Prototype Decision Support System Research Articles

TOWARD CASE‐BASED REASONING FOR DIABETES MANAGEMENT: A PRELIMINARY CLINICAL STUDY AND DECISION SUPPORT SYSTEM PROTOTYPE

This paper presents a case‐based decision support system prototype to assist patients with Type 1 diabetes on insulin pump therapy. These patients must vigilantly maintain blood glucose levels within prescribed target ranges to prevent serious disease complications, including blindness, neuropathy, and heart failure. Case‐based reasoning (CBR) was selected for this domain because (a) existing guidelines for managing diabetes are general and must be tailored to individual patient needs; (b) physical and lifestyle factors combine to influence blood glucose levels; and (c) CBR has been successfully applied to the management of other long‐term medical conditions. An institutional review board (IRB) approved preliminary clinical study, involving 20 patients, was conducted to assess the feasibility of providing case‐based decision support for these patients. Fifty cases were compiled in a case library, situation assessment routines were encoded to detect common problems in blood glucose control, and retrieval metrics were developed to find the most relevant past cases for solving current problems. Preliminary results encourage continued research and work toward development of a practical tool for patients.

Fuzzy Real Options in Brownfield Redevelopment Evaluation

Real options modeling, which extends the ability of option pricing models to evaluate real assets, can be used to evaluate risky projects because of its capacity to handle uncertainties. This research utilizes possibility theory to represent private risks of a project, which are not reflected in the market and hence are not fully evaluated by standard option pricing models. Using a transformation method, these private risks can be represented as fuzzy variables and then priced with a fuzzy real options model. This principle is demonstrated by valuing a brownfield redevelopment project using a prototype decision support system based on fuzzy real options. Because they generalize the original model and enable it to deal with additional uncertainties, fuzzy real options are entirely suitable for the evaluation of such projects.

A pilot prototype decision support system for recognition of Greek forest species

Expert Systems constitute a part of the broader field of Artificial Intelligence. There are applications which aim in the encasement of knowledge of an expert, in a certain area of science, in a computer application. Thus it is possible for the further use of the experts’ knowledge even by people who cannot directly communicate with an expert. In the field of environmental sciences expert systems were created for dealing with various problems. The purpose of this paper is the development of an expert system which would be able to identify wood produced by Greek forest species. The system will be available for wood industry professionals, for students as a support tool in the education process, and for anyone interested in wood identification.

Using multi-perspective methodologies to study users’ interactions with the prototype front end of a guideline-based decision support system for diabetic foot care

Purpose Clinical practice guidelines are important instruments for improving the quality of care; in paper form, however, they are not used as effectively as possible. In order to develop a guideline-based decision support system (DSS) prototype to help clinicians deal with diabetic patients’ foot problems, we drew on methodologies from qualitative research, cognitive science, and information systems. This multi-perspective approach was intended to facilitate user-centered design and evaluation. Methods We employed field observations, structured interviews, and document analyses to collect and analyze users’ workflow patterns, decision support goals, and preferences regarding interactions with a DSS. Next, we aligned their requirements with sequence diagrams and followed Nielsen's heuristics to develop a DSS prototype. We then performed think-aloud analyses and used the technology acceptance model to direct our evaluation of users’ perceptions of the prototype. Results Users had a positive response to the DSS prototype in terms of its clarity of design and ease of use. They expressed a high intention of using the system in the future. Conclusion Applying multi-perspective methodologies is an effective way to study and design user interactions with the front end of a guideline-based DSS.

Towards ubiquitous information supply for individual investors: A decision support system design

This paper introduces an IT artifact called MoFiN DSS that comprises hard- and software components that provide the basis for a prototype of a financial decision support system (DSS) to support individual investors reacting to unforeseen market events. We have derived our motivation for building such a system design from behavioral finance research. Analyses of the behavior of individual investors provide evidence that this segment does react more significantly to any public news published compared to institutional investors. On the other hand, the analyses show that they react significantly slower than their institutional counterparts. Since empirical intraday event study analyses show that capital markets react promptly to new information and that excess returns decrease over a specific period of time, individual investors miss significant trading opportunities due to their current strategies of information research. We address the problem that this market segment is not able to continuously observe diverse information channels and to assess all the new information available. Our prototype decision support system continuously observes company announcements and forecasts their potential impact on the corresponding stock price. After identifying those events for which significant market reactions can be expected, wireless push-based message services provide the technical basis for prompt and location-independent information supply. Based on a novel simulation-based evaluation methodology we have developed, we demonstrate and quantify the advantages that the developed system provides to the individual investors.

