Tu SW, Eriksson H, Gennari JH, Shahar Y, Musen MA. Ontology-based configuration of problem-solving methods and generation of knowledge acquisition tools: the application of PROTEGE-II to protocol-based decision support. Artif Intell Med 1995;7:257 -- 90.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....has often been modelled as a planning protocol directed therapy task. This is the case with Oncocin [22] which was designed following the problem solving method known as skeletal plan refinement [10] and whose conceptual model in KADS [26] has been presented in [13] The T HELPER system [21] also implements a protocol for AIDS treatment using the PROTEGE II methodology [16] The skeletal plan refinement method consists of selecting a general plan of predefined treatment (called a skeletal plan ) These plans specify standard treatment protocols, and their modification in function ....

....practice it is becoming more and more frequent that this task be carried out by following a therapeutic protocol. These protocols specify standard treatment plans and their modifications as a function of the patient s state. The design of advisory systems of therapy based on protocol planning [21,22] has been carried out by applying the method known as episodic skeletal plan refinement. The application of this method requires the existence of detailed therapeutic plans and heuristic knowledge on the adaptation of the skeletal plan to a specific patient. Nevertheless, in many clinical domains, ....

[Article contains additional citation context not shown here]

Tu SW, Eriksson H, Gennari JH, Shahar Y, Musen MA. Ontology-based configuration of problem-solving methods and generation of knowledge acquisition tools: the application of PROTEGE-II to protocol-based decision support. Artif Intell Med 1995;7:257 -- 90.

....way, a shared and computable representation of the published literature would grow with the literature itself. There has been good progress in the creation of tools that allow entry of data in standard formats[34] and techniques are being developed to acquire information for KBs similar to ours [35]. The main challenge in designing the classes within the KB is deciding the proper granularity of representation. Clearly, a scientific article contains many details of potential interest, and it is not yet feasible to represent everything in our KB. We try to make sure that our representations ....

Tu SW; Eriksson H; Gennari JH; Shahar Y; Musen MA . Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: application of PROTEGE-II to protocol-based decision support. Artificial Intelligence in Medicine, 1995 Jun, 7(3):257-89.

....compatibility with the CYC L KR language through KIF. In this way the CYC outputs become components of the KSE library of resources. Over time, as sharing becomes widespread the CYC and KSE visions may lead to the same result. Research on a smaller scale is being conducted by Pirlein and Studer (1994) who have developed KARO (Knowledge Acquisition environment with Reusable Ontologies) Their definition of an ontology is broader than the one presented by the KSE definition. They refer to that definition as a representation ontology, one that provides structure but no guidance. They are more ....

....is a fundamental basis of the object oriented paradigm. A key idea behind each of the approaches is the need to break the resource into reusable components of various sizes, including abstract and coarsely grained components which decompose into increasingly finer grained components (Steels 1993, Tu et al. 1994). Chandrasekaran and Johnson (1993) offer an interesting notion of what abstraction is all about. They argue that knowledge needs to be normalised in order to be reused. When abstraction is 8 viewed as a way of normalising knowledge then abstraction seems a logical requirement of reuse. Clancey ....

Tu, S.W., Eriksson, H., Gennari, J.H., Shahar, Y. and Musen, M.A. (1994) Ontology-Based Configuration of Problem-Solving Mehtods and Generation of Knowledge-Acquisition Tools: Application of PROTEGE-II to Protocol-Based Decision Support Knowledge Systems Laboratory, Medical Computer Science, KSL-94-22, December 1994.

....obtained from a library of modular, reusable ontologies. Once we define ontologies for one or several domains, we may organize them to create a library of reusable ontologies (Heijst et al. 1995) Such libraries can be useful for building information systems and during knowledge acquisition (Tu et al. 1995). When the models get large, we need tools to help with their management. Analysis tools can help with model verification and validation. Verification checks if the model satisfies existing syntactic rules (e.g. checking cardinality constraints for entity relationship like models or checking ....

