Expert systems in histopathology. II. Knowledge representation and rule-based systems

Two aspects of expert systems for use in diagnostic histopathology and cytopathology are examined: knowledge representation and the structure and operation of rule-based systems. Knowledge may be represented, e.g., in semantic networks, frames, multiple contexts and model-based structures; the choice of structure should be matched to the type of information to create an efficient and logically adequate expert system. In a rule-based system, knowledge is represented as "rules," often in the form of "IF (condition)-THEN (conclusion)" rules. The anatomy of such rules and their operation is explored via the use of examples. Uncertainty in rules is briefly addressed, and their processing by the symbolic reasoning of the "inference engine" of the expert system is described, including both "forward-chaining" ("data-driven") operations and "backward-chaining" ("goal-driven") operations.     

Machine learning in quantitative histopathology

The role of expert systems functioning as process controllers in learning image understanding systems is discussed. Numeric learning systems already have found a number of applications in cytologic and histopathologic diagnosis. Depending on the required capabilities, systems of increasing complexity are needed. Expert systems to guide scene segmentation in histopathologic imagery require model-based reasoning. Diagnostic image interpretation with learning capability demands a full model of the human expert's competence, including a considerable variety of knowledge representation schemes and inference strategies, coordinated by a meta-process controller.     

An integrated rule- and case-based approach to AIDS initial assessment

The traditional approach to the development of knowledge-based systems (KBS) has been rule-based, where heuristic knowledge is encoded in a set of production rules. A rule-based reasoning (RBR) system needs a well constructed domain theory as its reasoning basis, and it does not make substantial use of the knowledge embedded in previous cases. An RBR system performs relatively well in a knowledge-rich application environment. Although its capability may be limited when previous experiences are not a good representation of the whole population, a case-based reasoning (CBR) system is capable of using past experiences as problem solving tools, therefore, it is appropriate for an experience-rich domain. In recent years, both RBR and CBR have emerged as important and complementary reasoning methodologies in artificial intelligence. For problem solving in AIDS intervention and prevention, it is useful to integrate RBR and CBR. In this paper, a hybrid KBS which integrates a deductive RBR system and an inductive CRB system is proposed to assess AIDS-risky behaviors.     

Development and use of a rule-based pathology expert consultation system

Since histologic sections of pathologically changed tissues (e.g., tumors and inflammations) are highly complex structures, their subjective diagnostic or prognostic interpretation may result in a lack of interobserver and intraobserver agreement. Rule-based expert systems have the advantages that they require precise representation of the problem and can be used quickly and efficiently, even if the user is not acquainted with the special field concerned. Because of these and other advantages, a rule-based "Pathology Expert Consultation System" (PECS) is under development for the assessment of different premalignancies, malignancies and noncancerous conditions. In addition to supporting diagnosis making, the expert system can infer stage, type and grade, can check for inconsistencies in the answers and can predict the prognosis of an individual patient. PECS permits total integration of information contained in database, worksheet and text files with the rules and other control structures inherent in the rule base. The consultation can be interrupted to display a graph; when the user dismisses the graph, the consultation will resume where it left off or will move to another part of the system (if desired). If the user asks why a question is raised, the system will answer with a textual, graphic or combined explanation. The construction and use of the PECS expert system is discussed. Its initial applications to tumors of the lung, breast and endometrium have shown it to have both educational and clinical significance.     

Fuzzy rule-based Fine–Kinney risk assessment approach for rail transportation systems

Rail transportation is one of the most crucial public transportation types for big and crowded cities. In rail transportation systems, stakeholders face serious issues involved in workshops, stations, lines and their environments, and general office buildings. In order to reach an increased awareness and better occupational health and safety (OHS) management, a new risk assessment approach is proposed in this study. This approach includes a combination of Fine–Kinney method and a fuzzy rule-based expert system. It captures nonlinear causal relationships between Fine–Kinney parameters. Since there is a high level of vagueness involved in the OHS risk assessment data, the rule-based expert system is developed for probability (P), exposure (E), and consequence (C) for evaluating risk score. A case study is carried out in a rail transportation system in Istanbul/Turkey, and a comparison with the classical Fine–Kinney method is discussed. Results of the case study reveal risk clusters and corresponding control measures that should be taken into consideration. The study methodologically contributes to risk assessment in the knowledge, while case study in a real rail transportation system offers an insight into public transport industry in safety improvement.     

Medical diagnosis: Are expert systems needed?

An evaluation of the pitfalls of computer-aided diagnosis during the last ten yearns seems to show that increased emphasis on real clinical problems as well as increased use of medical knowledge are required. Since such an approach could fit into the ‘expert system’ framework, one should expect new developments in that research field to occur soon. However, expert systems can also be designed along the same concepts as previous models of diagnostic reasoning presumably with the same shortcomings.     

