Olivia R. Liu Sheng

Formulating the Data-Flow Perspective for Business Process Management

Workflow technology has become a standard solution for managing increasingly complex business processes. Successful business process management depends on effective workflow modeling and analysis. One of the important aspects of workflow analysis is the data-flow perspective because, given a syntactically correct process sequence, errors can still occur during workflow execution due to incorrect data-flow specifications. However, there have been only scant treatments of the data-flow perspective in the literature and no formal methodologies are available for systematically discovering data-flow errors in a workflow model. As an indication of this research gap, existing commercial workflow management systems do not provide tools for data-flow analysis at design time. In this paper, we provide a data-flow perspective for detecting data-flow anomalies such as missing data, redundant data, and potential data conflicts. Our data-flow framework includes two basic components: data-flow specification and data-flow analysis; these components add more analytical rigor to business process management.

Dynamic file migration in distributed computer systems

The importance of file migration is increasing because of its potential to improve the performance of distributed office, manufacturing and hospital information systems. To encourage research in the file migration problem, the authors summarize accomplishments of researchers of the problem, provide a detailed comparison of file migration and dynamic file allocation problems, and identify important areas of research to support the development of effective file migration policies.

Adoption of telemedicine technology by health care organizations: An exploratory study

Recent advances in information and biomedicine technology have significantly increased the technical feasibility, clinical viability, and economic affordability of telemedicine-enabled service collaboration and delivery. Health care organizations around the world have become increasingly interested in acquiring and implementing telemedicine technology to improve or extend existing patient care and services. The ultimate success of telemedicine in an adopting organization requires adequate attention to both technological and managerial issues. This study examined organizational technology adoption, an essential management issue facing many health care organizations interested in or currently evaluating telemedicine. On the basis of a framework proposed by Tornatzky and Fleischer [1], we developed a research model for targeted technology adoption and empirically evaluated it in a survey study that involved most of the public health care organizations in Hong Kong. Results from our exploratory study suggest that the model exhibits reasonable significance and explanatory utility to differentiate between adopting and nonadopting organizations. Specifically, the collective attitude of medical staff and perceived service risks were found to be significant determinants of targeted technology adoption. Several research and management implications that emerged from our study findings are also discussed.

Telework: Existing Research and Future Directions

Telework, which is defined as work performed at home or a satellite office to reduce commuting, is attracting much attention as an alternative way to organize work. Numerous studies have pointed out a variety of advantages of telework for individuals, organizations, and society. Current telework research, however, displays many weaknesses that inhibit use of this alternative as an effective vehicle to promote distributive organizational design. This study was undertaken to characterize existing telework research, improve understanding of problems and issues of telework, and guide future research directions. A review of the relevant literature and a characterization of telework were conducted from 3 different angles: the research methodology, the focus of existing telework studies, and the research paradigm. First, an overall lack of robust research methodology was found in many studies. Second, although telework is an organizational phenomenon, disproportionate attention has been given to teleworker-related personal issues. Finally, the current telework paradigm was discovered to be characterized by suitability-based planning that selects appropriate persons and tasks and by ad hoc implementation in response to local needs. We suggest that future research could be enriched with more rigorous research methodology, more balanced focus for studies, and more flexible perspectives in the research paradigm.

A decision support system for lower back pain diagnosis: uncertainty management and clinical evaluations

Lower back pain (LBP) is a common medical problem that deprives many individuals of their normal lifestyles and keeps them from routine activities. Diagnosing LBP is challenging because it requires highly specialized knowledge involving a complex anatomical and physiological structure as well as diverse clinical considerations. Although a handful of studies have proposed or developed systems to support LBP diagnosis and improve knowledge sharing, these systems have limited scope, lack systematic evaluations, and/or ignore diagnoses that consist of multiple parts (i.e., decision outcomes), each of which corresponds to a particular medical condition, disease, or abnormality. In this study, we design, implement, and evaluate a Web-based decision support system that employs an intuitive and easy-to-use framework to assess the patients information and recommend a diagnosis consisting of one or multiple parts. Our system design addresses the challenging characteristics of a LBP diagnosis and uses verbal probability estimation to represent and reason about the associated uncertainty. Our evaluations are systematic, including knowledge base verification, system validation using a modified Turing test, and clinical efficacy assessment involving 5 clinicians and 180 real-world cases collected from geographically dispersed clinics. Our evaluation design is more thorough than those used by most previous studies, and the proposed system is relatively ready for clinical deployment. Therefore, this study both contributes to decision support systems research and has advanced clinical support for LBP diagnosis. In light of some of the limitations of this study, we also identify and discuss several areas that need continued investigation.

Integrating expert systems with group decision support systems

Expert systems are powerful tools that serve as adjuncts to decision making and have found wide applicability in a wide variety of areas. Integrating expert systems with group decision support systems has the potential to enhance the quality and effeciency of group communication, negotiation, and collaborative work. This paper examines possible synergies between the two technologies and provides a survey of current partially-integrated systems. Finally, a prototype design of a highly-integrated system is described with directions for further research.