Tu, S. W., Eriksson, H., Gennari, J. H., Shahar, Y. & Musen, M. A. (1995). Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: Application of PROTEGE-II to protocol-based decision support. Artificial Intelligence in Medicine, 7, pp. 257-289.

.... has been used to diagnose the opportunistic non Hodgkin s lymphomas which often develop (Diamond et al. 1994) Knowledge based systems have been applied to HIV patient medical record systems (Musen et al. 1995; Safran et al. 1996) monitoring ongoing HIV patient protocols (Musen et al. 1996; Tu et al. 1995; Sonnenberg, Hagerty, Kulikowski 1994; Sobesky et al. 1994) and HIV patient assessment (Xu 1996; Ohno Machado et al. 1993) Less closely related are knowledge based systems that apply qualitative modeling and process simulation to HIV laboratory systems (Sieburg 1994; Ruggiero et al. 1994) To ....

Tu, S.; Eriksson, H.; Gennari, J.; Shahar, Y.; and Musen, M. 1995. Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools. AI in Medicine 7:257--289.

....paper has been elaborated in reponse to problems encountered when designing an ontology for SATIN [Kas97a] an expert system in neonatalogy. This ontology will be named OnS (for: the Ontology of SATIN) in the paper. OnS is an application ontology, as this term is understood by the PROTG group [Tu95] and the The copyright of this paper belongs to the papers authors. Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage. Proceedings of the IJCAI 99 workshop on Ontologies and Problem Solving ....

S.W. Tu, H. Eriksson, J.H. Gennari, Y. Shahar and M.A. Musen. Ontology-based configuration of problem-solving methods and generation of knowledge acquisition tools: the application of PROTEGE-II to protocol-based decision support. Artificial Intelligence in Medecine, 7:257-289.

.... markers) has been used to diagnose opportunistic non Hodgkin s lymphomas that may develop (Diamond et al. 1994) Knowledge based systems have been applied to HIV patient medical record systems (Musen et al. 1995, Safran et al. 1996) monitoring of HIV patient protocols (Musen et al. 1996, Tu et al. 1995, Sonnenberg et al. 1994, Sobesky et al. 1994) and HIV patient assessment (Xu, 1996, Ohno Machado et al. 1993) RAPIDLY MUTATING DRUG RESISTANT VIRUSES 305 Perception Experimental Data HIV Sequences From Patient Abstraction Extract Features, Objects Codons Named by Rules In Current HIV ....

S. Tu, H. Eriksson, J. Gennari, Y. Shahar, and M. Musen. Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools. AI in Medicine, 7:257--289, 1995.

No context found.

Tu SW, Eriksson H, Gennari JH, et al. Ontology -based configuration of problem-solving methods and generation of knowledge-acquisition tools: application of PROTG-II to protocolbased decision support. Artif. Intel. in Med. 7(1995) 257-289.

No context found.

Tu SW, Eriksson H, Gennari J, Shahar Y, Musen M.A. Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: Application of PROTG-II to protocol-based decision support. Artificial Intelligence in Medicine 1995; 7(3):257--289.

....2.3. The temporal abstraction knowledgeacquisition tool As part of our previous research, we have constructed a graphical knowledge acquisition tool for automated acquisition of temporal abstraction knowledge from domain experts [38] using the PROTG II framework. The PROTG II project [26, 39] develops a library of highly reusable, domain independent, problem solving methods. One advantage of the PROTG II approach is the production, given the relevant problem solvingmethod and domain ontologies, of automated knowledgeacquisition tools, tailored for the selected problem solving method ....

Tu, S. W., Eriksson, H., Gennari, J., Shahar, Y., & Musen, M. A. (1995). Ontology-based configuration of problemsolving methods and generation of knowledge-acquisition tools: Application of PROTG-II to protocol-based decision support. Artificial Intelligence in Medicine 7 (3), 257--289.

.... and a supporting suite of software tools, developed at the Section on Medical Informatics, Stanford University School of Medicine[5] When used in the domain of protocolbased care[6] PROTG II allows for significant cost savings by generating a protocol editing tool direct from disparate ontologies[7]. The word Ontology as used in PROTG II is defined as a hierarchical conceptualization of the classes of entities in a given domain, together with their attributes. We have produced a guideline editing tool to allow clinicians to author guidelines. We used PROTG II to represent the GPGM and ....

