Heart disease diagnosis: an efficient decision support system based on fuzzy logic and genetic algorithm
by K. Rajeswari, V. Vaithiyanathan
International Journal of Decision Sciences, Risk and Management (IJDSRM), Vol. 3, No. 1/2, 2011

Abstract: Computerised clinical guidelines can provide benefits to health outcomes and costs; however, their effective implementation presents significant problems. One effective solution to achieve the optimal trade-off between data ambiguity and good decision-making would be to integrate data mining and artificial intelligence techniques. We devise an efficient clinical decision support system (CDSS) for heart disease diagnosis using data mining and AI techniques. The proposed algorithm makes use of the association pattern mining algorithm, apriori and genetic algorithm (GA) to formalise the treatment of vagueness in decision support architecture. The GA produces a set of high impact parameters and their respective optimal values essential for heart disease diagnosis. The fuzzy logic is employed as a decision-making tool in the proposed CDSS. Based on the fuzzy membership function, the system effectively diagnoses the clinical cases of heart disease. Experimental results demonstrate the effectiveness of the proposed CDSS in heart disease diagnosis.

Online publication date: Tue, 30-Dec-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Decision Sciences, Risk and Management (IJDSRM):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com