TY - GEN
T1 - Biomarker discovery for risk stratification of cardiovascular events using an improved genetic algorithm
AU - Zhou, Xiaobo
AU - Wang, Honghui
AU - Wang, Jun
AU - Hoehn, Gerard
AU - Azok, Joseph
AU - Brennan, Marie Luise
AU - Hazen, Stanley L.
AU - Li, King
AU - Wong, Stephen T.C.
PY - 2006/12/1
Y1 - 2006/12/1
N2 - Detection of an optimal panel of biomarkers capable of predicting a patient's risk of major adverse cardiac events (MACE) is of clinical significance. Due to the high dynamic range of the protein concentration in human blood, applying proteomics techniques for protein profiling can generate large arrays of data for development of optimized clinical biomarker panels. The objective of this study is to discover a panel of biomarkers for predicting risk of MACE in subjects reliably. The development of immunoassay can only tolerate the complexity of the prediction model with less than ten selected biomarkers. Hence, traditional optimization methods, such as genetic algorithm, cannot be used to derive a solution in such a high-dimensional space. In this paper, we propose an improved genetic algorithm with the local floating searching technique to discover a subset of biomarkers with improved prognostic values for prediction of MACE. The proposed method has been compared with standard genetic algorithm and other feature selection approaches based on the MACE prediction experiments.
AB - Detection of an optimal panel of biomarkers capable of predicting a patient's risk of major adverse cardiac events (MACE) is of clinical significance. Due to the high dynamic range of the protein concentration in human blood, applying proteomics techniques for protein profiling can generate large arrays of data for development of optimized clinical biomarker panels. The objective of this study is to discover a panel of biomarkers for predicting risk of MACE in subjects reliably. The development of immunoassay can only tolerate the complexity of the prediction model with less than ten selected biomarkers. Hence, traditional optimization methods, such as genetic algorithm, cannot be used to derive a solution in such a high-dimensional space. In this paper, we propose an improved genetic algorithm with the local floating searching technique to discover a subset of biomarkers with improved prognostic values for prediction of MACE. The proposed method has been compared with standard genetic algorithm and other feature selection approaches based on the MACE prediction experiments.
UR - http://www.scopus.com/inward/record.url?scp=42749108274&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=42749108274&partnerID=8YFLogxK
U2 - 10.1109/LSSA.2006.250393
DO - 10.1109/LSSA.2006.250393
M3 - Conference contribution
AN - SCOPUS:42749108274
SN - 1424402786
SN - 9781424402786
T3 - 2006 IEEE/NLM Life Science Systems and Applications Workshop, LiSA 2006
BT - 2006 IEEE/NLM Life Science Systems and Applications Workshop, LiSA 2006
T2 - 2006 IEEE/NLM Life Science Systems and Applications Workshop, LiSA 2006
Y2 - 13 July 2006 through 14 July 2006
ER -