Hypertension diagnosis: A comparative study using fuzzy expert system and neuro fuzzy system

Hypertension is called the silent killer because it has no symptoms and can cause serious trouble if left untreated for a long time. It has a major role for stroke, heart attacks, heart failure, aneurysms of the arteries, peripheral arterial diseases, chronic kidney disease etc. An intelligent and accurate diagnostic system is mandatory for better diagnosis and treatment of hypertension patients. This study develops a fuzzy expert system to diagnose the hypertension risk for different patients based on a set of symptoms and rules. Next we design a neuro fuzzy system for the same set of symptoms and rules using three different types of learning algorithms which are Levenberg-Marquardt (LM), Gradient Descent (GD) and Bayesian Resolution (BR) based learning functions. Then this paper presents a comparative study between fuzzy expert system (FES) and feed forward back propagation based neuro fuzzy system (NFS) for hypertension diagnosis. This paper also presents a comparison among the learning functions (LM, GD and BR) where Levenberg-Marquardt based learning function shows its efficiency over the others. Comparison between FES and NFS shows the effectiveness of using NFS over FES. Here, the input data set has been collected from 10 patients whose ages are between 20 and 40 years, both for male and female. The input parameters taken are age, body mass index (BMI), blood pressure (BP), and heart rate. The diagnosis process, linguistic variables and their values were modeled based on expert´s knowledge and from existing database.