Computer aided fuzzy medical diagnosis.

Centre for Computational Intelligence, Department of Computer Science, De Montfort University, The Gateway, Leicester LE1 9BH, UK
Inf. Sci 01/2004; 162:81-104. DOI: 10.1016/j.ins.2004.03.003
Source: DBLP

ABSTRACT This paper describes a fuzzy approach to computer aided medical diagnosis in a clinical context. It introduces a formal view of diagnosis in clinical settings and shows the relevance and possible uses of fuzzy cognitive maps and fuzzy logic. A constraint satisfaction method is introduced which uses the temporal uncertainty in symptom durations that may occur with particular diseases. Together with fuzzy symptom descriptions, the method results in an estimate of the stage of a disease if the temporal constraints of the disease in relation to the occurrence of the symptoms are satisfied. The approach is evaluated through simulation experiments showing the effects of symptom ordering, temporal uncertainty and symptom strengths on the diagnosis efficiency. The method is effective and can be developed further using second order (Type 2) fuzzy logic to better represent uncertainty in the clinical context thus improving differential diagnosis accuracy.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This study is to propose a new approach for medical diagnosis using the dis-tance between interval-valued intuitionistic fuzzy sets. For this purpose, we developed an interview chart with interval fuzzy degrees based on the relation between symptoms and diseases (three types of headache), and utilized the interval-valued intuitionistic fuzzy weighted arithmetic average operator to aggregate fuzzy information from the symptoms. In addition, we proposed a measure based on distance between interval-valued intuition-istic fuzzy sets for medical diagnosis. The proposed method is illustrated by a numerical example.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In medical system, there may be many critical diseases, where experts do not have sufficient knowledgeto handle those problems. For these cases, experts may provide their opinion only about certain aspectsof the disease and remain silent for those unknown features. Feeling the need of prioritizing differentexperts based on their given information, this article uses a novel concept for assigning confident weightsto different experts which are mainly based on their provided information. Experts provide their opinionsabout various symptoms using intuitionistic fuzzy soft matrix (IFSM). In this article, we propose an algo-rithmic approach based on intuitionistic fuzzy soft set (IFSS) which explores a particular disease reflectingthe agreement of all experts. This approach is guided by the group decision making (GDM) model anduses cardinals of IFSS as novel concept. We have used choice matrix (CM) as an important parameterwhich is based on choice parameters of individual expert. This article has also validated the proposedapproach using distance measurements and consents of the majority of experts. The effectiveness of theproposed approach is demonstrated using a suitable case study.
    Applied Soft Computing 07/2014; · 2.68 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The parameter optimization of fuzzy classifiers using bio-inspired methods usually leads to the complex distribution of membership functions such that fuzzy classifiers can not provide a transparent linguistic interpretation. In this paper, we address the design of Mamdani-type fuzzy classifier from numerical data. A novel constrained parameter learning algorithm based on gradient projection method is presented to reserve the interpretability of fuzzy sets throughout the optimization process of parameter tuning. The proposed fuzzy classifier is validated for the well-known Wisconsin Breast Cancer problem. Satisfactory results show the effectiveness and feasibility of the proposed method.