Department of Computer Science and Information Systems, Mount Royal University, 4825 Mount Royal Gate SW, Calgary, Canada T3E6K6.
Comput Methods Programs Biomed. 2011 Jul;103(1):10-27. doi: 10.1016/j.cmpb.2010.06.003. Epub 2010 Jul 15.
The task of medical diagnosis is a complex one, considering the level vagueness and uncertainty management, especially when the disease has multiple symptoms. A number of researchers have utilized the fuzzy-analytic hierarchy process (fuzzy-AHP) methodology in handling imprecise data in medical diagnosis and therapy. The fuzzy logic is able to handle vagueness and unstructuredness in decision making, while the AHP has the ability to carry out pairwise comparison of decision elements in order to determine their importance in the decision process. This study attempts to do a case comparison of the fuzzy and AHP methods in the development of medical diagnosis system, which involves basic symptoms elicitation and analysis. The results of the study indicate a non-statistically significant relative superiority of the fuzzy technology over the AHP technology. Data collected from 30 malaria patients were used to diagnose using AHP and fuzzy logic independent of one another. The results were compared and found to covary strongly. It was also discovered from the results of fuzzy logic diagnosis covary a little bit more strongly to the conventional diagnosis results than that of AHP.
医学诊断的任务非常复杂，需要考虑到水平的模糊性和不确定性管理，尤其是当疾病有多种症状时。许多研究人员已经在医学诊断和治疗中利用模糊层次分析法（fuzzy-AHP）来处理不精确的数据。模糊逻辑能够处理决策中的模糊性和非结构化，而层次分析法则能够进行决策元素的两两比较，以确定它们在决策过程中的重要性。本研究试图在医疗诊断系统的开发中进行模糊和 AHP 方法的案例比较，其中涉及基本症状的提取和分析。研究结果表明，模糊技术相对于 AHP 技术具有非统计上显著的相对优势。从 30 名疟疾患者那里收集的数据分别使用 AHP 和模糊逻辑进行独立诊断。比较结果发现，两者具有很强的相关性。此外，模糊逻辑诊断的结果与传统诊断结果的相关性比 AHP 更强。
