Title :
Risk factor fusion for predicting multifactorial diseases
Author :
Phegley, James ; Perkins, Kyle ; Gupta, Lalit ; Dorsey, J. Kevin
Author_Institution :
Southern Illinois Univ., Carbondale, IL, USA
Abstract :
A generalized classification methodology which employs risk factor fusion, normalization, DKLT based transformation, feature selection, and parametric classifier design is developed to predict the presence or absence of a multifactorial disease. The validity of method is demonstrated by applying it to predict the occurrence of gout in patients.
Keywords :
Karhunen-Loeve transforms; covariance matrices; diseases; eigenvalues and eigenfunctions; patient diagnosis; pattern classification; sensor fusion; DKLT based transformation; data-fusion based pattern recognition approach; feature selection; generalized classification methodology; gout; multifactorial diseases prediction; normalization; parametric classifier design; risk factor fusion; Arthritis; Covariance matrix; Diseases; Karhunen-Loeve transforms; Pattern recognition; Testing; Vectors; Virtual manufacturing;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020632
