Case-based Decision Support System Research Articles

Graph augmented triplet architecture for fine-grained patient similarity

Electronic Health Records (EHRs) provide rich information for the research of multiple healthcare applications that improve chance of survival in Intensive Care Units (ICU), especially the case-based decision support system, which helps physicians make effective clinical decisions in the rapidly changing environment of ICUs according to similar historical patient records. Thus, an efficient approach being able to measure clinically similarities among patients is a fundamental and critical module for the decision support system. In this paper, we propose a novel framework that derives informative EHR graphs from patient records to augment information transmission in Recurrent Neural Networks (RNNs) for fine-grained patient similarity learning, named Graph Augmented Triplet Architecture (GATA). Specifically, GATA firstly derives Dynamic Bayesian Networks (DBNs) from EHRs to reveal correlations among medical variables, then it constructs graph augmented RNNs where each unit aggregate information from variables that it conditionally dependent in DBNs. After that, the specially designed RNNs will act as the fundamental components of the Triplet architecture to measure similarities among patients. GATA has been compared to different baselines based on a real-world ICU dataset MIMIC III, and the experimental results illustrate the effectiveness of GATA in fine-grained patient similarity learning, providing a promising direction for the research on clinical decision support.

Implementing Guideline-Based, Experience-Based, and Case-Based Approaches to Enrich Decision Support for the Management of Breast Cancer Patients in the DESIREE Project.

DESIREE is a European-funded project to improve the management of primary breast cancer. We have developed three decision support systems (DSSs), a guideline-based, an experience-based, and a case-based DSSs, resp. GL-DSS, EXP-DSS, and CB-DSS, that operate simultaneously to offer an enriched multi-modal decision support to clinicians. A breast cancer knowledge model has been built to describe within a common ontology the data model and the termino-ontological knowledge used for representing breast cancer patient cases. It allows for rule-based and subsumption-based reasoning in the GL-DSS to provide best patient-centered reconciled care plans. It also allows for using semantic similarity in the retrieval algorithm implemented in the CB-DSS. Rainbow boxes are used to display patient cases similar to a given query patient. This innovative visualization technique translates the question of deciding the most appropriate treatment into a question of deciding the colour dominance among boxes.

A Use Case Analysis of Heterogeneous Semistructured Objects in Information Security Problems

This paper is devoted to solving the problem of developing a case-based decision support system for information security problems. The source data can be described as heterogeneous semistructured objects and formalized as property vectors. An approach to constructing a knowledge base for such problems using a two-level representation (the level of case-objects and the use case structure level) is given. The authors consider a use case modeling method for preparing a basic data set. Methods for assessing the similarity of heterogeneous semistructured objects and higher-level use cases are proposed. Results of experimental approbation of the described solutions and the architecture of the corresponding decision support system are presented.

Case-Based Decision Support System for Breast Cancer Management

Case-Based Decision Support System for Breast Cancer Management

Case-Based Decision Support System for Breast Cancer Management

Breast cancer is identified as the most common type of cancer in women worldwide with 1.6 million women around the world diagnosed every year. This prompts many active areas of research in identifying better ways to prevent, detect, and treat breast cancer. DESIREE is a European Union funded project, which aims at developing a web-based software ecosystem for the multidisciplinary management of primary breast cancer. The development of an intelligent clinical decision support system offering various modalities of decision support is one of the key objectives of the project. This paper explores case-based reasoning as a problem solving paradigm and discusses the use of an explicit domain knowledge ontology in the development of a knowledge-intensive case-based decision support system for breast cancer management.

Intelligent Case Based Decision Support System for Online Diagnosis of Automated Production System

Diagnosis of Automated Production System (APS) is a decision-making process designed to detect, locate and identify a particular failure caused by the control law. In the literature, there are three major types of reasoning for industrial diagnosis: the first is model-based, the second is rule-based and the third is case-based. The common and major limitation of the first and the second reasonings is that they do not have automated learning ability. This paper presents an interactive and effective Case Based Decision Support System for online Diagnosis (CB-DSSD) of an APS. It offers a synergy between the Case Based Reasoning (CBR) and the Decision Support System (DSS) in order to support and assist Human Operator of Supervision (HOS) in his/her decision process. Indeed, the experimental evaluation performed on an Interactive Training System for PLC (ITS PLC) that allows the control of a Programmable Logic Controller (PLC), simulating sensors or/and actuators failures and validating the control algorithm through a real time interactive experience, showed the efficiency of our approach.

The case-based decision support system in the field of IT-consulting

In the present paper, we propose an approach to facilitation of decision-making in the field of IT-consulting. The approach is based on knowledge representation in the form of cases containing past history about decision making. We also proposed an ontology to store the cases as instances of classes. Classification of cases in the ontology is executed by means of fuzzy inference. The method of classification is based on the original algorithm of transformation of cases (precedents) sample to the set of linguistic rules allowing one to make relevant decisions. Research of the method has shown good accuracy of the decisions classification according to test data.

