Decision Support Platform Research Articles

Reference distribution based decision support platform

There many decision problems where numerous partial achievement functions are considered impartially which makes the distribution of achievements more important than the assignment of several achievements to the specific criteria. Such models are generally related to the evaluation and optimization of various systems which serve many users where quality of service for every individual user defines the criteria. This applies to various technical systems, like to telecommunication ones among others, as well as to social systems. An example arises in location theory, where the clients of a system are entitled to equal treatment according to some community regulations. This paper presents an implementation of decision support framework for such problems. This platform is designed for multiple criteria problems analyzed with the reference distribution approach. Reference distribution approach is an extension of the reference point method.

Automated Correction of Room Location Errors in Anesthesia Information Management Systems

Anesthesia information management systems (AIMS) and operating room information management systems (ORIMS) are both used in operating rooms (OR). Anesthesia providers use AIMS to document their care in near real-time, including milestone events, and these systems automatically record vital signs from patient monitors. Circulating nurses use ORIMS primarily to document procedural information. Because of automatic documentation, AIMS would be ideal platforms for OR managerial decision support if the correct locations of cases in progress were known accurately. Trust is diminished if recommendations are poor. We compiled room location error rates from prior analyses of ORIMS data. Data from 24 consecutive 4-wk periods (45,459 cases) were analyzed from one hospital where both ORIMS and AIMS data were available. The actual location of cases was inferred from the physical location of the workstation recording the majority of pulse oximetry saturations. These were compared to the listed location in the AIMS and the final corrected location in the ORIMS. The scheduled and final ORIMS locations were compared to determine how often location changes were updated before the start of anesthesia. The location of cases was inferred in near real-time by using the identifier of the AIMS workstation transmitting pulse oximetry saturated electrocardiogram heart rate, and end-tidal CO(2) partial pressures. Location error rates ranged from 0% to 7.5% at 42 hospitals. The error rate at the studied hospital was just 0.4%, showing that the hospital was suitable for investigation. The 0.4% error rate was based on cases listed as overlapping in the same OR, and thus under-estimated the actual error rate in the ORIMS (1.0%). With education, there was a decrease in the moved cases in the ORIMS whose location was not changed before the start of anesthesia (9.3%-2.0%, P < 10(-5)). Despite the significant improvement (P < 10(-5)) in the error rate between the AIMS listed and actual locations, the residual AIMS real-time error rate was 4.1% of cases. Use of vital sign data reduced errors to <0.1%. Education can only modestly improve the accuracy of OR locations in ORIMS and AIMS data. The actual location can be inferred, either in near real-time or afterwards, from the AIMS workstation transmitting vital sign data. This addresses the fundamental problem of cases having more than one location during the course of anesthetic care (e.g., holding area, block room, OR, and postanesthesia care unit), which cannot be determined from scheduled ORIMS or listed AIMS locations.

Waste management modeling with PC‐based model — EASEWASTE

AbstractAs life‐cycle‐thinking becomes more integrated into waste management, quantitative tools are needed for assessing waste management systems and technologies. This article presents a decision support model to deal with integrated solid waste management planning problems at a regional or national level. The model is called EASEWASTE (environmental assessment of solid waste systems and technologies). The model consists of a number of modules (submodels), each describing a process in a real waste management system, and these modules may combine to represent a complete waste management system in a scenario. EASEWASTE generates data on emissions (inventory), which are translated and aggregated into different environmental impact categories, e.g. the global warming, acidification, and toxicity. To facilitate a “first level” screening evaluation, default values for process parameters have been provided, wherever possible.The EASEWASTE model for life‐cycle‐assessment of waste management is described and applied to a case study for illustrative purposes. The case study involving hypothetical but realistic data demonstrates the functionality, usability, and flexibilities of the model. The design and implementation of the software successfully address the substantial challenges in integrating process modeling, life‐cycle inventory (LCI), and impact assessment (LCIA) modeling, and optimization into an interactive decision support platform. © 2008 American Institute of Chemical Engineers Environ Prog, 2008

Service-oriented Subscription Management of Medical Decision Data in the Intensive Care Unit