....needed with models specialized for each use and domain. Generic Protocol and Guideline Model The GPGM was inspired by three earlier projects involving reasoning about clinical decisions the Oxford System of Medicine, Bordeaux Oncology Support System (itself partly inspired by ONCOCIN) and LEMMA[7]. These projects emphasized the benefits of the declarative style of knowledge representation and the separation of domain and control knowledge. The DILEMMA consortium found the initial description of a guideline as a guided sequence of decisions insufficient. More accurately, guidelines and ....

[Article contains additional citation context not shown here]

Tu SW, Eriksson, H, Gennari J, Shahar Y, Musen MA. Ontology-based configuration of problemsolving methods and generation of knowledgeacquisition tools: Application of PROTEGE-II to protocol-based decision support. Artif Intel Med 1995;7:257-89.

No context found.

Tu SW, Eriksson H, Gennari JH, et al. Ontologybased configuration of problem-solving methods and generation of knowledge-acquisition tools: application of PROTG-II to protocol-based decision support. Artif. Intel. in Med. 7(1995) 257289.

No context found.

Tu SW, Eriksson H, Gennari J, Shahar Y, Musen MA. Ontology -based configuration of problem-solving methods and generation of knowledge-acquisition tools: application of prot6g6-II to protocol-based decision support. Artif Intell Med. 1995;7(3):257-89.

....or implicitly) in the context ontology. To facilitate KA and validation, we have created an automated graphic KA tool for acquisition of TA knowledge [27] The TA KA tool is generated automatically by tools from the PROTG project for automatic generation of KA tools for knowledge based systems [28]. The TA mechanisms (except for context formation) operate within the temporal span of context intervals and do not depend on the event and context ontologies. These mechanisms assume the existence of context intervals and of interpretation contexts as part of the input parameter propositions. ....

S.W. Tu, H. Eriksson, J.G. Gennari, Y. Shahar, and M.A. Musen, Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: Application of PROTG-II to protocol-based decision support, Artificial Intelligence in Medicine 7(3)(1995) 257289.

....of highways. 1. Introduction: Knowledge Reuse and Spatiotemporal Abstraction Knowledge based architectures present unique opportunities for software reuse. Several theoretical and practical frameworks for knowledge reuse have been proposed. One such framework is PROTG II [Musen et al. 1995; Tu et al. 1995; Eriksson et al. 1995] PROTG II uses a library of domain independent problem solving methods, which can be reused to solve different domain dependent tasks by defining explicit mappings between method ontologies (i.e. a theory of entities, their properties, and their relations) and domain ....

Tu, S.W., Eriksson, H., Gennari, J., Shahar, Y., and Musen, M.A. 1995. Ontology-based configuration of problemsolving methods and generation of knowledgeacquisition tools: Application of PROTG-II to protocol-based decision support. Artificial Intelligence in Medicine 7(3):257--289.

....are followed by comments. 13 2.4 ACQUISITION AND MAINTENANCE OF GUIDELINE PLANS Expert physicians need not have familiarity with the syntax of the Asbru language to author clinical guidelines. Graphical knowledge acquisition (KA) tools can be generated automatically by systems such as PROTG II [Tu et al. 1995]. The KA tools can internally use the Asbru representation or its equivalent, but that representation need not necessarily be known to the user. In addition to creation of an internal (e.g. object oriented) version of the plan, the KA tool should be able to generate a textbased Asbru version. The ....

Tu, S. W., Eriksson, H., Gennari, J. H., Shahar, Y., and Musen, M. A. (1995). OntologyBased Configuration of Problem-Solving Methods and Generation of Knowledge-Acquisition Tools: Application of PROTG-II to Protocol-Based Decision Support. Artificial Intelligence in Medicine, 7(3):257-289.

