A MEDICAL DIAGNOSTIC SUPPORT SYSTEM FOR THE MANAGEMENT OF HYPERTENSION (MEDDIAG)

X.Y. Djam¹, Y. H. Kimbi²

¹Department of Mathematics, Gombe State University, Gombe State, Nigeria

²State Specialist Hospital, Gombe, Gombe State, Nigeria

 E-mail: dxaveria@yahoo.com

ABSTRACT

Hypertension is one of the silent killer diseases and the need to optimize the management using fuzzy logic approach is a dual need. Hypertension directly or indirectly concerns us in one way or the other. As far as hypertension is concerned, one can be a patient, a patient’s relative or a wise counselor. A little more knowledge and understanding will make a wiser counselor. In this paper, a medical diagnostic support system for the management of hypertension (MEDDIAG) is presented. MEDDIAG diagnoses the possibility of the disease and its severity using fuzzy logic approach. Fuzzy logic technology provides a simple way to arrive at a definite conclusion from vague, ambiguous, imprecise or noisy data (as found in medical data) using linguistic variables that are not necessarily precise. In order to achieve this, a study of the knowledge base system for the management of hypertension was undertaken. MEDDIAG applied forward chaining method in making inferences and the Root Sum Square (RSS) of drawing inference was employed to infer the data from the rules developed. The defuzzification technique employed is the Centroid approach. MEDDIAG was implemented in the Fuzzy Logic Toolbox in MATLAB 7.10.0. Diagnostic data from 30 patients with confirmed diagnosis of hypertension were evaluated and the computed results were in the range of the predefine limits by the domain experts. Fuzzy diagnosis had 85% exact diagnosis. Based on the results obtained, fuzzy diagnosis resembles human decision making with its ability to work from approximate reasoning and ultimately find a precise solution.

Keywords: Medical diagnosis, Fuzzy Logic, Knowledge-base, Hypertension