Decision Support Capabilities Research Articles

The HELP hospital information system: update 1998

The HELP hospital information system has been operational at LDS Hospital since 1967. The system initially supported a heart catheterization laboratory and a post open heart Intensive Care Unit. Since the initial installation the system has been expanded to become an integrated hospital information system providing services with sophisticated clinical decision-support capabilities to a wide variety of clinical areas such as laboratory, nurse charting, radiology, pharmacy, etc. The HELP system is currently operational in multiple hospitals of LDS Hospital’s parent health care enterprise—Intermountain Health Care (IHC). The HELP system has also been integrated into the daily operations of several other hospitals in addition to those at IHC. Evaluations of the system have shown: (1) it to be widely accepted by clinical staff; (2) computerized clinical decision-support is feasible; (3) the system provides improvements in patient care; and (4) the system has aided in providing more cost-effective patient care. Plans for making the transition from the ‘function rich’ HELP system to more modern hardware and software platforms are also discussed.

Fletcher Allen Health Care’s Telemedicine Initiative

As hospitals and caregivers struggle with the new economics of health care, some are investigating telemedicine technologies, which circumvent the traditional constraints of time and place. This case describes the early stages in a teaching hospital’s use of telemedicine applications. Vermont’s only tertiary-care teaching hospital, Fletcher Allen Health Care (FAHC) is promoting video-conferencing and other telemedicine technologies in its catchment area, consisting of Vermont and six New York counties. An ambitious $30 million technology initiative was funded, with $17 million allocated to enhancing Fletcher Allen’s IT infrastructure and decision support capabilities, and $13 million allocated to development of a regional telemedicine network. The case examines how administrators and caregivers address various technical, organizational, and social risks associated with the assimilation of emerging telemedicine technologies. Fletcher Allen’s CIO (Bill Montgomery) and a vascular surgeon who describes himself as a “telemedicine evangelist” (Dr. Mike Ricci) agree that telemedicine is critical to Fletcher Allen’s successful transition to a system of “capitation” (prepaid managed care) by enabling improved services at reduced costs. Montgomery and Ricci wonder whether they are doing all that they can to encourage the use of this valuable capability, and whether they have adequately addressed such issues as medical licensure, liability, and specialist physicians’ relationships with rural caregivers.

Application of intelligent agent technology for managerial data analysis and mining

Data analysis and mining technologies help bring business intelligence into organizational decision support systems (DSS). While a myriad of data analysis and mining technologies are commercially available today, organizations are seeing a growing gap between powerful storage (data warehouse) systems and the business users' ability to analyze and act effectively on the information they contain. We contend that to narrow this gap effectively, a data analysis and mining environment is needed that can bring together and make available for use many of these technologies, that can support business users with different backgrounds, and with which the users can work comfortably.This paper illustrates the design and construction of such an environment, called the Intelligent Data Miner. IDM is Web-based and it is intended to provide an organization-wide decision support capability for business users. Intelligent agent technology is used as the basis for IDM design. IDM provides several types of data access capabilities to access and analyze the data contained in a data warehouse to obtain the critical information needed by business decision-makers. It supports both predefined and ad hoc data access, data analysis, data presentation, and data mining requests from non-technical users.An operational prototype of IDM, implemented using Java and JATLite (Java Agent Template, Lite from Stanford University), allowed us to examine the feasibility of having the "agents" automatically control and coordinate activities and tasks on the business users' behalf. These agents proved to hide the complexity of data analysis and mining activities, techniques, and methods from the business users, for effective use of the warehouse data.

Towards a knowledge-based scheduling system for semiconductor testing

This paper describes our efforts towards the development of a knowledge-based scheduling system for the scheduling of semiconductor testing operations. Semiconductor testing is the final phase of a four-phase semiconductor manufacturing process. The scheduling problem is a static deterministic version of what we call the workstation scheduling problem (WS). WS can be characterized as a generalized job shop problem with both parallel workstation clusters and batch processors; it requires sequencing and routeing decisions on discrete (i.e. nonbatch) and batch workstations. The proposed system consists of two distinct components: a knowledge base developed using a frame-based knowledge representation scheme, and a solution strategy based on filtered beam search. The scheduling mechanism and the associated knowledge representation scheme have been implemented on a Sun Sparc station 1+ using the programming language Common Lisp. We report on our experience to date with the system on three dimensions: computational experience, decision support capability, and knowledge management. Further research directions are suggested.

Data Marts: Plan Big, Build Small

Data marts provide many decision support capabilities without incurring the cost and complexity associated with an enterprise data warehouse. With proper planning, they can be gradually consolidated to create a centralized warehouse that meets business needs and leverages improved technologies.

