We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Tıbbi Tahminde Alternatif Bir Yaklaşım: Destek Vektör Makineleri.
- Authors
AKŞEHİRLİ, Özge YILMAZ; ANKARALI, Handan; AYDIN, Duygu; SARAÇLI, Özge
- Abstract
Objective: This study was intended as an application in medical research of support vector machines (SVM) that is commonly used in many domains and aimed to determine the success of correct classification of SVM method by using a medical data set. Material and Methods: In this study, supervised SVM that is used for classification or regression was performed. Here an application of two class SVM was performed for nonlinear relationships. A support vector machine constructs a hyperplane or set of hyperplanes in a high- or infinite- dimensional space, which can be used for classification, regression, or other tasks. Intuitively, a good separation is achieved by the hyperplane that has the largest distance to the nearest training data points of any class, since in general the larger the margin the lower the generalization error of the classifier. So, SVM training algorithm builds a model that assigns new examples into one category or the other. In medicine, SVM is used for cancer morphology, identifying success of treatment and related gene, diagnosing various diseases. In application of the study, informations about 433 patient who were refer to the outpatient department of Zonguldak Karaelmas University Faculty of Medicine between date of 1 -31 January 2011 for complaints of night eating syndrome were used. Results: Descriptive statistics for 17 variables were calculated and according to the results obtained from univariate analysis, GYA, BSQ, SCL scores, marital status, smoking status, psychological diagnosis are effective variables for diagnosis of night eating syndrome. When the results obtained by using nonlinear SVM were examined, the success of diagnosis of the model was observed very well according to accuracy and area under ROC curve. Conclusion: SVM method based on statistical learning theory is a new and effective method for classification nonlinear data with complex structure. For this reason it can prefer to many classification method.
- Subjects
SUPPORT vector machines; REGRESSION analysis; DESCRIPTIVE statistics; ALGORITHMS; HYPERPLANES
- Publication
Turkiye Klinikleri Journal of Biostatistics, 2013, Vol 5, Issue 1, p19
- ISSN
1308-7894
- Publication type
Article