Applying the Logistic Regression Model to Predict the Stenosis in Carotid Artery Using the Sequential Color Doppler Ultrasound Image Processing

Document Type : Original Article

Abstract

Background- Early detection of stenosis in carotid artery is essential because it directly affects the
patients' clinical management and is of prognostic value. Therefore, estimating mechanical
properties of this artery in normal and atherosclerosis cases is important as far as medical
treatment is concerned. We applied a logistic regression model to predict carotid artery
stenosis in a group of patients based on the quantitative features extracted from the processing
of the conventional color Doppler ultrasound images.
Methods- Our database includes 128 patient records consisting 10 quantitative features. The
database is then randomly divided into the training and validation samples including 98 and
30 patient records respectively. The training and validation samples are used to construct the
logistic regression model and to validate its performance. Finally, important criteria such as
sensitivity, specificity, accuracy and receiver operating characteristic curve (ROC) analysis
for this method are evaluated.
Results- Our results show that the logistic regression model is able to classify correctly 28 out of 30
cases presented in the validation sample. The output of this method showed a high positive
predictive value of 94%.
Conclusion- We have established a logistic discriminator approach which is able to predict the
probability of stenosis in the carotid artery using features extracted from ultrasonic
measurements on ultrasound imaging (Iranian Heart Journal 2008; 9 (2):43-50).

Keywords


M. Mokhtari-Dizaji PhD, P. Abdolmaleki2 PhD, H. Saberi3 MD, T. Rahmani1 MSc

1. Johnson MB, Wilkinson ID, Wattam J.
Comparison of Doppler ultrasound, magnetic
resonance angiographic techniques and catheter
angiography in evaluation of carotid stenosis.
Clin Radiol 55: 912-920, 2000.
2. Cohn JN. New approaches to screening for
vascular and cardiac risk. AJH 14: 218-220,
2001.
3. Nagaiy Y, Mutsumoto M, Metter EJ. The carotid
artery as a noninvasive window for
cardiovascular risk in apparently healthy
individuals. Ultrasound Med Biol 28: 1231-
1238, 2002.
4. Benetos A, Waeber B, Izzo J, Mitchell G,
Resnick L, Asmar R, et al. Influence of age,
risk factors and cardiovascular and renal disease
on arterial stiffness: clinical application. AJH
15: 1101-1108, 2002.
5. Reneman RS, Hoeks AP. Noninvasive vascular
ultrasound: an asset in vascular medicine.
Cardiovasc Res 45: 27-35, 2002.
6. Hayoz D, Rutschmann B, Perret F. Conduit
artery compliance and distensibility are not
necessarily reduced in hypertension. Am J
Hypertension 20: 1-6, 1992.
7. Simon A, Levenson J. Use of arterial compliance
for evaluation of hypertension. Am J
Hypertension 4: 97-105, 1991.
8. Merode TV, Hick P. Carotid artery wall
properties in normotensive and borderline
hypertensive subjects of various ages.
Ultrasound Med Biol 14: 563- 569, 1998.
9. Zanchetti A, Bond MG, Hennig M. Risk factors
associated with alteration in carotid intimamedia
thickness in hypertension: baseline data
from the European lacidipine study on
atherosclerosis. J Hypertens 16: 949-961, 1998.
10. Airaksinen KE, Salmela PI. Diminished arterial
elasticity in diabetes; association with
fluorescent advanced glycosylation end
products in collagen. Cardiovasc Res 27: 942-
945, 1998.
11. Hickler RB. Aortic and large artery stiffness:
current methodology and clinical correlations.
Clin Cardiol 13: 317-322, 1990.
12. Howard G, Sharrett AR, Heiss G. Carotid artery
intimal-media thickness distribution in general
populations as evaluated by B-mode ultrasound.
ARIC investigators. Stroke 24: 1297-1304,
1993.
13. Alva F, Samaniego V, Gonzalez V. Structural
and dynamic changes in the elastic arteries due
to arterial hypertension and
hypercholesterolemia. Clin Cardiol 16: 614-
618, 1993.
14. Tomochika Y, Okuda F, Tanaka N.
Improvement of atherosclerosis and stiffness of
thoracic descending aorta with cholesterollowering
therapies in familial
hypercholesterolemia. Arterioscler Thromb
Vasc Biol 16: 955-962, 1996.
15. Metz CE. Some practical issues of experimental
design and data analysis in radiological ROC
studies. Invest Radiol 24: 234-245, 1989.
16. Metz CE. ROC methodology in radiologic
imaging. Invest Radiol 21: 720-733, 1986.
17. Mokhtari-Dizaji M, Nikanjam N, Saberi H.
Detection of initial symptoms of atherosclerosis
using estimation of local static pressure by
ultrasound. Atherosclerosis 178: 123-128, 2005.
18. Peterson LH, Jensen RE, Parnell J. Mechanical
properties of arteries in vivo. Circ Res 8: 622-
639, 1960.
19. Hayashi K, Handa H, Nagasawa S. Stiffness and
elastic behavior of human intracranial and
extracranial arteries. J Biomech 13: 175-184,
1980.
20. Anderson JA. Separate sample logistic
discrimination. Biometrika 1972.
21. Hosmer D W, Lemeshow S. Applied logistic
regression; Wiley, New York, 1989.
22. Abdolmaleki P, Yarmohammadi M, Gity M.
Comparison of logistic regression and neural
network models in predicting the outcome of
biopsy in breast cancer from MRI findings. Iran
J Radiat Res 1: 217-228, 2004.
23. Nagelkerke NJD. A note on general definition of
the coefficient of determination. Biometrika 78:
691–692, 1991.
24. Jiang Y, Metz CE, Nishikawa RM. A receiver
operating characteristic partial area index for
highly sensitive diagnostic tests. Radiol 201:
745-750, 1996.
25. Trucksass AS, Grathwohl D, Schmid A, Boragk
R, Upmeier C, Keul J and et al. Assessment of
carotid wall motion and stiffness with tissue
Doppler imaging. Ultrasound Med Biol 24:
639- 646, 1998.
26. Giannoglou GD, Saulis JV, Farmakis TM,
Farmakis DM, Louridas GE. Haemodynamic
factors and the important role of local low static
pressure in coronary wall thickening. Int J
Cardiology 86: 27-40, 2002.
27. Savely VS, Yablokov EG. Ultrasound
assessment of atherosclerosis dynamic under
treatment of dislipoproteidemia. Eur J
Ultrasound 6: 19, 1997.
28. Mokhtari-Dizaji M, Nikanjam N, Babapoor B.
Estimation of elastic modulus, stiffness
distensibility, compliance and Young modulus
in atherosclerosis human common carotid
artery. Iran Heart J 4: 68-74, 2003.
29. Chou YH, Tiu CM, Hung GS, Wu SC, Chang
TY, Chiang HK. Stepwise logistic regression
analysis of tumor contour features for breast
ultrasound diagnosis. Ultrasound Med Biol 27:
1493-498, 2001.