A methodology for estimation of vehicle emissions in an urban environment: an example from Greater Manchester

Road transport is a major contributor to urban air pollution. The introduction of local air qua lity management in the UK will require objective test procedures to evaluate and prioritise the air pollution benefits of existing transport systems and proposed developments. This methodology has been developed to assist the land use and transport planning professionals in evaluating current and potential future impacts on air quality. The method couples an emissions estimation procedure to a traffic flow database. It requires data on emission factors, the composition of the vehicle fleet, vehicle control technologies and the daily traffic flow profile. With these data, it is possible to generate emission estimates per kilometre, link or road as selected by the user. Forecasts can be made by varying input variables. The current methodology allows prediction of five or more pollutant species/classes, limited only by availability of emission factors. The method utilises a commercially available personal computer based spreadsheet. Further coupling of the method to a geographical information system will improve the decision support capability of the method.

Conceptual Modelling in Generic Prototyping Approach

The generic prototyping approach (GPA) has been conceived according to some major orientations in complex system engineering field, with the emphases on manufacturing systems and their decision support capabilities. In the framework provided by this approach, the conceptual modelling is a central activity in the object oriented analysis and design of the future generic system. The paper presents the place of the conceptual model in the GP A development cycle, the specific structure of this constmct and its role as the major result of the requirement definition phase. Then, the adopted model structure is argued and the solutions proposed for the implementation of the object, control and user-interface components are detailed, putting the stress on the decision control Petri nets formalism for the behaviour modelling. A case study of a job shop control system has been chosen to illustrate the approach.

GIS and Environmental Decisionmaking to Aid Smelter Reclamation Planning

Abandoned mines and mining-related activities typically cause environmental problems related to erosion and pollutant transport. Traditional methods of smelter reclamation plan design are hampered by the lack of data integration and by time-consuming analysis. The proposed spatial decision-support system will minimize these problems as data integration and analysis are offered within one computerized environment. A geographical information system (GIS), remotely sensed data, erosion modeling, and multicriteria decisionmaking (MCDM) methods have been integrated to support reclamation procedures better. Integration of the digital data sources and analysis will produce more realistic, up-to-date models of damaged lands. This methodology is applicable to any number of damaged sites, including mine sites, smelter sites, widespread hazardous-waste sites, and areas negatively impacted by intense agriculture or forestry. The system has been tested at the Anaconda smelter site, an Environmental Protection Agency superfund site near Butte, Montana. The primary surficial problems are related to metal toxicity and transport. In addition to producing a description of the physical conditions at the entire site, the system provides spatial decision-support capabilities for generating and evaluating revegetation strategies for the site with the use of different priority schemes.

Computer decision support for capital budgeting: some empirical findings of practice

While recent surveys suggest that capital budgeting systems in business organizations continue to become more formalized and sophisticated, a constraint on the use of sophisticated capital budgeting techniques seems to be the degree of support provided by firms' capital budgeting information systems (CABIS). This paper, based on a survey of 146 large firms, outlines the current status of CABIS and their usage pattern. It was found that although two-thirds of sample firms have specific computer application systems for capital budgeting, most CABIS are relatively unsophisticated and less than adequate in providing the information and decision support capabilities required to use sophisticated capital budgeting techniques effectively. In particular, the barrier and problems encountered in the use of probabilistic risk analysis were explored. Implications of these findings are discussed.

Computer Decision Support for Capital Budgeting: Some Empirical Findings of Practice

While recent surveys suggest that capital budgeting systems in business organizations continue to become more formalized and sophisticated, a constraint on the use of sophisticated capital budgeting techniques seems to be the degree of support provided by firms’ capital budgeting information systems (CABIS). This paper, based on a survey of 146 large firms, outlines the current status of CABIS and their usage pattern. It was found that although two-thirds of sample firms have specific computer application systems for capital budgeting, most CABIS are relatively unsophisticated and less than adequate in providing the information and decision support capabilities required to use sophisticated capital budgeting techniques effectively. In particular, the barrier and problems encountered in the use of probabilistic risk analysis were explored. Implications of these findings are discussed.

DEVELOPING A SINGLE PERFORMANCE INDICATOR FROM HIERARCHICAL METRICS

AbstractA contemporary System Engineering task is development of process performance metrics. Executive management desires a single performance indicator that combines subsidiary metrics into a meaningful summary representation of organization health with respect to its mission. A purely mathematical approach can produce such an indicator, but when constituent metrics also contain subsidiary metrics, a multiple stage method is required. Because not all metric result customers are fully competent to audit the result, this paper sets forth a generally understandable method that “presells” the output to all involved parties through their approval of each model base before alternatives performance data are entered. The eminent decision support capability inherent in this method suits it for complex tradeoff analyses and System Engineering Maturity Modeling.

Spatial data quality and its evaluation

This paper reviews recent concepts of data quality assessment and presents a model for data quality evaluation. Data quality may be acquired in a static state by quantitative or qualitative testing, or in an operational state by tracking what processing steps have been applied. The complexity and variety of spatial data attests to the reconsideration of data quality evaluation: as one goal for evaluating spatial data quality is to determine fitness for use, representation of quality information should be based on capabilities for decision support. Four steps in the evaluation process are described, with specific tasks outlined for each step. Computer tools for evaluation in both static and operational states may improve the amount and detail of data quality information archived with digital data.

