Agent‐Based Referral Decision Support Framework for Medical Services Identification: A Design Science Approach

Intelligent decision support (IDS) systems leverage artificial intelligence techniques to generate recommendations that guide human users through the decision making phases of a task. However, a key challenge is that IDS systems are not perfect, and in complex real-world scenarios may produce suboptimal output or fail to work altogether. The field of explainable AI (XAI) has sought to develop techniques that improve the interpretability of black-box systems. While most XAI work has focused on single-classification tasks, the subfield of explainable AI planning (XAIP) has sought to develop techniques that make sequential decision making AI systems explainable to domain experts. Critically, prior work in applying XAIP techniques to IDS systems has assumed that the plan being proposed by the planner is always optimal, and therefore the action or plan being recommended as decision support to the user is always optimal. In this work, we examine novice user interactions with a non-robust IDS system – one that occasionally recommends suboptimal actions, and one that may become unavailable after users have become accustomed to its guidance. We introduce a new explanation type, subgoal-based explanations, for plan-based IDS systems, that supplements traditional IDS output with information about the subgoal toward which the recommended action would contribute. We demonstrate that subgoal-based explanations lead to improved user task performance in the presence of IDS recommendations, improve user ability to distinguish optimal and suboptimal IDS recommendations, and are preferred by users. Additionally, we demonstrate that subgoal-based explanations enable more robust user performance in the case of IDS failure, showing the significant benefit of training users for an underlying task with subgoal-based explanations.

A SDSS combines database storage technologies, geographic information systems (GIS) and decision modeling into tools which can be used to address a wide variety of decision support areas (Eklund, Kirkby, and Pollitt, 1996). Recently, various emerging technologies in computer hardware and software such as speedy microprocessors, gigabit network connections, fast internet mapping servers along with Web-based technologies like extensible markup language (XML), Web services, etc provide promising opportunities to take the traditional spatial decision support systems one step further to provide easy-to-use, round-the-clock access to spatial data and decision support over the Web. Traditional DSS and Web-based spatial DSS can be further improved by integrating expert knowledge and utilizing intelligent software components (such as expert systems and intelligent agents) to emulate the human intelligence and decision making. These kinds of decision support systems are classified as intelligent decision support systems. The objective of this chapter is to discuss the development of an intelligent web-based spatial decision support system and demonstrate it with a case study for planning snow removal operations.

A SDSS combines database storage technologies, geographic information systems (GIS) and decision modeling into tools which can be used to address a wide variety of decision support areas (Eklund, Kirkby, and Pollitt, 1996). Recently, various emerging technologies in computer hardware and software such as speedy microprocessors, gigabit network connections, fast internet mapping servers along with Web-based technologies like extensible markup language (XML), Web services, etc provide promising opportunities to take the traditional spatial decision support systems one step further to provide easy-to-use, round-the-clock access to spatial data and decision support over the Web. Traditional DSS and Web-based spatial DSS can be further improved by integrating expert knowledge and utilizing intelligent software components (such as expert systems and intelligent agents) to emulate the human intelligence and decision making. These kinds of decision support systems are classified as intelligent decision support systems. The objective of this chapter is to discuss the development of an intelligent web-based spatial decision support system and demonstrate it with a case study for planning snow removal operations.

With the increased complexity and uncertainty in business operations, adaptive and collaborative business processes and exception management (EM) are gaining growing attention. In the logistics industry, the current logistics exceptions are managed using human resources together with the traditional workflow technology-based supply-chain management or other logistics tools. The traditional workflow technology models and manages business processes and anticipated exceptions based on predefined logical procedures of activities from a centralised perspective that offers inadequate decision support for flexibility and adaptability in EM. These procedures are limited when monitoring logistics activities in real time in order to detect and resolve the exceptions in a timely manner. In order to mitigate these problems, a design-science research approach-specifically an intelligent-agent decision support approach in logistics EM-has been proposed and investigated in this research. It contains three interrelated research phases. The first research phase focuses on the conceptualisation of the logistics EM. It consists of two parts. The first part is logistics exception classification, in order to enable more efficient decision support practices for logistics EM. The second part focuses on the development of the conceptual framework (an artefact) for design and development of logistics EM systems for decision making. The second research phase focuses on the formalisation of the conceptual framework. A multi-agent-based logistics EM system is designed based on the conceptual framework. The third research phase will focus on the development of the designed logistics EM artefact. It will include two stages. First, a prototype will be developed. To provide more adaptive, flexible and collaborative decision support, the intelligent agent technology will be used for implementation. Second, the prototype will be evaluated via social-science research methods: semi-structured interviews and laboratory experiment. It is proposed that this theory-driven agent-based logistics EM system will provide more efficient and timely decision-making support for managers in relation to logistics EM. The designed artefacts and the research design are the major contributions of this research, which add knowledge to design-science research theory and practice. The conceptualisation-formalisation-development research approach can be applied in other similar IS design-science research.

