TY - GEN
T1 - Newborn Screening System Based on Adaptive Feature Selection and Support Vector Machines
AU - Hsieh, Sung-Huai
AU - Chien, Yin-Hsiu
AU - Shen, Chia-Ping
AU - Chen, Wei-Hsin
AU - Chen, Po Hao
AU - Hsieh, Sheau-Ling
AU - Cheng, Po-Hsun
AU - Lai, Feipei
PY - 2009
Y1 - 2009
N2 - The clinical symptoms of metabolic disorders during neonatal period are often not apparent, if not treated early irreversible damages such as mental retardation may occur, even death. Therefore, practicing newborn screening is very important to prevent neonatal from these damages. In this paper, the newborn screening system used support vector machines (SVM) classification technique is proposed in place of cut-off value decision to evaluate the metabolic substances concentration raw data obtained from tandem mass spectrometry (MS/MS) and determine whether the newborn has some kinds of metabolic disorder diseases. On the basis of the proposed features, new analytic combinations are identified with superior discriminatory performance compared with the best published combinations. Classifiers built with the feature selection to find C3/C2, C3 and C16 of three key point features achieved diagnostic sensitivities, specificities and accuracy approaching 100%.
AB - The clinical symptoms of metabolic disorders during neonatal period are often not apparent, if not treated early irreversible damages such as mental retardation may occur, even death. Therefore, practicing newborn screening is very important to prevent neonatal from these damages. In this paper, the newborn screening system used support vector machines (SVM) classification technique is proposed in place of cut-off value decision to evaluate the metabolic substances concentration raw data obtained from tandem mass spectrometry (MS/MS) and determine whether the newborn has some kinds of metabolic disorder diseases. On the basis of the proposed features, new analytic combinations are identified with superior discriminatory performance compared with the best published combinations. Classifiers built with the feature selection to find C3/C2, C3 and C16 of three key point features achieved diagnostic sensitivities, specificities and accuracy approaching 100%.
KW - TANDEM MASS-SPECTROMETRY
U2 - 10.1109/BIBE.2009.72
DO - 10.1109/BIBE.2009.72
M3 - Conference contribution
BT - 9th IEEE International Conference on BioInformatics and BioEngineering
PB - IEEE
ER -