Pattern Detection of Atherosclerosis from Carotid Artery Doppler Signals using Fuzzy Weighted Pre-Processing and Least Square Support Vector Machine (LSSVM)
Annals of Biomedical EngineeringPublished 26 March 2007
Kemal Polat, Sadık Kara, Fatma Lati̇foğlu, Salih Güneş
Citations22
SJR quartileQ2
SJR score0.77
SNIP1.19
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The employed expert system has achieved 100% classification accuracy using a 10-fold Cross Validation (CV) method and fuzzy weighted pre-processing based is proposed expert system, applied to inputs obtained from spectral analysis of Carotid Artery Doppler Signals.
Abstract
Carotid Artery Doppler Signals were recorded from 114 subjects, 60 of whom had Atherosclerosis disease while the rest were healthy controls. Diagnosis of Atherosclerosis from Carotid Artery Doppler Signals was conducted using Fuzzy weighted pre-processing and Least Square Support Vector Machine (LSSVM). First, in order to determine the LSSVM inputs, spectral analysis of Carotid Artery Doppler Signals was performed via Autoregressive (AR) modeling. Then, fuzzy weighted pre-processing based is proposed expert system, applied to inputs obtained from spectral analysis of Carotid Artery Doppler Signals. LSSVM was used to detect Atherosclerosis from Carotid Artery Doppler Signals. All data set were obtained from Carotid Artery Doppler Signals of healthy subjects and subjects suffering from Atherosclerosis disease. The employed expert system has achieved 100% classification accuracy using a 10-fold Cross Validation (CV) method.
Keywords
MedicineHealth Professions
IEEE Transactions on Automatic ControlA new look at the statistical model identification
50,732 Citations1974Hirotugu Akaike
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Neural Processing LettersLeast Squares Support Vector Machine Classifiers
9,375 Citations1999Johan A. K. Suykens, Joos Vandewalle
A least squares version for support vector machine (SVM) classifiers that follows from solving a set of linear equations, instead of quadratic programming for classical SVM's.
Proceedings of the IEEESpectrum analysis—A modern perspective
3,142 Citations1981Steven Kay, S.L. Marple
A summary of many of the new techniques developed in the last two decades for spectrum analysis of discrete time series is presented, including the classical periodogram, classical Blackman-Tukey, autoregressive, moving average, autotegressive-moving average, maximum likelihood, Prony, and Pisarenko methods.
Artificial Intelligence in MedicinePredicting breast cancer survivability: a comparison of three data mining methods
1,216 Citations2004Dursun Delen, Glenn Walker +1 more
The comparative study of multiple prediction models for breast cancer survivability using a large dataset along with a 10-fold cross-validation provided us with an insight into the relative prediction ability of different data mining methods.
CirculationStiffness of systemic arteries in patients with myocardial infarction. A noninvasive method to predict severity of coronary atherosclerosis.
748 Citations1989Toshinori Hirai, S Sasayama +2 more
The static elastic properties of arterial tree (abdominal aorta and common carotid artery) provided sufficiently reliable information on changes caused by atherosclerosis.
European Heart JournalDistensibility of the ascending aorta: comparison of invasive and non-invasive techniques in healthy men and in men with coronary artery disease
449 Citations1990Christodoulos Stefanadis, Costas Stratos +3 more
It is indicated that aortic distensibility in patients with coronary artery disease can be obtained non-invasively with a high degree of accuracy.
The LancetAortic distensibility in patients with isolated hypercholesterolaemia, coronary artery disease, or cardiac transplant
263 Citations1991Anthony M. Dart, Florence Lacombe +5 more
The results indicate that aortic distensibility might be an indicator of coronary heart disease and that it might be useful in identifying which symptom-free subjects with modest hypercholesterolaemia should be treated aggressively.
Pattern RecognitionFeature extraction and dimensionality reduction algorithms and their applications in vowel recognition
260 Citations2003Xuechuan Wang, Kuldip K. Paliwal
The minimum classification error (MCE) training algorithm (which was originally proposed for optimizing classifiers) is investigated for feature extraction and a generalized MCE (GMCE)Training algorithm is proposed to mend the shortcomings of the MCE training algorithm.