Development of a novel framework for the design of transport policies to achieve environmental targets

The formulation of policies requires the selection and configuration of effective and acceptable courses of action to reach explicit goals. A one-size-fits-all policy is unlikely to achieve the desired goals; as a result, the identification of a suite of alternative policies, together with clear indications of their trade-offs, is crucial to accommodate the diversity of stakeholders’ preferences. At present, the formulation of transport policies is done manually; this fact, together with the size of the space of possible policies, results in a large part of that space being left unexplored. A six-step framework to explore the space of alternative transport policies in order to achieve environmental targets is proposed. The process starts with a user-defined set of specific policy measures, using them as building blocks in the generation of alternative policy packages, clusters and future images according to the user's preferences and goals. The analysis framework is based on the visioning and backcasting approach used in the VIBAT report [Banister, D., & Hickman, R. (2006a). Visioning and backcasting for UK transport policy (VIBAT) project. Department for Transport's Horizons Research Programme 2004/06. The Bartlett school of planning and Halcrow Group Ltd. Retrieved 1/18/2008 http://www.ucl.ac.uk/∼ucft696/vibat2.html]. The framework is being implemented as a prototype decision support system around a case study: the formulation and analysis of policies required to achieve CO 2 emission targets for the transport sector in the UK. Important insights on how to develop the framework have also been elicited from engineering design. The goal is to accelerate the task of policy-making and improve the effectiveness of the resulting policies. The proposed method and computer implementation is fundamentally different from the tools commonly used in the transport sector and is intended to assist (not replace) transport policy makers, and complement (not substitute nor compete with) existing mathematical modelling tools. This research constitutes the first step towards the development of a general family of computer-based systems that support the design of policies to achieve environmental targets—not only for transport, but also for other sectors such as energy and water.

A prototype decision support system for sustainable urban tree planting programs

The prototype decision support system (PDSS) described within this paper represents one of the first of its kind in the urban forest/civil engineering research arena. The primary objective of this research was to develop a user-friendly, intuitive PDSS that provides users with tools for improved micro-management of the urban forest canopy. The secondary objective was to generate further discussion with respect to the relevance of viewing the urban forest as a municipal infrastructure, and designing and implementing sound management plans with the same rigor and attention to detail that is adhered to in the design and implementation of its civil engineering counterparts. The PDSS is divided into seven modules: (1) determination of potential native and non-native tree species available for planting; (2) defining the plantable and non-plantable areas in a defined region; (3) determination of planting locations; (4) species diversity assignment; (5) evaluating age distribution; (6) evaluating canopy cover, and (7) shadow analysis. Within each module the PDSS provides flexibility with respect to user input and constraints and for ease of use contains downloadable user reference guides. The PDSS was developed in three components, using three commonly used software programs: (1) SMODT, which is a south to south-central Ontario, Canada database of trees, developed in Microsoft Access Database; (2) ArcTrees, which is a GIS-based application that uses customized tools to map the plantable and non-plantable area in the urban environment, and (3) TreeModules, which uses a customized user interface in Microsoft Excel to carry out functions for Module 1 and Modules 3 through 7 inclusive. The PDSS uses rule-based algorithms that interact with expert knowledge and heuristics to draw inferences based on guided user inputs, through customized user-interfaces.

