TY - JOUR
T1 - Diagnosing anorexia based on partial least squares, back propagation neural network, and support vector machines
AU - Zhao, C. Y.
AU - Zhang, R. S.
AU - Liu, H. X.
AU - Xue, C. X.
AU - Zhao, S. G.
AU - Zhou, X. F.
AU - Liu, M. C.
AU - Fan, B. T.
PY - 2004/11
Y1 - 2004/11
N2 - Support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a predictive model for early diagnosis of anorexia. It was based on the concentration of six elements (Zn, Fe, Mg, Cu, Ca, and Mn) and the age extracted from 90 cases. Compared with the results obtained from two other classifiers, partial least squares (PLS) and back-propagation neural network (BPNN), the SVM method exhibited the best whole performance. The accuracies for the test set by PLS, BPNN, and SVM methods were 52%, 65%, and 87%, respectively. Moreover, the models we proposed could also provide some insight into what factors were related to anorexia.
AB - Support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a predictive model for early diagnosis of anorexia. It was based on the concentration of six elements (Zn, Fe, Mg, Cu, Ca, and Mn) and the age extracted from 90 cases. Compared with the results obtained from two other classifiers, partial least squares (PLS) and back-propagation neural network (BPNN), the SVM method exhibited the best whole performance. The accuracies for the test set by PLS, BPNN, and SVM methods were 52%, 65%, and 87%, respectively. Moreover, the models we proposed could also provide some insight into what factors were related to anorexia.
UR - http://www.scopus.com/inward/record.url?scp=10044235707&partnerID=8YFLogxK
U2 - 10.1021/ci049877y
DO - 10.1021/ci049877y
M3 - Article
C2 - 15554673
AN - SCOPUS:10044235707
SN - 0095-2338
VL - 44
SP - 2040
EP - 2046
JO - Journal of Chemical Information and Computer Sciences
JF - Journal of Chemical Information and Computer Sciences
IS - 6
ER -