Neural NetworksFuzzy least squares support vector machines for multiclass problems
220 Citations2003D. Tsujinishi, Shigeo Abe
The Journal of Clinical MonitoringClassification-algorithm evaluation: Five performance measures based onconfusion matrices
147 Citations1995A. Dean Forbes
Five performance measures lead to similar inferences when comparing a trio of QRS-detection algorithms using a large data set, and the modified NMI is preferred, because it obeys each of the constraints and is the most conservative measure of performance.
Ultrasound in Medicine & BiologyA comparative study and assessment of doppler ultrasound spectral estimation techniques part II: Methods and results
124 Citations1988P.J. Vaitkus, R.S.C. Cobbold +1 more
Results indicate that both the AR(Yule-Walker) and ARMA(singular value decomposition) models of orders (8) and (4,4), respectively, show good agreement with the theoretical spectrum, and yield estimates with variances considerably less than the Fast Fourier Transform (FFT).
Ultrasound in Medicine & BiologyA Brief History of Doppler Ultrasound in the Diagnosis of Peripheral Vascular Disease
120 Citations1998Bernard Sigel
Through progressive steps, Doppler ultrasound technology has provided clinical applications in blood-flow sensing, waveform analysis, localizing blood flow and two-dimensional mapping of blood flow.
Expert Systems with ApplicationsA new method to medical diagnosis: Artificial immune recognition system (AIRS) with fuzzy weighted pre-processing and application to ECG arrhythmia
119 Citations2005Kemal Polat, Seral Şahan +1 more
F fuzzy weighted pre-processing, which can be improved by the authors', is a new method and firstly, it is applied to ECG dataset, which is classified by using AIRS classifier system.
Archives of SurgeryUpstream Stenosis
87 Citations1980R N Baird
LT damping is a sensitive method of analyzing femoral Doppler signals in the noninvasive detection of iliac artery stenosis and the results with PI were inferior at every grade of severity of ileic disease when assessed by receiver-operator characteristic curves.
British journal of surgeryCommon femoral artery Doppler wave-forms: A comparison of three methods of objective analysis with direct pressure measurements
68 Citations1984D S Macpherson, David H. Evans +1 more
Principal component analysis appears to be the most powerful method of Doppler wave‐form analysis so far described and may have a place in the non‐invasive assessment of the aorto‐iliac segment.
Ultrasound in Medicine & BiologySelection of the order of autoregressive models for spectral analysis of doppler ultrasound signals
57 Citations1990Fernando S. Schlindwein, David H. Evans
It was found that, for more than 98% of the 1280 frames of Doppler signals analyzed, the order selected by the various criteria was ten or less, and overestimating the model order is better than underestimating it.
Journal of Vascular SurgeryComparison of color-flow Doppler scanning, power Doppler scanning, and frequency shift for assessment of carotid artery stenosis
50 Citations2001Martín Müller, Pierra Ciccotti +2 more
CD and PD carotid artery stenosis measurements are highly reproducible, and in the hands provided accuracy equal to PSF.
PubMedAssessment of aortoiliac obstructive disease by Doppler spectrum analysis of blood flow velocities in the common femoral artery at rest and during reactive hyperemia.
46 Citations1991W N van Asten, W. J. Beijneveld +4 more
Analysis of Doppler spectra-obtained noninvasively from the common femoral artery at rest and during reactive hyperemia provides an accurate hemodynamic assessment of the aortoiliac segment.
British journal of surgeryPostocclusive hyperaemic duplex scan: A new method of aortoiliac assessment
18 Citations1995I.C. Currie, Y.G. Wilson +2 more
The PHD test provides a simple, non‐invasive assessment for aortoiliac disease that can be performed on the initial outpatient clinic visit and was more sensitive than femoral pulse palpation and compared favourably with arteriography.
Ultrasonic ImagingDoppler Angle Estimation of Pulsatile Flows Using AR Modeling
7 Citations2002Chih‐Kuang Yeh, Pai‐Chi Li
It is concluded that real-time two-dimensional estimation of the Doppler angle is possible using the AR method in the presence of pulsatile flows and both the AR and FFT methods are not adequate due to the spectral broadening effects from the turbulence.