Abstract
Four algorithms of data mining (C&RT, CHAID, C4.5 and WizWhy) were applied to produce rules for classification of three types of stroke on 298 cases used for learning and testing. The C&RT, CHAID algorithms did not give acceptable results of the classification. The system See5 was able to give low classification error in the mode of constructing a decision tree with decisions amplification in combination with fuzzy thresholds. Unfortunately, the rule sets obtained on the training samples, in test mode showed unsatisfactory results. WizWhy system showed acceptable accuracy, but practical use of generated rules is rather complicated.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Kotova, E.Y.: Clinical and epidemiological characteristics, the leading risk factors, the features of the of stroke in Ulyanovsk, Russia (according to the Register of stroke). Abstract of PhD thesis, Moscow, p. 25 (2009) (in Russian)
Gusev, E.I., et al.: Epidemiology of stroke in Russia. J. Neurol. Psychiatry, Suppl. 103(8), 4–9 (2003) (in Russian)
Wardlaw, J.M., Keir, S.L., Dennis, M.S.: The impact of delays in computed tomography of the brain on the accuracy of diagnosis and subsequent management in patients with minor stroke. J. Neurol. Neurosurg. Psychiatry 74(1), 77–81 (2003)
Saur, D., Kucinski, T., Grzyska, U., et al.: Sensitivity and interrater agreement of CT and diffusion-weighted MR imaging in hyperacute stroke. Am J. Neuroradiol. 24(5), 878–885 (2003)
Kalafut, M.A., Schriger, D.L., Saver, J.L., Starkman, S.: Detection of early CT signs of 1 / 3 middle cerebral artery infarctions: interrater reliability and sensitivity of CT interpretation by physicians involved in acute stroke care. Stroke 31(7), 1667–1671 (2000)
Dippel, D.W., Du Ry van Beest Holle, M., van Kooten, F., Koudstaal, P.J.: The validity and reliability of signs of early infarction on CT in acute ischaemic stroke. Neuroradiology 42(9), 629–633 (2000)
Grotta, J.C., Chiu, D., Lu, M., Patel, S., et al.: Agreement and variability in the interpretation of early CT changes in stroke patients qualifying for intravenous rtPA therapy. Stroke 30(8), 1528–1533 (1999)
Yu, R.O.: Application of data mining to solve the problem of medical diagnostics. News of Artificial Intelligence (3), 76–80 (2004) (in Russian)
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Cole Advanced Books & Software. Wadsworth & Brooks, Monterey (1984)
Kass, G.V.: An exploratory technique for investigating large quantities of categorical data. Applied Statistics 29, 119–127 (1980)
Friedman, J.H.: Stochastic Gradient Boosting. Stanford University (1999)
Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning: Data mining, Inference and Prediction. Springer, New York (2001)
Hyafil, L., Rivest, R.L.: Constructing Optimal Binary Decision Trees is NP - complete. Information Processing Letters 5(1), 15–17 (1976)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Naftulin, I.S., Rebrova, O.Y. (2010). Application of C&RT, CHAID, C4.5 and WizWhy Algorithms for Stroke Type Diagnosis. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2010. Lecture Notes in Computer Science(), vol 6113. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13208-7_81
Download citation
DOI: https://doi.org/10.1007/978-3-642-13208-7_81
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13207-0
Online ISBN: 978-3-642-13208-7
eBook Packages: Computer ScienceComputer Science (R0)