| Formalization of treatment guidelines using Fuzzy Cognitive Maps and semantic web tools. | |
| | |
MedLine Citation:
|
PMID: 21911082 Owner: NLM Status: Publisher |
Abstract/OtherAbstract:
|
Therapy decision making and support in medicine deals with uncertainty and needs to take into account the patient's clinical parameters, the context of illness and the medical knowledge of the physician and guidelines to recommend a treatment therapy. This research study is focused on the formalization of medical knowledge using a cognitive process, called Fuzzy Cognitive Maps (FCMs) and semantic web approach. The FCM technique is capable of dealing with situations including uncertain descriptions using similar procedure such as human reasoning does. Thus, it was selected for the case of modeling and knowledge integration of clinical practice guidelines. The semantic web tools were established to implement the FCM approach. The knowledge base was constructed from the clinical guidelines as the form of if-then fuzzy rules. These fuzzy rules were transferred to FCM modeling technique and, through the semantic web tools, the whole formalization was accomplished. The problem of urinary tract infection (UTI) in adult community was examined for the proposed approach. Forty-seven clinical concepts and eight therapy concepts were identified for the antibiotic treatment therapy problem of UTIs. A preliminary pilot-evaluation study with 55 patient cases showed interesting findings; 91% of the antibiotic treatments proposed by the implemented approach were in fully agreement with the guidelines and physicians' opinions. The results have shown that the suggested approach formalizes medical knowledge efficiently and gives a front-end decision on antibiotics' suggestion for cystitis. Concluding, modeling medical knowledge/therapeutic guidelines using cognitive methods and web semantic tools is both reliable and useful. |
| | |
Authors:
|
Elpiniki I Papageorgiou; Jos De Roo; Csaba Huszka; Dirk Colaert |
Publication Detail:
|
Type: JOURNAL ARTICLE Date: 2011-9-1 |
Journal Detail:
|
Title: Journal of biomedical informatics Volume: - ISSN: 1532-0480 ISO Abbreviation: - Publication Date: 2011 Sep |
Date Detail:
|
Created Date: 2011-9-13 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 100970413 Medline TA: J Biomed Inform Country: - |
Other Details:
|
Languages: ENG Pagination: - Citation Subset: - |
Copyright Information:
|
Copyright © 2011. Published by Elsevier Inc. |
Affiliation:
|
Department of Informatics & Computer Technology, Technological Educational Institute of Lamia, 3rd Km Old National Road Lamia-Athens, 35100 Lamia, Greece. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Effect of Cu-nano particles versus Cu-salt in Enchytraeus albidus (Oligochaeta): Differential gene e...
Next Document: CNI induced Th17/Treg imbalance and susceptibility to renal dysfunction in renal transplantation.