Establishing software development process control: Technical objectives, operational requirements, and the foundational framework

To produce and maintain product quality, one must control the development and maintenance processes through the collection, examination, and analysis of both process and product indicators. Process indicators provide measures that reflect the effectiveness of software development and maintenance activities. Product indicators provide measures that indicate the extent to which desirable, quality attributes are present (or absent) in the product (documentation and code). This article proposes a foundational framework for establishing control over the software development process. Critical objectives stressed within this framework include the complementary integration of maintenance and development activities, the identification and definition of a (semi)automated data collection and analysis process which employs quality indicators that are definitively linked to the existence of process and product attributes, and the formulation and use of control methods that are designed to work within the defined automated process and provide decision support capabilities. The significance and necessity of these objectives are established through an examination of the abstraction refinement model, the objectives/principles/attributes framework, and the software quality indicator concept.

DREAM: a shell-like software system for medical data analysis and decision support

A software system was designed whose aim is to support everyday scientific research of physicians in different fields of medicine. DREAM is a shell-like tool which can be customized embedding in it the desirable structure of a particular medical problem. Various basic statistical analyses are provided along with the decision support capabilities. The decision aid is proposed in two steps — feature selection and classifier design. Genetic algorithm is implemented as the feature selection procedure. The classifier design option includes crisp and fuzzy k-Nearest Neighbors rule and a two-level classification scheme based on majority rule on the votes of several first-level k-Nearest Neighbors classifiers. The system's performance is illustrated with a database from aviation medicine.

The French communicable diseases computer network: A technical view

This paper describes an information system (IS) established in France in 1984 for the national surveillance of communicable diseases. This IS is based on a videotex server and a relational database management system. The videotex server is the IS front-end. It performs the following functions: interpersonal communications, synthetic information retrieval into an epidemiologic info-base and data entry owing to its specialized applications. The relational database management system allows the user to manage and consult an epidemiologic database updated in quasi-real time. Several specific tools have also been developed in order to enhance data representation and analysis and the decision support capabilities of the IS.

Development of decision support systems

Use of hospital information systems (HIS) are no longer limited to administrative functions. The addition to these systems of decision support capability is now a necessity. Development of the decision support modules requires a different software architecture than that employed by most HIS systems today. This paper describes the generic uses of decision support throughout the many hospital applications. Several levels of decision support are outlined with examples to illustrate the many areas where decision support is useful. At LDS Hospital in Salt Lake City, Utah we have developed an HIS using a new software architecture which supports the creation of decision support applications. This system uses a frame structure to represent knowledge. Examples of the frames and their syntax is presented. Using the frame tools which are provided, an application developer can easily develop and test decision support modules which interact directly with the clinical user and the patient database.

Derived Relations with Exceptions Decision Support Capabilities

:Despite the widespread use of relational database management systems, their decision support capabilities have been limited. These limitations include: (1) very limited support for expression of general statements and exceptions, (2) limited capabilities for what-if analysis, and (3) problems with the way derived data is handled. This paper shows that additional power can be placed in relational database systems via a new construct called Derived Relations with Exceptions (dres). Dres are a superset of relational views that provide greater decision support capabilities in that they handle exceptions to general rules and can operate in a hypothetical mode that provides an easier way to experiment with alternative scenarios in a what-if fashion. Dres are implemented by extending the SQL database language.

Representing generalizations and exceptions in expert database systems

To further increase the decision support capabilities of database management systems, previous research has suggested the development of expert database systems by coupling expert systems to database management systems. One approach is to combine the capabilities of logic systems and relational databases. Logic allows the specification of general rules representing abstract knowledge while database management systems provide efficient management of large masses of data representing specific facts. In many practical situations, general rules cannot or are not intended to describe every possible case, thus leading to the necessity of representing exceptions. A classification of exceptions is made in this paper, and their representation in expert database systems that combine logic and relational databases is discussed. In addition, a description is made of extensions needed to the relational language SQL to permit the specification of rules that allow exceptions.

A Database Approach to Hierarchical Materials Planning

A workstation‐based system for materials planning is intended to complement a host‐based materials‐planning system, thereby leading to a multi‐level system that combines fully detailed planning procedures with “aggregate” decision support capabilities. Planning objects as well as planning procedures are formulated within the relational database frame‐work. By that means, at execution time the database management system guarantees processing efficiency as well as consistency control. After a short characterisation of the state‐of‐the‐art of database utilisation in conventional materials planning, a set of requirements which have to be met by the proposed approach is formulated. Based on this, the suitability of the relational database model as a framework for multi‐stage materials planning is discussed. In particular, the integration of abstraction hierarchies is emphasised and hierarchical planning procedures adopted from artificial intelligence are integrated into the concept. Some examples adopted from a prototype show that, at least for simple planning problems, it is possible to achieve end‐user support at any level of detail when using a relational database system for materials planning.

Geographic Information Systems: An Emerging Component of Decision Support

Quietly, yet productively, geographic information systems(GISs) have introduced new decision support capabilities in organizations whose demands for spatially oriented data bases are important. These systems will have a substantive impact in selected industries, government units, and businesses by integrating maps with spatially oriented data base information and enabling decision makers (i.e., IS and senior managers) to access forms of information not previously available.