Information Technology Reference
In-Depth Information
Atherosclerosis is usually diagnosed after symptoms or complications have arisen.
There are a number of tests in diagnosing vascular diseases, including blood tests,
electrocardiogram, stress testing, angiography, ultrasound, and computed tomogra-
phy. Angiography is used to look inside arteries to see if there is any blockage and
how much [2, 3]. This is the most accurate way to assess the presence and severity of
vascular disease. On the other hand this technique involves injecting dye directly into
the arteries. Therefore this is a much more invasive.
Having so many factors to analyze to diagnose the Atherosclerosis disease of a pa-
tient makes the physician's job difficult. A physician usually makes decisions by
evaluating the current test results of a patient and by referring to the previous deci-
sions she or he made on other patience with the same condition. The former method
depends strongly on the physician's knowledge. On the other hand, the latter depends
on the physician's experience to compare her patient with her earlier patients. This
job is not easy considering the number of factors she has to evaluate. In this crucial
step, she may need an accurate tool that lists her previous decisions on the patient
having same (or close to same) factors.
In this study, resource allocation of AIRS was changed with its equivalence formed
with Fuzzy-Logic to increase its classification performance by means of resource
number. The effects of this change were analyzed in the applications using Carotid
Artery Doppler Signals. Fuzzy-AIRS, which proved it self to be used as an effective
classifier in medical field by reaching its goal, has also provided a considerable de-
crease in the number of resources. In all applications conducted, Fuzzy-AIRS ob-
tained high classification accuracies for diagnosis of Atherosclerosis disease.
The remaining of the paper is organized as follows. We present the used procedure
in the next section. In Section 3, we give the used algorithm called Artificial Immune
Recognition System and Fuzzy resource allocation mechanism. In Section 4, we give
the experimental data to show the effectiveness of our method. Finally, we conclude
this paper in Section 5 with future directions.
2 The Procedure
Fig.1 shows the procedure used in the proposed system. It consists of four parts: (a)
Measurement of Carotid Artery Doppler Signal, (b) Spectral Analysis (AIRS inputs
were selected), (c) Artificial Immune Recognition System with fuzzy resource alloca-
tion mechanism and (d) Classification results (Atherosclerosis and healthy).
2.1 Hardware and Demographic Acknowledgments
Carotid arterial Doppler ultrasound signals were acquired from 60 patients and 54
healthy volunteers. The patient group included thirty-three males and twenty-seven
females with an established diagnosis of atherosclerosis through coronary or aorto-
femoropopliteal (lower extremity) angiography (mean age: 45 years; range: 25-69
years). Healthy volunteers including thirty-five males and nineteen females (mean
age: 26 years; range: 20-39 years) were young non-smokers who appeared not to bear
any risk of atherosclerosis. The two study groups represent the upper and lower