Knowledge-based simulation of DNA metabolism: prediction of enzyme action

We have developed a knowledge-based simulation of DNA metabolismthat accurately predicts the actions of enzymes on DNA undera large number of environmental conditions. Previous simulationsof enzyme systems rely predominantly on mathematical models.We use a frame-based representation to model enzymes, substratesand conditions. Interactions between these objects are expressedusing production rules and an underlying truth maintenance system.The system performs rapid inference and can explain its reasoning.A graphical interface provides access to all elements of thesimulation, including object representations and explanationgraphs. Predicting enzyme action is the first step in the developmentof a large knowledge base to envision the metabolic pathwaysof DNA replication and repair. Received on February 1, 1990; accepted on October 2, 1990     

Chapter 1: Biomedical Knowledge Integration

The modern biomedical research and healthcare delivery domains have seen an unparalleled increase in the rate of innovation and novel technologies over the past several decades. Catalyzed by paradigm-shifting public and private programs focusing upon the formation and delivery of genomic and personalized medicine, the need for high-throughput and integrative approaches to the collection, management, and analysis of heterogeneous data sets has become imperative. This need is particularly pressing in the translational bioinformatics domain, where many fundamental research questions require the integration of large scale, multi-dimensional clinical phenotype and bio-molecular data sets. Modern biomedical informatics theory and practice has demonstrated the distinct benefits associated with the use of knowledge-based systems in such contexts. A knowledge-based system can be defined as an intelligent agent that employs a computationally tractable knowledge base or repository in order to reason upon data in a targeted domain and reproduce expert performance relative to such reasoning operations. The ultimate goal of the design and use of such agents is to increase the reproducibility, scalability, and accessibility of complex reasoning tasks. Examples of the application of knowledge-based systems in biomedicine span a broad spectrum, from the execution of clinical decision support, to epidemiologic surveillance of public data sets for the purposes of detecting emerging infectious diseases, to the discovery of novel hypotheses in large-scale research data sets. In this chapter, we will review the basic theoretical frameworks that define core knowledge types and reasoning operations with particular emphasis on the applicability of such conceptual models within the biomedical domain, and then go on to introduce a number of prototypical data integration requirements and patterns relevant to the conduct of translational bioinformatics that can be addressed via the design and use of knowledge-based systems.

What to Learn in This Chapter

• Understand basic knowledge types and structures that can be applied to biomedical and translational science;
• Gain familiarity with the knowledge engineering cycle, tools and methods that may be used throughout that cycle, and the resulting classes of knowledge products generated via such processes;
• An understanding of the basic methods and techniques that can be used to employ knowledge products in order to integrate and reason upon heterogeneous and multi-dimensional data sets; and
• Become conversant in the open research questions/areas related to the ability to develop and apply knowledge collections in the translational bioinformatics domain.

This article is part of the “Translational Bioinformatics” collection for PLOS Computational Biology.

     

Indicators of environmentally sound land use in the humid tropics: The potential roles of expert opinion,knowledge engineering and knowledge discovery

Despite abundant literature on indicators for sustainable resource management, practical tools to help local users to apply its general concepts at a local to regional level are scarce. This means that decisions over land evaluation and land use at a local level are often not based on the formal application of indicators or decision support systems for environmentally sound management but instead on the opinion of local expertise, for instance forest managers, cattle breeders, farmers and/or academics. This is particularly seen to be the case in the tropics where access to modern communication and information technologies is restricted.As the opinions of experts are often based on and influenced by personal experience, intuition, heuristics and bias, their evaluations and decision are often unclear to the non-expert working at a local level. In order to make their reasoning more comprehensible to the non-expert, the ecological condition of 176 plots in the tropical Southeast of Mexico were evaluated by experts on soil fertility, forest management, cattle breeding and agriculture. With the assistance of a knowledge engineer (one who converts expert knowledge and reasoning into a model), these expert opinions and reasoning were then translated into a formal computer model.As an alternative approach we applied a knowledge discovery technique, namely the induction of regression trees and automatically developed models using the expert evaluations as training data. Where knowledge engineering was tedious and time consuming, regression models could be rapidly generated. Moreover, the correspondence between regression trees and expert opinions was considerably higher than the correspondence between expert opinion and their own models. The regression trees used less explicative variables than the models generated by the experts. The minimisation of sampling effort due to variable space reduction means that the application of regression tree induction has a high potential for a rapid development of indicators for narrowly defined ecological assessments, needed for decision making on a local or regional scale.     

A grounded theory of abstraction in artificial intelligence

In artificial intelligence, abstraction is commonly used to account for the use of various levels of details in a given representation language or the ability to change from one level to another while preserving useful properties. Abstraction has been mainly studied in problem solving, theorem proving, knowledge representation (in particular for spatial and temporal reasoning) and machine learning. In such contexts, abstraction is defined as a mapping between formalisms that reduces the computational complexity of the task at stake. By analysing the notion of abstraction from an information quantity point of view, we pinpoint the differences and the complementary role of reformulation and abstraction in any representation change. We contribute to extending the existing semantic theories of abstraction to be grounded on perception, where the notion of information quantity is easier to characterize formally. In the author's view, abstraction is best represented using abstraction operators, as they provide semantics for classifying different abstractions and support the automation of representation changes. The usefulness of a grounded theory of abstraction in the cartography domain is illustrated. Finally, the importance of explicitly representing abstraction for designing more autonomous and adaptive systems is discussed.     