This paper addresses the design of a platform for the management of medical decision data in the ICU. Whenever new medical data from laboratories or monitors is available or at fixed times, the appropriate medical support services are activated and generate a medical alert or suggestion to the bedside terminal, the physician's PDA, smart phone or mailbox. Since future ICU systems will rely ever more on medical decision support, a generic and flexible subscription platform is of high importance. Our platform is designed based on the principles of service-oriented architectures, and is fundamental for service deployment since the medical support services only need to implement their algorithm and can rely on the platform for general functionalities. A secure communication and execution environment are also provided. A prototype, where medical support services can be easily plugged in, has been implemented using Web service technology and is currently being evaluated by the Department of Intensive Care of the Ghent University Hospital. To illustrate the platform operation and performance, two prototype medical support services are used, showing that the extra response time introduced by the platform is less than 150 ms. The platform allows for easy integration with hospital information systems. The platform is generic and offers user-friendly patient/service subscription, transparent data and service resource management and priority-based filtering of messages. The performance has been evaluated and it was shown that the response time of platform components is negligible compared to the execution time of the medical support services.

Real-time decision support for planning concrete plant operations enabled by integrating vehicle tracking technology, simulation, and optimization algorithms

By integrating the vehicle tracking system, discrete-event simulation algorithm, and evolutionary optimization algorithm, we developed HKCONSIM-Realtime, a decision-support platform created specifically for handling ready-mixed concrete operations. This platform is capable of (1) tracking the positions of concrete trucks and monitoring the motion and status of concrete deliveries in real time, (2) transforming the tracking records into data that provide updated input to simulation, and (3) optimizing the operations and logistics of concrete production based on simulation of the production system using the most current data. This paper presents an overview of the design and development of (1) the hardware and software modules, (2) the data flow and processing throughout the system, and (3) the role of the system in providing interactive, effective support for the human operator to attain cost efficiency. Case studies are given to demonstrate the functionality and application of the prototype system. Key words: simulation, optimization, vehicle tracking, construction planning, ready-mixed concrete, Hong Kong.

05/01811 Comprehensive risk assessment for railtransportation of dangerous goods: A validated platform for decision support: Gheorghe, A. V. Reliability Engineering & System Safety, 2005, 88, (3),247–272

05/01811 Comprehensive risk assessment for railtransportation of dangerous goods: A validated platform for decision support: Gheorghe, A. V. Reliability Engineering & System Safety, 2005, 88, (3),247–272

OPF With SVC and UPFC Modeling for Longitudinal Systems

This paper presents a formulation of the Optimal Power Flow problem with an explicit modeling of Static Var Compensator (SVC) and Unified Power Flow Controller (UPFC) devices. The optimization problem is solved by using Sequential Quadratic Programming, where two convergence criteria and four different methods are studied to solve the quadratic subproblems. The proposed model is integrated in an object-oriented based decision support platform for competitive power markets. Validation of the method and practical applications to real longitudinal systems are discussed, where FACTS location and a UPFC-based interconnection are described. Results show the impact of SVC and UPFC FACTS technologies in the physical and economic behavior of a real system.

Comprehensive risk assessment for rail transportation of dangerous goods: a validated platform for decision support

Currently, the most advanced and well documented risk assessments for the transportation of dangerous goods by railway take into account: statistics-based loss of containment frequencies, specification of potential consequences for a given release situations using event tree methodology as an organisational tool and consequence calculation models to determine a risk figure known as CCDF (Complementary Cumulative Distribution Function). Such procedures for the risk assessment (including for example decision-making on preventive measures) may offer only a limited insight into the causes and sequences leading to an accident and do not allow for any kind of predictive analysis. The present work introduces an enhanced solution, and a related software platform, which attempts to integrate loss of containment causes and consequences with system's infrastructure and its environment. The solution features: the use of a detailed Master Logical Diagram, including fault/event tree analysis to determine a loss of containment frequency based on different initiating events, scenarios and specific basic data, the characterization of a resulting source term following a release situation, and the calculation of various potential impacts on the neighbouring site. Results are wrapped into a CCDF format for each selected traffic segment. The risk-related results are integrated on a software platform, structured as a decision support system using intelligent maps and a variety of GIS (Geographical Information System) data processing procedures. The introduction of the hot spot approach, allows us to focus on the most risk-relevant areas and to use information on various railway infrastructure elements (e.g. points, tunnels), are the basis of the new models employed. The software is applicable to any railway transportation system, comprising its technical infrastructure, rolling stock, human actions, regulation and management procedures. It provides the determination of the annual societal risk due to potential accident scenarios, while also revealing information on the potential causes of an accident taking into account spatial parameters. The approach and software have been validated by a case study done for a particular traffic segment of the Swiss Federal Railway company.