Valuation of urban sustainability and building energy efficiency: a case study

The general objective of the research is to set up a strategy of sustainable conservation at two levels: at city level, to conceive and plan interventions at block, street, neighbourhood scale; at building level to propose and design specific conservation and enhancement interventions that pay particular attention to the ecological and energy dimensions. Specific objective of the research is to build up a prototype of decision support system (DSS) including a general valuation system (GVS or SGV), aiming to support planning and design of building sustainable conservation and to make possible its subsequent generalisation at city level. The proposed prototype structure is based upon powerful GIS tools, which coordinate allied software for both energy management and cost estimate as well as for life-cycle valuation of conservation and energy optimisation interventions.

A Multi-Objective Optimization Decision Support Model for Renewal Planning of Sewer Networks

A new integrated approach for optimal renewal planning of municipal infrastructure systems has been developed. This chapter discusses the application of the proposed approach to implement a GIS-based Decision Support System (DSS) to support the renewal planning of sewer networks. The approach involves several steps addressing condition rating, risk assessment, and prioritization of sewers. It also incorporates a procedure for identifying and selecting the most suitable renewal technologies. A genetic algorithm (GA)-based multi-objective optimization (MOO) technique is used to find a Pareto front and identify a set of feasible solutions, in which a set of sewers is selected for renewal each year, along with the associated costs and expected benefits in terms of condition improvement and risk reduction. The chapter also presents an example application of the prototype DSS on the sewer network in Regina, Canada.

A hybrid hierarchical decision support system for cardiac surgical intensive care patients. Part I: Physiological modelling and decision support system design

To develop a clinical decision support system (CDSS) that models the different levels of the clinician's decision-making strategies when controlling post cardiac surgery patients weaned from cardio pulmonary bypass. A clinical trial was conducted to define and elucidate an expert anesthetists' decision pathway utilised in controlling this patient population. This data and derived knowledge were used to elicit a decision-making model. The structural framework of the decision-making model is hierarchical, clearly defined, and dynamic. The decision levels are linked to five important components of the cardiovascular physiology in turn, i.e. the systolic blood pressure (SBP), central venous pressure (CVP), systemic vascular resistance (SVR), cardiac output (CO), and heart rate (HR). Progress down the hierarchy is dependent upon the normalisation of each physiological parameter to a value pre-selected by the clinician via fluid, chronotropes or inotropes. Since interventions at each and every level cause changes and disturbances in the other components, the proposed decision support model continuously refers back decision outcomes back to the SBP which is considered to be the overriding supervisory safety component in this hierarchical decision structure. The decision model was then translated into a computerised decision support system prototype and comprehensively tested on a physiological model of the human cardiovascular system. This model was able to reproduce conditions experienced by post-operative cardiac surgery patients including hypertension, hypovolemia, vasodilation and the systemic inflammatory response syndrome (SIRS). In all the simulated patients scenarios considered the CDSS was able to initiate similar therapeutic interventions to that of the expert, and as a result, was also able to control the hemodynamic parameters to the prescribed target values.

A Methodology to Improve PCI Use in Industry

This article presents the development of a methodology using decision trees to resolve issues in industry with using process capability indices (PCIs). The methodology forms the structure of a prototype decision support system (PDSS) for PCI selection, calculation, and interpretation. Download instructions for the PDSS are available at http://program.20m.com.

Integrated Decision Support System for Optimal Renewal Planning of Sewer Networks

Municipalities are under increasing pressure to adopt proactive and optimized renewal strategies to reduce the risks, life-cycle costs, and resources needed to maintain acceptable performance and service levels of their infrastructure assets. A new integrated approach for optimal renewal planning of municipal infrastructure systems has been developed. This paper discusses the application of the proposed approach to implement a GIS-based decision support system (DSS) to support the renewal planning of sewer networks. Condition rating, risk assessment, and prioritization techniques are described. A procedure for identifying and selecting the most suitable renewal technologies is also presented. A genetic algorithm-based multiobjective optimization technique is used to find a Pareto front of feasible solutions, each comprising a set of sewers to be renewed each year, along with the associated costs and expected benefits in terms of condition improvement and risk reduction. The paper also presents an example application of the prototype DSS on the sewer network in Regina, Canada.