In this paper, the authors have presented an expert system to support decision makers in nutrition therapy planning. This system is an extended version of a fuzzy decision support system for nutrition therapy. The presented expert system is equipped with an updated knowledge base component by using a set of rules. Also in order to deal with vagueness and uncertainty, fuzzy set theory could provide a suitable framework for data management, modelling and decision support. Therefore, fuzzy rules empower this system to be implemented more realistically. In addition, for developing knowledge management component, artificial neural network (ANN) is applied to survey the input data and information in the long term. The integration of ANN with the expert system provides the possibility for a set of novel rules to be generated and consequently adds new knowledge to the system.

A decision support and information delivery framework, CoastAdapt, has been built to support the coastal adaptation community in Australia to take action to address climate change and sea-level rise. For such frameworks to be useful, used and long-lived, their development requires collaboration between creators and potential users. Therefore, we undertook extensive consultation throughout the design, build and evaluation. In this paper, we explore those aspects of the consultation that focused on understanding and addressing user needs and how CoastAdapt could best provide support to effectively carry out adaptation planning and action. The first step was to identify, through an online survey and workshops, the knowledge gaps and barriers that could be addressed by CoastAdapt. The responses fed into the design and build, together with additional feedback from users on the layout and content. Following release of the beta version, further comments from users were collected and scrutinised to identify modifications that could increase relevance and utility. Finally, test cases were carried out to understand whether CoastAdapt is truly fit for purpose in addressing ‘real-world’ adaptation situations. The end result is a supportive framework for coastal adaptation that will require constant monitoring and updating to ensure it remains fit for purpose given Australia’s rapidly evolving adaptation landscape.

Equity in Global Health Research.

With the developing of industry, maintenance has become an important factor that influences survival and development of business. As an interdisciplinary activity, maintenance management needs technical support from computer decision support system when using that knowledge. There are numerous pieces of equipment in a power plant, but the maintenance requirements are different for different equipment. Making condition based maintenance in a power plant is a systemic and integrative maintenance management activity which needs a special maintenance decision support system. As a main developing direction of decision support system, intelligent decision support system has got a comprehensive and successful application in many domains. According to the characteristic of operation and maintenance in a power plant, an intelligent maintenance decision support system is designed in this paper where the system goal, function, framework and platform are particularly introduced.

This paper constructs an intelligent decision support system using text combination feature extraction, case similarity, XBoost sentencing prediction model, and other related technologies. The performance of the smart decision support system is tested for grabbing responses and monitoring response reliability. The XGBoost algorithm is used to construct the sentencing prediction model to achieve the intelligence of sentencing prediction. The effectiveness of the sentencing prediction model is examined by comparing the XGBoost model with different algorithms (Random Forest, CBDT, CNN). The practical application of intelligent decision support systems was summarized, highlighting the positive and negative effects. The results show that the overall responsiveness performance of the intelligent decision support system’s magisterial document capture and retrieval is reliable, and the number of captured and retrieved magisterial documents rises as the capture time increases. In XGBoost’s sentencing prediction, nine overlapping parts of the ten keywords were extracted for sentence and fine. In contrast, the keyword similarities are all higher than 0.5, and the difference between the predicted and real sentence values and fine is small. The intelligent decision support system has resulted in a gradual decrease in the number of court cases and an improvement in efficiency. The re-sentencing and retrial initiation rate decreased by over 20% from 2019 to 2023.

Simulation and optimization methods as decision support tools for operation of oil refinery hydrogen networks.

