Knowledge acquisition in the fuzzy knowledge representation framework of a medical consultation system

Boegl, Karl; Adlassnig, Klaus-Peter; Hayashi, Yuzo; Rothenfluh, Thomas E.; Leitich, Harald

doi:10.1016/s0933-3657(02)00073-8

Cited by 82 publications

(36 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…152,153 Suitability of the computer systems using fuzzy methods and computerized monitoring and medical decision making systems have been reported. [154][155][156][157][158] Fuzzy frameworks are also developed for the medical imaging, interface program designing and knowledge mining. [159][160][161] The novel object oriented frameworks to construct fuzzy expert systems are proposed.…”

Section: Fuzzy Expert System Shells and Frameworkmentioning

confidence: 99%

Fuzzy Expert Systems (FES) for Medical Diagnosis

Sikchi¹,

Sikchi²,

Ali³

2013

IJCA

View full text Add to dashboard Cite

Fuzzy logic has proved to be the remarkable tool for building intelligent decision making systems based on the expert's knowledge and observations. This paper reviews the trend in development of FES and application potential over past two and half decades in the medical field, based on the references of 173 articles from 124 journals, several proceedings and web media. In order to investigate the significance of FES for medical diagnosis, the articles are classified into five distinct categories: Reviews and Surveys on Fuzzy Expert Systems in Medical Diagnosis, Applications of Fuzzy Expert Systems in Medical Diagnosis, Methodologies and Modelling of Fuzzy Expert Systems, Neuro-Fuzzy Approaches, Fuzzy Expert System Shells and Frameworks. The development of disease specific applications using FES is observed to be the area of most significant interest of the researchers. The earlier contributions are reviewed, classified, analyzed and suggested the future scope.

show abstract

Section: Fuzzy Expert System Shells and Frameworkmentioning

confidence: 99%

Fuzzy Expert Systems (FES) for Medical Diagnosis

Sikchi¹,

Sikchi²,

Ali³

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…Domain concepts are constrained early on and are too inflexible for practitioner's needs. The practice of constraining knowledge at an early acquisition stage is inherent in object-oriented techniques (Boegl, Adlassnig et al 2004) and leads to impoverished concept descriptions, unrecorded knowledge (Gahegan, Pike 2006) and creeping system obsolescence (Beale 2002). Knowledge sharing can be maximised across an interdisciplinary super-domain (such as ESS) by empowering domain specialists with the ability to model domain concepts in a computable way themselves, and by allowing for the evolution of the domain concepts within the model.…”

Section: Introductionmentioning

confidence: 99%

Towards a Digital Earth: using archetypes to enable knowledge interoperability within geo-observational sensor systems design

Stacey¹,

Berry²

2018

Earth Sci Inform

View full text Add to dashboard Cite

Earth System Science (ESS) observational data are often inadequately semantically enriched by geoobservational information systems in order to capture the true meaning of the associated data sets. Data models underpinning these information systems are often too rigid in their data representation to allow for the ever-changing and evolving nature of ESS domain concepts. This impoverished approach to observational data representation reduces the ability of multi-disciplinary practitioners to share information in a computable way.Object oriented techniques typically employed to model data in a complex domain (with evolving domain concepts) can unnecessarily exclude domain specialists from the design process, invariably leading to a mismatch between the needs of the domain specialists, and how the concepts are modelled. In many cases, an over simplification of the domain concept is captured by the computer scientist. This paper proposes that two-level modelling methodologies developed by Health Informaticians to tackle similar problems of specific domain use-case knowledge modelling can be re-used within ESS Informatics. A proposed methodology to re-use two-level modelling within geo-observational sensor systems is described. We show how the Open Geospatial Consortium's (OGC) Observations & Measurements (O&M) standard can act as a pragmatic solution for a stable reference-model (necessary for two-level modelling), and upon which more volatile domain specific concepts can be defined and managed using archetypes. A use-case is presented, followed by a worked example showing the implementation methodology and considerations leading to an O&M based, two-level modelling design approach, to realise semantically rich and interoperable Earth System Science based geo-observational sensor systems.