.... engineer [23] One solution we are currently exploring for automating the acquisition of TA knowledge is the automatic generation of a knowledge acquisition tool for the TA mechanisms given the domains ontology and the ontology of the KBTA method, using a framework similar to the PROTG II project [24, 26, 34, 9, 11]. Y. Shahar and M.A. Musen, ################################### 1996 8(3) 267298 24 6. RSUM and other clinical TA systems Several different approaches have been applied in philosophy, in general computer science, and in AI to tasks that are at least comparable to the TA task as we define it. A ....

.... process can use either a manual methodology driven by the knowledge roles defined in the KBTA inference structure, or can use automatically generated knowledge acquisition tools, tailored to the domain and to the task, such as the knowledge acquisition tools generated by the PROTGII system [34]. Whatever the knowledge acquisition methodology chosen, however, understanding the knowledge required for abstracting clinical data over time in any particular domain is a useful undertaking. A clear specification of that knowledge, and its representation in an ontology specific to the task of ....

S.W. Tu, H. Eriksson, J.H. Gennari, Y. Shahar, and M.A. Musen, Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: Application of PROTG-II to protocol-based decision support, Artificial Intelligence in Medicine. (in press).

....a common data format. 2. It clarified the conflation between classes instances and the knowledge data distinction (which was, until then, mostly a background assumption) 3. It enabled the definition of the MARBLE tool and an associated language for declarative specification of mappings ( Gennari, Tu, Rothenfluh and Musen, 1994). This work was later extended in (Park et al., 1997) 4. It enabled early experiments in knowledge base reuse across knowledge modeling frameworks. For example, the Ontolingua system (see (Gruber, 1991) and (Gruber, 1993) included a Protg translator. While this was mostly a curiosity, it ....

Tu, S.W., Eriksson, H., Gennari, J.H., Shahar, Y., and Musen, M.A. (1994). Ontology-Based Configuration of Problem-Solving Methods and Generation of Knowledge-Acquisition Tools: Application of Protg-II to Protocol-Based Decision Support.. Stanford SMI Technical Report 94-520.

....Protocol Based Care We will ground our discussion in an example: the use of the EON architecture to automate protocol based care. Although the Protg methodology (Musen et al. 1995; Eriksson et al. 1995) and the use of Protg to construct decision support systems based on the EON architecture (Tu et al. 1995; Musen et al. 1996) have been presented previously, it is helpful to review here how our group has used Protg to create a family of application systems that provide assistance with protocol based patient care. In the example that follows, we emphasize the role of the domain ontology both in ....

Tu, S.W., Eriksson, H., Gennari, J.H., Shahar, Y., and Musen, M.A. (1995). Ontology-based configuration of problemsolving methods and generation of knowledge-acquisition tools: Application of PROTG-II to protocol-based decision support. Artificial Intelligence in Medicine. 1995; 7:257--289.

....Tool We developed a graphical KA tool to automate the process of entry and maintenance of temporalabstraction knowledge by expert physicians in multiple clinical domains. We constructed the KA tool using software tools from the Protg project (Musen, 1992; Musen et al. 1995; Musen, 1998; Tu et al. 1995). Technically, the tool is semiautomated, in two senses: in its mode of generation and in its mode of use. First, it is a software tool that is generated automatically by the Protg system and provides multiple automated support services for KA; however, custom tailoring of the final interface is ....

....for example, machine learning techniques that learn only from data) interaction with a human domain expert (i.e. an expert physician) who enters the domain specific knowledge using the dialog implicit in the structure of the KA tool. 3. 2 The Protg System The Protg framework (Musen, 1998a; Tu et al. 1995) is a workbench for construction and use of ontologies and for creation of domain specific knowledge acquisition tools. The version (Protg Win) that we used runs in a Windows 95 or Windows NT environment. A major advantage of the Protg approach is the production, given the relevant ....

Tu, S. W., Eriksson, H., Gennari, J., Shahar, Y., and Musen, M. A. (1995). Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: Application of PROTG-II to protocol-based decision support, Artificial Intelligence in Medicine, 7(3):257-89.