A case-based decision support system for product development

Companies that are developing new products are now facing increasing global competition. Continual success in the marketplace depends upon how efficiently and effectively a company is able to respond to customers' ever changing needs. In this article, a Case-based Product-development Enhancement System (CPES) is designed to help manufacturing industry to support product development by retrieving and analysing useful knowledge and solutions in a timely and cost-effective manner. CPES provides important support for, and information on product development, and enhances effectiveness in product development strategies by integrating techniques such as data warehouse, Online Analytical Processing and Case-Based Reasoning. When applying CPES in a light emitting diode manufacturer, it was possible to maximise resource utilisation, increase work efficiency and greatly reduce cost in product development.

Case-based Sentencing Using a Tree of Legal Concepts

The Judge's Apprentice is a case-based decision support system implemented and intended for use in Israeli criminal law to aid sentencing in cases of either robbery or rape. The system uses a sentencing tree, which is a hierarchical classification of 371 legal concepts relevant to criminal sentencing. Each leaf in this tree represents an index, which can be input for any case. The indexes are important for determining index similarity in the retrieval process and for computation of the proposed sentence. After retrieval of suitable cases and selection of the best case, we use a case-based quantitative evaluation as a formula for computing a verdict for the case at hand.

Case-based decision support system: Architecture for simulating military command and control

For a military commander, a system that can offer decision support in the process of command and control, a tool that can provide the space in which to exercise his command and control ability have always been ultimate goals. This is not only because of the complexity of the problem domain but also because of the difficulty in obtaining help from past knowledge and extend past knowledge for solving new problem. This paper intends to present an architecture which incorporates case-based reasoning (CBR) and decision support system (DSS) as a tool for military officers to simulate and to train the military Standard Operation Procedure (SOP) in the decision-making process of command and control. The experiment and evaluation of the case-based decision support system (CBDSS) are also presented.

Development of a case-based decision support system for process modeling in BPR

This paper presents a knowledge-based methodology for business process reengineering that uses a case-based reasoning paradigm to provide decision support to its users in the modeling of a current problem and a redesign of critical business processes. As a process modeling tool for representing the business process, the event process chain (EPC) modeling method is used in this paper. We developed a CAPMOSS (CAse-based Process MOdeling Supporting System) to support our proposed methodology. To reengineer a new business process problem, CAPMOSS retrieves from its case base the case that is most similar to the current problem. CAPMOSS uses a retrieved case to guide the structuring of AS-IS models and TO-BE models of a target business process. Using the transformational knowledge of a retrieved case, CAPMOSS helps the user to transform an AS-IS model into a TO-BE model for the target process with ease and the purchasing process in a government R&D institute is explained as an application of this approach. Copyright © 2000 John Wiley & Sons, Ltd.

A case-based reasoning approach towards learning from experience connecting design and shop floor

Many problems in manufacturing cannot be completely covered by theoretical models but can only be solved with the help of experience. This paper presents a case-based reasoning approach towards systems that learn from experience. A case-based decision support system for design aids the designing engineer to choose working principles for functions of a product based on prior experiences with them. A diagnostic system supports fault detection on the shop floor. The two systems work together, forming quality control loops breaking from taylorism. A prototypical implementation to evaluate the concept was built up for the domain of injection mold design and the injection molding process.

Case-based decision support system with artificial neural network

Abstract The framework of the case-based decision support system (CBDSS) is introduced to allow people to resort to the valuable cases in similar decision environments with computer-based decision support systems. A CBDSS shell is developed which consists mainly of a problem analyser, a case base, a knowledgebase, a learning engine and an inference engine. The artificial neural network (ANN) is employed to draw knowlege from verified cases. A prototype of a CBDSS generated from the shell for failure analysis of metal parts is established and the experimental results presented.

Case-Based Reasoning and Imaging Procedure Selection

Case-based reasoning, an artificial intelligence technique for learning and reasoning from experience, has shown great potential for use in decision support systems. The authors developed and tested a prototype case-based decision support system to explore the applicability of this technique to the selection of diagnostic imaging procedures. A case-based system, ProtoISIS, was developed based on the Protos learning apprentice. ProtoISIS learned the domain of ultrasonography and body computed tomography by reviewing 200 consecutive cases of actual requests for imaging procedures. ProtoISIS was tested by using it to classify four sets of 25 cases of actual imaging procedure requests. ProtoISIS correctly classified 72% of the imaging-procedure requests. Its performance improved as it gained experience: in the last two test series, it correctly classified 84% of the cases presented. Case-based reasoning can be applied successfully to the selection of diagnostic imaging procedures and holds potential for use in clinical decision support aids. Further work is necessary to realize a clinically useful system.