show abstract

“…The continued expansion of the HIV pandemic makes it unlikely that the growth in medical personnel will be able to keep pace with the need for expertise in antiretroviral therapy, particularly in the poorer nations. Furthermore, HIV/AIDS treatment is, unfortunately, among one of the most complex treatments for any disease, with treatment failures resulting in diminished future treatment options for both treated patients and those infected with treatment-resistant HIV virus strains [3], [11]. Although the U.S. Department of Human Health and Services HIV/AIDS treatment guidelines cover the first-round combination antiretroviral therapy and describe a conceptual approach to the more complex second (or subsequent) rounds, they do not provide individualized treatment advice and must be frequently updated as treatment options evolve.…”

Section: Introductionmentioning

confidence: 99%

“…We have recently combined the merits of fuzzy systems technology [1], [3], [12], [24], [27], [32], [41], [42], [46], [50] with the advantages of conventional discrete event system (DES) technology [5] and have established a theoretical framework for a comprehensive theory of fuzzy DES (FDES) [19], [20]. We have generalized the conventional (crisp) finite automaton model to fuzzy finite automaton model.…”

Section: Introductionmentioning

confidence: 99%

A Self-Learning Fuzzy Discrete Event System for HIV/AIDS Treatment Regimen Selection

Ying

Feng

MacArthur

et al. 2007

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

Abstract-The U.S. Department of Health and Human ServicesHuman Immunodeficiency Virus (HIV)/Acquired Immune Deficiency Syndrome (AIDS) treatment guidelines are modified several times per year to reflect the rapid evolution of the field (e.g., emergence of new antiretroviral drugs). As such, a treatmentdecision support system that is capable of self-learning is highly desirable. Based on the fuzzy discrete event system (FDES) theory that we recently created, we have developed a self-learning HIV/AIDS regimen selection system for the initial round of combination antiretroviral therapy, one of the most complex therapies in medicine. The system consisted of a treatment objectives classifier, fuzzy finite state machine models for treatment regimens, and a genetic-algorithm-based optimizer. Supervised learning was achieved through automatically adjusting the parameters of the models by the optimizer. We focused on the four historically popular regimens with 32 associated treatment objectives involving the four most important clinical variables (potency, adherence, adverse effects, and future drug options). The learning targets for the objectives were produced by two expert AIDS physicians on the project, and their averaged overall agreement rate was 70.6%. The system's learning ability and new regimen suitability prediction capability were tested under various conditions of clinical importance. The prediction accuracy was found between 84.4% and 100%. Finally, we retrospectively evaluated the system using 23 patients treated by 11 experienced nonexpert faculty physicians and 12 patients treated by the two experts at our AIDS Clinical Center in 2001. The overall exact agreement between the 13 physicians' selections and the system's choices was 82.9% with the agreement for the two experts being both 100%. For the seven mismatched cases, the system actually chose more appropriate regimens in four cases and equivalent regimens in another two cases. It made a mistake in one case. These (preliminary) results show that 1) the System outperformed the nonexpert physicians and 2) it performed as well as the expert physicians did. This learning and prediction approach, as well as our original FDESs theory, is general purpose and can be applied to other medical or nonmedical problems.Index Terms-Artificial intelligence, discrete event systems, fuzzy discrete event systems, fuzzy logic, HIV/AIDS treatment.

show abstract

Knowledge acquisition in the fuzzy knowledge representation framework of a medical consultation system

Cited by 82 publications

References 19 publications

Fuzzy Expert Systems (FES) for Medical Diagnosis

Fuzzy Expert Systems (FES) for Medical Diagnosis

Towards a Digital Earth: using archetypes to enable knowledge interoperability within geo-observational sensor systems design

A Self-Learning Fuzzy Discrete Event System for HIV/AIDS Treatment Regimen Selection

Contact Info

Product

Resources

About