....class and instance editing in the same tool. Thus, the division between class and instance editing creates di#culties in certain domains where it is important for experts to define many classes. Examples of such domains are medical domains with class hierarchies of symptoms, diseases, and drugs (Tu, Eriksson, Gennari, Shahar Musen, 1995), technical domains with component hierarchies (Rothenfluh, Gennari, Eriksson, Puerta, Tu Musen, 1996) and characterization oriented domains (Domingue Motta, 1999) Figure 2 summarizes the tool generation process in Protege II. The enhancements to Protege II presented here allow for ontology ....

....1995) is an ontology editor and knowledge management system that allows developers to create ontologies with inheritance, property, statement, relation, and facet hierarchies. CODE 4 has an advanced user interface that provides several views on the knowledge structures edited. KARO (Pirlein Studer, 1995) is an approach that provides semantic means for reusing ontologies. This approach emphasizes retrieval and adaptation of reusable ontologies, and the construction of new ontologies from such components. Rational Rose (Quantrani, 1998) is a commercial visual modeling environment that allows ....

[Article contains additional citation context not shown here]

Tu, S. W., Eriksson, H., Gennari, J. H., Shahar, Y. & Musen, M. A. (1995). Ontology-based configuration of problem-solving methods and generation of knowledgeacquisition tools: Application of PROT EG E-II to protocol-based decision support. Artificial Intelligence in Medicine, 7, 201--225.

....experts, such as expert physicians, need not have familiarity with the syntax of the Asbru language to author skeletal plans, such as clinical guidelines. Graphic knowledge acquisition (KA) tools can be generated automatically by systems such as PROTG II (Eriksson, et al. 1995; Musen, et al. 1995; Tu, et al. 1995). The KA tools can internally use the Asbru representation or its equivalent, but that representation need not necessarily be known to the user. In addition to creation of an internal (e.g. object oriented) version of the plan, the KA tool should be able to generate a text based Asbru version. ....

Tu, S. W., Eriksson, H., Gennari, J. H., Shahar, Y., and Musen, M. A. (1995). Ontology-Based Configuration of Problem-Solving Methods and Generation of Knowledge-Acquisition Tools: Application of PROTG-II to Protocol-Based Decision Support. Artificial Intelligence in Medicine, 7(3):257-289.

....advantages of explicit representation of temporalabstraction knowledge for acquiring, maintaining, and reusing that knowledge. A graphical tool for acquiring temporal abstraction knowledge from expert physicians was constructed [Stein et al. 1996] using the PROT G II framework s set of tools [Tu et al. 1995]. The R SUM system is currently integrated within the EON componentbased architecture for guidline based care [Musen et al. 1996] An example of using the R SUM system in a medical domain is an evaluation that we performed in the domain of monitoring patients who have insulin dependent ....

....might still need to be acquired from expert physicians. Currently, we are using a graphic knowledge acquisition tool that uses threedimensional tables to represent D functions [Stein et al. 1996] and that is generated automatically, given the KBTA ontology, by tools from the PROT G II project [Tu et al. 1995]. Thus, our future plans are to (1) construct a Bayesiansemantics framework for the interpolation operation, 2) attempt to learn local and global interpolation functions from large temporal databases (given some domain knowledge, such as the abstraction hierarchy and classification functions, ....

S.W. Tu, H. Eriksson, J. Gennari, Y. Shahar, and M.A. Musen. Ontology-based configuration of problem-solving methods and generation of knowledgeacquisition tools: Application of PROTÉGÉ-II to protocolbased decision support. Artificial Intelligence in Medicine, 7(3):257--289, 1995.

No context found.

Tu S, Eriksson H, Gennari J, Shahar Y, Musen M. Ontologybased configuration of problem-solving methods and generation of knowledge-acquisition tools: application of PROTI2GI2-II to protocol-based decision support. Artif Intell Med. 1995;7:257-89.

No context found.

Tu SW, Shortliffe EH, Gennari J, Shahar Y, Musen MA. Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: Application of Protege-II to protocol-based decision support. Technical Report KSL-94-22, Knowledge Systems Lab, Stanford, CA, 1994.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC