Aim: The Boosting Tree, one of the most successful combining methods. The principal aim of these combining algorithms is to obtain strong classifier with small estimation error from the combination of weak classifiers.
Material and Methods: We used boosting method to classify patients with Carpal Tunnel Syndrome. The individuals, who applied to Mersin University’s Medical School’s Neurology Main Scientific Branch’s Electrophysiology Laboratory between the years of 2006 and 2010, with a pre-diagnosis of Carpal Tunnel Syndrome (CTS) were included in the study. Boosting Tree application was conducted in Statistica 7.0 software package.
Results: General success of the model in accurate classification according to the test data was found as 87.67%. Sensitivity and specificity of the latest model, when the test data were used, were calculated respectively as 85.65% and 92.36% .
Conclusion: The model can be used in CTS diagnosis as a successful method.
Key Words: Classification; Boosting Tree; Weak Classifiers.
This article presented at XIII. National Biostatistics Congress on 12-14 September 2011, Ankara, Kızılcahamam.
|
