use the ranking method known as Simple Additive Weighting (SAW). The SAW method works by summing the weighted attributes that are interrelated. This method is quite simple and is able to provide the right decisions for employees who have the best performance to be recommended in job promotions. In this research, assessment attributes are used, namely education, experience, expertise, collaboration, work quality, and discipline. The final results show that employees on behalf of Ferdinal have the highest value with a value of 0.850.

Experience with home-based, remote non-stress tests, including automatic decision support for interpretation of reactivity

The fetal non-stress test (NST) for antepartum surveillance involves frequent, burdensome in-office visits. INVUTM is a wireless, remote, FDA-cleared monitoring device, designed to perform self-administered NST from home. Here, we present (1) our initial experience with INVUTM home NST monitoring, and (2) a novel machine learning decision support system (DSS) to detect fetal heart rate (FHR) accelerations, with the potential to alert clinicians on NST reactivity. A single-center, prospective, open label study was conducted, in which women with ≥32 week high-risk singleton gestations performed self-administered NST using the INVUTM device at home, replacing in-clinic NSTs. NSTs were reviewed by clinicians via the INVUTM web application who determined clinically interpretability and reactivity. Interpretable sessions were retrospectively analyzed by the DSS for reactivity and compared to clinician assessment (Figure). The time to reactivity as analyzed by the DSS was compared to the session length until reactivity was determined by clinicians. Of the first 30 INVUTM sessions (across 9 subjects), clinicians deemed 27 (90%) interpretable, and 27/27 as reactive (100%). The DSS correctly classified 92.6% (25/27) of the interpretable NSTs compared with clinicians. In the 2 cases where DSS did not match the clinician decision, DSS did not rule the NST reactive, whereas the clinician did. On review, these cases may have been due to clinician averaging the FHR baseline from which accelerations are measured, compared to the conservative nature of the DSS. In the cases deemed reactive by DSS, time to reactivity was reduced by 14.72±13.79 min as compared to clinician determination. Early clinical experience conducting self-administered, remote NSTs at home using the INVUTM device supports the feasibility of bringing this telehealth solution to high risk pregnancy care. In addition, a novel DSS tool accurately identifies reactivity, which could reduce the length of NST sessions and improve clinician workflow.

Evaluation of structural integrity of tubulars in directional wellbores: A case study in north-eastern parts of India

Severe fatigue and excessive load transmissions on drill strings during rotary drilling may lead to unexpected drill string failure. And if the driller within the stipulated time-bound did not control these load forces, the situation might increase NPT. To achieve the same by driller in real-time, the structural integrity of the tubular was monitored with a workflow that estimates the overall stresses acting along the drill string. In actual operating conditions, the drill string is subjected to both internal and external pressures, and it can be well explained in terms of true tension and effective tension. The estimation of these tensional forces and other load forces acting on the drill string is important for efficient drilling operation and the selection of optimum operational parameters. In addition, these forces are further utilized to estimate the neutral point and load acting at the deadline. The conventional rigs are subjected to numerous uncertainties that affect the precision of the hookload measurement at the deadline. Therefore, the factors affecting the hookload measurement at the deadline are summed up to a quantifiable metric labeled as Rig Uncertainty Compensation (RUC) factor. Further, the estimated hookload is compared with the actual hookload to detect the upcoming complications and prevent it from aggravation. And, to confirm the upcoming anomaly, the wellbore secondary drilling parameters are monitored in the real-time drilling operation. Additionally, all the forces acting along the drill string were also determined and monitored dynamically such that stress exposure in all the sections of the drill string is below a threshold value. To determine the efficacy of the developed model, the model was integrated with a Decision Support System (DSS) tool and tested in the actual field conditions. The tool was able to detect the upcoming complication successfully, and a field case study was presented in brief. • Effective tension and true tension are utilized to estimate the load acting at the deadline. • An analytical model to determine the total stresses acting along the length of the drill string. • The factors affecting the accuracy of the hookload measurement at the deadline were cumulatively labeled as “Rig Uncertainty Compensation” factor. • A case study of a directional well drilled in North-Eastern parts of India is presented.

Crop Models: Important Tools in Decision Support System to Manage Wheat Production under Vulnerable Environments

Decision support systems are key for yield improvement in modern agriculture. Crop models are decision support tools for crop management to increase crop yield and reduce production risks. Decision Support System for Agrotechnology Transfer (DSSAT) and an Agricultural System simulator (APSIM), intercomparisons were done to evaluate their performance for wheat simulation. Two-year field experimental data were used for model parameterization. The first year was used for calibration and the second-year data were used for model evaluation and intercomparison. Calibrated models were then evaluated with 155 farmers’ fields surveyed for data in rice-wheat cropping systems. Both models simulated crop phenology, leaf area index (LAI), total dry matter and yield with high goodness of fit to the measured data during both years of evaluation. DSSAT better predicted yield compared to APSIM with a goodness of fit of 64% and 37% during evaluation of 155 farmers’ data. Comparison of individual farmer’s yields showed that the model simulated wheat yield with percent differences (PDs) of −25% to 17% and −26% to 40%, Root Mean Square Errors (RMSEs) of 436 and 592 kg ha−1 with reasonable d-statistics of 0.87 and 0.72 for DSSAT and APSIM, respectively. Both models were used successfully as decision support system tools for crop improvement under vulnerable environments.

Emergence modelling of 18 species susceptible to be used as cover crops in Mediterranean semiarid vineyards

Cover Crops (CC) are increasingly appreciated in vineyards because they can provide ecosystems services, such as preventing soil erosion and compaction, increasing soil organic matter or, controlling weeds. Many species from different botanical families can be used depending on the final purpose of the CC, but their successful establishment in Mediterranean semiarid conditions of NE Spain can be challenging. Therefore, it is mandatory to understand and be able to predict the emergence patterns of the chosen species as their success is crucial to achieve a good soil cover. Different models based on thermal time (TT), hydrothermal time (HTT), photohydrothermal time (PhHTT) and photosolar hydrothermal time (PhSHTT) have already been used in crops and weeds for this purpose. In this paper, these four models have been developed for the 18 species susceptible of being CC, some of them being successfully validated with independent data from southern France. Results suggest that, although TT and HTT based models are accurate, their precision is improved when light is included (R2 >0.9). Models including light could be widespread used in some species as the successful validation with independent data demonstrates. These models considerably contribute to inter-row management in vineyards as decision support systems (DSS) tools to predict CC establishments.