INTRODUCTION his/her distinct attributes, the availability of an enhanced

INTRODUCTION

Technological
improvements in the field of science and health care have given rise to the
application of computer aided systems and applications in handling medical and
health issues. Medical practitioners which include doctors, laboratory specialists
and assistants, nurses are faced with hundreds of situations where they have to
make a decision about the health condition of their patients based on the
patient’s symptoms and signs.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

With the increasing
need for efficient health care and the need for timely decisions, it is obvious
that the traditional method of sieving knowledge from records can no longer be
sustained as this result to delay and errors in medical decisions. The amount
of time required for laboratory diagnostic results to be available must be
optimized for better health care and for timely decision making. Data mining as
a branch of computer science has evolved to assist medical personnel in
performing their functions more effectively. With the availability of large
amount of patient information in health organizations, decision making as
regards patients condition can be more optimized and made faster through data
mining knowledge discovery techniques. Many computational tools and algorithms
have been recently developed to increase the experiences and the abilities of
physicians for taking decisions about different diseases.(1)

Diabetes mellitus is a
chronic disease caused by inherited and/or acquired deficiency in production of
insulin by the pancreas, or by the ineffectiveness of the insulin produced.
Such a deficiency results in increased concentrations of glucose in the blood,
which in turn damage many of the body systems, in particular the blood vessels
and nerves.(2) according to the WHO media center, “The number of people with
diabetes has risen from 108million in 1980 to 422 million in 2014. In 2015, an
estimated 1.6million deaths were directly caused by diabetes with another 2.2
million deaths attributable to high blood glucose in 2012. Diabetes is a major
cause of blindness, kidney failure, heart attack, stroke and lower limb
amputation,” (2). Early diagnosis has been identified as a major step in the
fight against the dangers of diabetes. Although every individual has his/her
distinct attributes, the availability of an enhanced data mining algorithm to
help in the early diagnosis of diabetes will help advert the dangers of late
diagnosis and improve the management of diabetic cases.

In this study, an
evaluation of the performance of Naïve Bayesian classifier in predicting diabetes
disease in individuals is analyzed using experimental and statistical
procedures. Classification is a form of data analysis that extracts models
describing important data classes. Such models called classifiers predict
categorical(discrete, unordered) class labels.(3)  Classification is the process of splitting a
dataset into mutually exclusive groups called a class based on suitable
attributes.(4). Classification has numerous applications including fraud
detection, target marketing, performance prediction, manufacturing and medical
diagnosis. Naïve Bayesian classifier can show the result of a patients test
with a pre-test probability (of the population), to predict or determine the
chance of finding a particular disease. With the application of Naïve Bayesian
classifier we can imply that Bayes theorem can be used as a rule for inferring
or updating the amount of “belief” in the light of new information(5). The main
goal of this study is to show the effectiveness of Naïve Bayesian Classifier in
the prediction of diabetes diagnosis.