A decision support maintenance management system

Competitiveness has forced companies to improve the overall performance of the business. In the area of maintenance, much has been written about strategies, such as total productive maintenance or reliability centred maintenance, in order to increase the reliability and therefore capacity of the industrial plants in their quest for world‐class maintenance. However, if a strategy is to be effective, it must be supported with an invaluable resource, information. In the present work, the role of computerised maintenance management systems (CMMSs) is discussed as a powerful tool necessary for obtaining information from raw data and support the decision‐making process. Furthermore, a CMMS has been designed, developed, customised and implemented for a disc brake pad manufacturing company based in England. In addition, a maintenance maturity grid has been proposed to support the CMMS implementation. The grid shows that the complexity of the CMMS will increase as the maintenance function moves from a reactive to a proactive culture. The implemented CMMS aims to reduce total downtime and frequency of failures of the machines by improving the efficiency and effectiveness of the maintenance force. The computer program simplifies and reduces the time of data capture compared to the currently used paper‐based reporting system. It also provides the maintenance planners with a platform for decision analysis and support often ignored in the commercial CMMSs available in the market.

Arrhythmogenic right ventricular dysplasia/cardiomyopathy (ARVD/C): a multidisciplinary study: design and protocol.

Arrhythmogenic right ventricular dysplasia/cardiomyopathy (ARVD/C) is a relatively newly recognized disease. A clinical profile of patients with this condition was first published in 1982.1 In that report, it was observed that the majority of patients were male. Patients presented with ventricular tachycardia of left bundle-branch block morphology. An enlarged right ventricle due to fibrofatty infiltration of the right ventricular free wall and a familial association were noted. It was considered to be a rare disease of unknown cause. Since then, it has been diagnosed with increasing frequency and has been reported to account for 3% to 5% of unexplained sudden cardiac death under the age of 65 years.2,3 Evidence of the disease is found in 30% to 50% of family members who are studied by noninvasive tests, including ECG, echocardiography, and signal-averaged ECG.4,5 It has been suggested that MRI may also be used for diagnostic purposes, but this remains controversial.6,7 Six genetic loci have been reported to be associated with ARVD/C, and 3 genes have been identified: ryanodine receptor (RyR2),8 plakoglobin (JUP),9and desmoplakin (DSM).10 There is autosomal dominant transmission with all the genetic forms except Naxos disease8 and Carvahal syndrome,11 both of which have autosomal recessive transmission. These 2 autosomal recessive disorders are variants of ARVD/C that are associated with skin and hair abnormalities. The cardiac presentation in Carvahal syndrome is that of a left ventricular cardiomyopathy and arrhythmias. With the recognition that ARVD/C is frequently familial and can cause arrhythmic death, the clinical challenge is how to definitively identify individuals with ARVD/C who have mild or minimal structural abnormalities of the right ventricle. Definite identification of minimal structural abnormalities of the right ventricle can be difficult because of the irregular shape and asymmetrical contractile pattern …

Data Warehouse Strategy to Enable Performance Analysis

The Virginia Department of Transportation (VDOT) has engaged to implement an enterprise data warehouse as part of a strategic investment in its information technology (IT) infrastructure. Data warehousing provides an information architecture that serves as the enterprisewide source of data for performance analysis and organizational reporting. To assist VDOT in achieving its strategic outcome area objectives, a programming and scheduling (P&amp;S) data mart is being developed to track preconstruction project activities. This data mart and subsequent data marts function as departmental decision support platforms, enabling VDOT’s operating divisions to perform their own enhanced analytical processing, visualization, and data mining for more informed business decision capabilities. Presented is a case study based on the enterprise data warehouse and P&amp;S data mart being developed and implemented for VDOT by TransCore. Explicitly described is how one VDOT division, Programming and Scheduling, will benefit by investing in IT to achieve its strategic goals. The design approach, methodology, and implementation procedure for the P&amp;S decision support data mart are detailed. The methodology for capturing the performance measures that have been defined by the P&amp;S division in the context of its strategic outcome areas is highlighted. Recommended future direction and the technologies that the agency should adopt to continue to maximize their IT investment are outlined.