In this chapter we review the knowledge-based view on decision support and argue the emergence of a new type of intelligent decision support system — an intelligent gateway for supporting specific knowledge needs. The modern view on decision support and expert systems has shifted from considering these as purely analytical tools for assessing best-decision options to seeing them as a more comprehensive environment for supporting efficient information processing based on a good understanding of the problem context. Such intelligent decision support systems incorporate problem-domain knowledge to improve their information processing and provision capabilities. More recently, information portals have been proposed as tools for matching users’ information needs in order to enhance their decision-making ability. This chapter looks at portals as new types of intelligent decision support systems, which use problem-domain knowledge in order to improve efficiency in information provision. The main focus of the chapter is on suggesting mechanisms for implementing intelligent decision support capabilities in a healthcare portal, which seeks to deliver personalized information to support efficient decision making. BCKOnline, a healthcare portal built around breast cancer information, is described as an example of such implementation.

This Plenary paper critically analyses the nature and state of Intelligent Systems (IS) and Decision Support Systems (DSS) theories, research and applications. The issues and challenges of the Intelligent Systems and/or Smart Systems of the Future are briefly presented and discussed. The need for using Intelligent Decision Support Systems (IDSS) in developing Intelligent Cities of the Future is outlined. A brief historical review of DSS and how Artificial Intelligence (AI) has been embedded into the DSS and how this generated the interesting scientific area of Intelligent Decision Support Systems (IDSS) is provided. The challenge and absolute need for Making Decisions is briefly outlined. The challenge now is to make sense of DSS in Decision Making by planning it in understanding context and by searching new ways to utilize other advanced methodologies to the challenging issues in the future. The possibility of using Fuzzy Logic, Fuzzy Cognitive Maps (FCM) and Intelligent Systems (IS) in DSS is reviewed and analyzed. The new generic method for DSS been proposed before, and this leading to the Decision Making Support System (DMSS) is briefly presented. Open issues for future research of IDMSS and Intelligent Cities of the future are outlined and briefly discussed.

With the progress of transmission and power plant separation and competition before supply, generation companies are anxious to have an efficient bidding assistant decision system to gain more benefit. Intelligent bid decision support system for generation companies (GCBIDSS) is a computer system to assist generation companies to price the electricity. This paper introduces the conception of intelligent decision support system (IDSS), and puts emphasis on the systematical structural framework, work process, design principal, and fundamental function of GCBIDSS. The case study illustrates that the friendly window-based user interface of the system enables the user to take full advantage of the capabilities of the system in order to make effective real-time decision.

The model of support of processes of development of intelligent decision-making support systems (IDMSS) is presented. The model contains a description of methods and tools to support the processes of development of IDMSS, the structure of the repository of decision-making methods, architecture and methodology of development of a typical IDMSS. The methodology is based on such principles: use of existing solutions, scalability, accessibility, independence from the subject area, informativeness. Adherence to these principles is ensured by the use of ontological, microservice and framework approaches, as well as approaches to rapid prototyping and methodology of flexible software development. The main methodological provisions of using the model are based on elements of Web technologies and development of information and analytical resources. The means of support of IDMSS development processes are described in detail – ontology of the field of knowledge “Decision-making support”, information-analytical resource, repository of decision-making support methods (DMS), methods of IDMSS development. As a framework of IDMSS it is offered to use an information-analytical resource which is constructed on the basis of ontology of subject area and methods of the used technology. With the help of services connected to the resource, which implement the stored DMS methods, the functionality of the developed IDMSS is provided. The language of descriptive logic is used to describe the model of complex support. Architectural solutions for which the developer and user interface are deployed in a separate container are presented. A solution for storing content and ontologies of the subject area in the repository with the organization of access through services is proposed.

Decision Support Systems (DSS) are mainly computer based applications include essential component called Database to support rational Decision Making process by analyzing, determining and evaluating the available raw data, documentations, knowledge to reach rational alternative set of actions, identify and solve business problems, and present various economical business decisions. UAE has been determine more than ten years ago a clear strategy to reduce the dependency of their GDP on Oil products. The main aim of this paper is to analyze the UAE’s oil independence strategy and to propose a Decision Support Framework (DSF) generalizing their excellent perspective for the other oil producer countries to determine the most appropriate economical alternative solution as a substitute for a Gas Crisis. In this article, one of the famous DSS is used; Group Decision Support system is the most suitable tool for the investigated problem to build an effective Decision Support to help the oil producer countries for the sack of their GDP’s oil independency.The proposed DSF will help the users to achieve their main competitive advantage through effective acts in innovation. Its simulate the UAE strategy through the new technologies as well as modern techniques that used to create new things has never been made before and can be recognized as a unique product. This article introduced a DSF to support the oil producer countries to diversify their GDP resources and to reduce its oil dependency.