Prediction of neural tube defect using support vector machine.
- Author:
Jin-Feng WANG
1
;
Xin LIU
;
Yi-Lan LIAO
;
Hong-Yan CHEN
;
Wan-Xin LI
;
Xiao-Ying ZHENG
Author Information
- Publication Type:Journal Article
- MeSH: China; epidemiology; Humans; Neural Tube Defects; epidemiology; Pilot Projects
- From: Biomedical and Environmental Sciences 2010;23(3):167-172
- CountryChina
- Language:English
-
Abstract:
OBJECTIVETo predict neural tube birth defect (NTD) using support vector machine (SVM).
METHODThe dataset in the pilot area was divided into non overlaid training set and testing set. SVM was trained using the training set and the trained SVM was then used to predict the classification of NTD.
RESULTNTD rate was predicted at village level in the pilot area. The accuracy of the prediction was 71.50% for the training dataset and 68.57% for the test dataset respectively.
CONCLUSIONResults from this study have shown that SVM is applicable to the prediction of NTD.