An object-oriented methodology for knowledge base/database coupling

1 base and facts into a database enhances the maintenance and portability of both and thereby increases their life spans [l, 15, 221. n na* q nrrr;-r 7 Advantages of coupled knowledge base/ database (KB/DB) systems have been widely recognized by both researchers and practitioners (l, 10, 15,21, 401. Unfortunately, large knowledge bases (such as those required to support database semantics) Irl:rr I~rrr:rr7 are difficult to develop and maintain because of theu htmted capacity for handling large amounts of factual data. Our goal is to investigate how to achieve a nahlral and effective KB/DB coupling. Al:..:” I :.. Intensional knowledge has been classified as “knowledge beyond the factual content oFthe database” [45]. Intensional 1’ knowledge is more abstract than extensional knowledge items and the system knowledge needed for query A and response control. The least abstract subcategory of intensional knowledge, structural knowledge, cornprises the

LinkSelector: A Web mining approach to hyperlink selection for Web portals

As the size and complexity of Web sites expands dramatically, it has become increasingly challenging to design Web sites where Web surfers can easily find the information they seek. In this article, we address the design of the portal page of a Web site, which serves as the homepage of a Web site or a default Web portal. We define an important research problem---hyperlink selection: selecting from a large set of hyperlinks in a given Web site, a limited number of hyperlinks for inclusion in a portal page. The objective of hyperlink selection is to maximize the efficiency, effectiveness, and usage of a Web sites portal page. We propose a heuristic approach to hyperlink selection, LinkSelector, which is based on relationships among hyperlinks---structural relationships that can be extracted from an existing Web site and access relationships that can be discovered from a Web log. We compared the performance of LinkSelector with that of the current practice of hyperlink selection (i.e., manual hyperlink selection by domain experts), using data obtained from the University of Arizona Web site. Results showed that LinkSelector outperformed the current manual selection method.

Solving discrete multicriteria decision problems based on logic on logic-based decision support systems

Since the initial consideration, early experimental prototypes and clinical use over the 1950s, 1960s, w x and 1970s 7 , both the importance and the chalŽ . lenges of decision support systems DSS for healthcare have been elevated because of the increasing financial significance and cost-control and quality improvement pressures of healthcare. Because of the improvement in medical knowledge and practices, the demand for healthcare services and resources have been increasing steadily in the 20th century. In 1998, the healthcare expenditure w x in US is

Mining competitor relationships from online news: A network-based approach

1160 billion and 13.6% of the GDP 9 , w x rising from the 1950s from less than 5% 3 . As this demand has exceeded the supply of healthcare revw x enue and services since the early 1990s 2 , the pressure to control cost and improve quality has been growing. Computerized decision support which is targeted at assisting healthcare providers and administrators with such decision tasks as information retrieval, data analysis, diagnosis and test, procedure and case management recommendation has been one of the critical information technologies heavily dew x plored to transform healthcare 1 . Good decision support depends on reliable patient data and medical knowledge, and effective decision models and problem solving methods. Healthcare decision support is faced with the challenges of complex and diverse data and knowledge forms and tasks, the lack of standardized terminology compared to basic sciences, the stringent performance and accuracy requirements and the prevalence of legacy systems. Its research has high values in discovering new decision support requirements, methods, and tools that can be generalizable to other application areas. This issue samples recent research results in healthcare decision support that span a range of research problems in focus and the research methods used. These research results exemplify impact of both high theoretical and practical values via the use of real world problem and testing settings and the rigor of the studies. The following overviews the five articles and three short contribution papers included in the issue. AAutomated Learning of Patient Image Retrieval Knowledge: Neural Networks versus Inductive Decision TreesB by Liu Sheng et al. demonstrated the potency of two automated learning techniques to predict and prefetch prior patient image to be retrieved during a reading radiologist’s primary image reading. Such decision support techniques can be easily replicated for different healthcare practices using health providers’ clinical log data. AReducing Surgical Patient Costs Through Use of An Artificial Neural Network to Predict Transfusion RequirementsB by Steve Walczak and John Scharf demonstrated the feasibility of reducing healthcare expenditures without lowering healthcare quality using decision support technology. It showed that radial function based neural networks can provide surgical blood order decision support that increases blood order efficiency and surgical cost savings. This study gives a clear testimony that the healthcare cost savings potential of judicial decision support cannot be underestimated. AEstimating DrugrPlasma Concentration Levels by Applying Neural Networks to Pharmacokinetic Data SetsB by Kristin Toole, Hsinchun Chen and Hsiao-Hui Chow addressed the need to provide a cost effective, user friendly, and timely analysis tool for effectively predicting blood contraction ranges in human subjects. The paper exemplified how a feedforward back-propagation neural network can over-