Prediction of neural tube defect using support vector machine.

Authors :: Wang JF
Liu X
Liao YL
Chen HY
Li WX
Zheng XY
Source :: Biomedical and environmental sciences : BES [Biomed Environ Sci] 2010 Jun; Vol. 23 (3), pp. 167-72.
Publication Year :: 2010
Abstract: Objective: To predict neural tube birth defect (NTD) using support vector machine (SVM).<br />Method: The 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.<br />Result: NTD 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.<br />Conclusion: Results from this study have shown that SVM is applicable to the prediction of NTD.<br /> (Copyright © 2010 The Editorial Board of Biomedical and Environmental Sciences. Published by Elsevier B.V. All rights reserved.)