Expert System for Modeling and Simulating the Action of Electric and Electromagnetic Fields on Biological Membranes

The biological effects and applications in the developing technology involving electric and electromagnetic fields are as promising as they are diverse. Their effects, leading to remission in certain patients, can be obtained through electroporation, electrochemotherapy, electrotherapy, electroimmunotherapy, and gene electrotherapy. The main therapeutic uses of electromagnetic fields (EMF) are the introduction of chemical or organic substances into opportunely opened cells (electro-chimiotherapy) and the stimulation of specific elements of the immune system (electro-immunotherapy). Their benefits can be modeled by the use of expert systems, constructed to mimic human reasoning. As well as testing new therapies, such systems can analyze and synthesize existing data, and provide a new pedagogical device, and can be implemented on the Internet network. These techniques can be performed conjointly with other therapies like X-ray therapy, neutrotherapy and, in certain conditions, will optimize their effects. Some mathematical models, representing the electromagnetic field's action on cellular membranes, have been elaborated by means of the SADT method (a structured hierarchy modular method) and implanted into the expert system SEI4. This expert system simulates the immune system's behavior when facing electromagnetic fields, in the face of immunodeficient illness such as some cancers or AIDS.     

基于二叉分类推理的昆虫分类辅助鉴定多媒体专家系统通用平台TaxoKeys的设计与开发

本文详细介绍了基于二叉式分类推理的昆虫分类辅助鉴定多媒体专家系统通用平台TaxoKeys的设计与开发,及其所具备的主要特点。该研究根据昆虫分类学的特点,将昆虫分类的两项式检索表用数据库表示成系统知识库,利用计算机数据结构中二叉树结构的分枝结点搜索技术来实现其推理过程,进行昆虫分类的辅助鉴定,为昆虫分类专家提供一个通用专家系统平台。该系统具有可扩充性好、设计简单、操作方便等特点,同时也适用于一般性生物分类鉴定。另外,本文还就本系统功能的进一步扩展与应用研究等进行了探讨。     

The Balance-Scale Task Revisited: A Comparison of Statistical Models for Rule-Based and Information-Integration Theories of Proportional Reasoning

We propose and test three statistical models for the analysis of children’s responses to the balance scale task, a seminal task to study proportional reasoning. We use a latent class modelling approach to formulate a rule-based latent class model (RB LCM) following from a rule-based perspective on proportional reasoning and a new statistical model, the Weighted Sum Model, following from an information-integration approach. Moreover, a hybrid LCM using item covariates is proposed, combining aspects of both a rule-based and information-integration perspective. These models are applied to two different datasets, a standard paper-and-pencil test dataset (N = 779), and a dataset collected within an online learning environment that included direct feedback, time-pressure, and a reward system (N = 808). For the paper-and-pencil dataset the RB LCM resulted in the best fit, whereas for the online dataset the hybrid LCM provided the best fit. The standard paper-and-pencil dataset yielded more evidence for distinct solution rules than the online data set in which quantitative item characteristics are more prominent in determining responses. These results shed new light on the discussion on sequential rule-based and information-integration perspectives of cognitive development.     

Detection of the inferred interaction network in hepatocellular carcinoma from EHCO (Encyclopedia of Hepatocellular Carcinoma genes Online)

Background

An adequate and expressive ontological representation of biological organisms and their parts requires formal reasoning mechanisms for their relations of physical aggregation and containment.

Results

We demonstrate that the proposed formalism allows to deal consistently with "role propagation along non-taxonomic hierarchies", a problem which had repeatedly been identified as an intricate reasoning problem in biomedical ontologies.

Conclusion

The proposed approach seems to be suitable for the redesign of compositional hierarchies in (bio)medical terminology systems which are embedded into the framework of the OBO (Open Biological Ontologies) Relation Ontology and are using knowledge representation languages developed by the Semantic Web community.     

Expertise in expert systems: knowledge acquisition for biological expert systems

In this paper it is argued that an expert system requires morethan factual knowledge before it can display expertise in agiven domain. The additional knowledge consists of the heuristicsor ‘rules of thumb’ used by an expert to manipulateand interpret the factual knowledge. The knowledge acquisitionphase of an expert system project involves determining the factualknowledge (which may be obtained from published sources) andthe heuristics used by an expert to manipulate that knowledge-theseheuristics can only be obtained from an expert. In reviewingexisting biological expert systems it is apparent that manycontain only the factual knowledge relating to the domain, andlack the heuristics that enable such systems to show expertise.This paper reviews a number of knowledge acquisition techniqueswhich could be used for acquiring heuristic knowledge and discusseswhen their use is appropriate. The knowledge acquisition techniquesdiscussed are those suitable for the development of small-scaleexpert systems as these are most likely to be of interest tobiologists. The techniques include the use of questionnaires,interview techniques and protocol analysis; particular emphasisis placed on a mod cation to the ‘twenty questions’interview technique which was developed specifically to elicittaxonomic knowledge relating to water mite identification.