Methodology for the use of DSSAT models for precision agriculture decision support

A prototype decision support system (DSS) called Apollo was developed to assist researchers in using the Decision Support System for Agrotechnology Transfer (DSSAT) crop growth models to analyze precision farming datasets. Because the DSSAT models are written to simulate crop growth and development within a homogenous unit of land, the Apollo DSS has specialized functions to manage running the DSSAT models to simulate and analyze spatially variable land and management. The DSS has modules that allow the user to build model input files for spatial simulations across predefined management zones, calibrate the models to simulate historic spatial yield variability, validate the models for seasons not used for calibration, and estimate the crop response and environmental impacts of nitrogen, plant population, cultivar, and irrigation prescriptions. This paper details the functionality of Apollo, and presents the results of an example application.

Evaluation of the implementation of a fully automated algorithm (eMPC) in an interacting infusion pump system for the establishment of tight glycaemic control in medical ICU patients

The purpose of this study was to investigate the performance of a newly developed prototype decision support system for the establishment of tight glycaemic control in patients in the medical ICU for a period of 72 hours.

Key Performance Indicators for the Assessment of Pediatric Pharmacotherapeutic Guidance

Given the paucity of actual guidance provided for managing pediatric drug therapy, prescribing caregivers must be able to draw on the limited published information in pediatrics and/or guidance provided in adults with some account for expected pediatric response. Guidance for managing drug therapy in children is clearly desirable. Our objectives were to construct key performance indicators (KPIs) for pediatric pharmacotherapy guidance to identify drugs where pharmacotherapy guidance would be most beneficial. A pilot survey to assess variation in caregiver appreciation for pediatric dosing guidance has also been constructed to provide a complementary subjective assessment. Three KPI categories, drug utilization (based on hospital admission and billing data collected from 2001 through 2006), medical need, and guidance outcome value along with a KPI composite score have been proposed. Low scores are favored with respect to prioritization for pharmacotherapy guidance. The pilot survey consisted of 15 questions to assess 1) physician knowledge regarding dosing guidance, 2) attitudes toward dose modification and patient individualization, 3) the accessibility, ease of use and appropriateness of existing data stores, and 4) frequency of dosing modification, consultation of dosing compendiums and estimate of success rate in dosing guidance. Pilot results suggest that dosing guidance is generally viewed as important and that the existing resources are insufficient to guide recommendations for all drugs. While the majority of respondents check more than one resource less than 25% of the time, at least 25% of the respondents check more than one resource 25-50% of the time. The majority viewed the relevance of dosing guidance very important to the management of drug therapy. The questionnaire is being extended to the primary care centers, the Kids First Network and specialty care centers. Results will guide the development of decision support systems (DSS) that provide patient-specific pharmacotherapy guidance as part of our pediatric knowledgebase initiative. For the top 25 most utilized agents at our institution over the last 6 years, KPI score ranged from 35 (dexamethasone) to 77 (cefazolin and ampicillin) with an average score of 55. Prototype DSS for tacrolimus and methotrexate are strongly supported by the KPI scoring which ranks their selection in the top 5% of drugs on formulary. KPI metrics provide an objective means of ranking agents for which pediatric pharmacotherapeutic guidance is clearly needed.

A Decision Support System for Telemedicine Through the Mobile Telecommunications Platform

In this paper we have discussed the application of artificial intelligence in telemedicine using mobile device. The main goal of our research is to develop methods and systems to collect, analyze, distribute and use medical diagnostics information from multiple knowledge sources and areas of expertise. Physicians may collect and analyze information obtained from experts worldwide with the help of a medical decision support system. In this information retrieval system, modern communication tools such as computers and mobile phones can be used efficiently. In this work we propose a medical decision support system using the general packet radio service (GPRS). GPRS, a data extension of the mobile telephony standard Global system for mobile communications (GSM) is emerging as the first true packet-switched architecture to allow mobile subscribers to benefit from high-speed transmission rates and run JAVA based applications from their mobile terminals. An academic prototype of a medical decision support system using mobile device was implemented. The results reveal that the system could find acceptance from the medical community and it could be an effective means of providing quality health care in developing countries.

Airline disruption management—Perspectives, experiences and outlook

Since the deregulation of many markets, airlines have become more concerned with developing an optimal flight schedule, allowing little slack to accommodate variations from the optimal solution. During operation, the planned schedules often have to be revised because of disruptions caused by severe weather, technical problems and crew sickness. Thus, airline disruption management techniques have emerged. The purpose is, first to offer an introduction to airline disruption management, provide a description of the planning processes, and deliver a detailed overview of the numerous aspects of airline disruption management. Second, it is to report on experiences from a development project on airline disruption management that is the first prototype of a multiple resource decision support system at the operations control center in a major airline to be implemented.

Data warehousing for construction equipment management

Equipment logistics, maintenance, and repair are important aspects of construction equipment management. A well-managed equipment fleet helps reduce downtime, as well as total maintenance and repair costs. With quickly growing fleets of equipment, large contractors tend to divert the maintenance and repair of equipment from equipment managers to project managers. As a result, the equipment managers shift their attention from operational-level decision-making to corporate-level strategic decision-making regarding equipment management, which is often a challenging job with the current equipment management system. This paper presents an equipment data warehouse and a prototype decision support system (DSS). The proposed equipment data warehouse enables equipment managers to visually analyze the equipment fleet data from different perspectives and at various level of details. The data-warehouse-based DSS facilitates high-level, fact-based decision-making regarding equipment logistics, supplies, maintenance, repair, and replacement and has higher levels of performance and flexibility than the current equipment management system.Key words: data warehouse, decision support system, equipment management, multidimensional modeling.

A web-based GIS Decision Support System for managing and planning USDA's Conservation Reserve Program (CRP)

The Conservation Reserve Program (CRP) is one of the largest programs of the U.S. Department of Agriculture (USDA) aimed at encouraging farmers and ranchers to address soil, water, and related natural resource issues on their lands in an environmentally sustainable manner. This paper outlines the design and development of a prototype web-GIS Decision Support System (DSS), CRP-DSS, for use in resource management and assessment of environmental quality. Specifically, the DSS is targeted toward aiding USDA to better manage and plan CRP enrollments. The DSS is based on the emerging industry-standard ArcIMS GIS platform and integrates a mapping component AFIRS (Automated Feature Information Retrieval System) and a modeling component SWAT (Soil and Water Assessment Tool). Our novel integrated web-GIS DSS is implemented using web server and Java Servlet technology over an ArcIMS platform to support data access and processing in a distributed environment. AFIRS functions as a feature extraction protocol that uses multisource geospatial data sets and SWAT serves to simulate long-term trends of soil and water quality. The prototype DSS was applied to simulate the sediment and nutrient dynamics of a small watershed in the Oklahoma Panhandle. We intend to develop the prototype CRP-DSS into a full-fledged tool geared to enable USDA better manage and plan future CRP enrollments.

CB-Contract: Case-Based Reasoning Approach to Construction Contract Strategy Formulation

The formulation of an appropriate contract strategy is a fundamental yet critical aspect of contractual arrangement for a project. This paper presents a decision support system (DSS) prototype for contract strategy formulation using the case-based reasoning (CBR) approach. The prototype is called CB-Contract. An overview on the scope and formulation process of contract strategy is provided. Contract strategy is regarded as comprising four main substrategies: (1) work packaging; (2) functional grouping; (3) contract type; and (4) award method. The significance of CBR in contract strategy formulation is examined. The overall architecture of CB-Contract is discussed, with particular emphasis on its knowledge component. A case structure for case representation has been suggested taking into account the important factors that need to be considered while formulating a contract strategy, in particular project characteristics, client's objectives, and client's comparative advantages. Issues pertaining to case indexing and similarity calculation for efficient retrieval of similar cases are explored. An illustrative example to obtain similar cases for a given set of project information is presented. Case adaptation that considers the robustness of each substrategy, the compatibility of the substrategies, and the expected effectiveness of the contract strategy is also included in the illustrative example.