000169229 001__ 169229
000169229 005__ 20190316235218.0
000169229 020__ $$a978-1-4244-4122-8
000169229 02470 $$2ISI$$a000298810000036
000169229 037__ $$aCONF
000169229 041__ $$aeng
000169229 245__ $$aExample-based Support Vector Machine for Drug Concentration Analysis
000169229 269__ $$a2011
000169229 260__ $$bIeee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa$$c2011
000169229 336__ $$aConference Papers
000169229 520__ $$aMachine learning has been largely applied to ana- lyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (SVM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVM- based approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.
000169229 6531_ $$aalgorithms and techniques for systems modelling
000169229 6531_ $$aparameter estimation
000169229 6531_ $$amedical decision making
000169229 700__ $$0242425$$g190358$$aYou, Wenqi
000169229 700__ $$aWidmer, Nicolas
000169229 700__ $$g167918$$aDe Micheli, Giovanni$$0240269
000169229 7112_ $$dAugust 30 - September 3, 2011$$cBoston, Massachusetts, USA$$a33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2011)
000169229 773__ $$tProceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2011)$$q153-157
000169229 8564_ $$uhttps://infoscience.epfl.ch/record/169229/files/00382701.pdf$$zn/a$$s590536$$yn/a
000169229 909C0 $$xU11140$$0252283$$pLSI1
000169229 909CO $$pIC$$ooai:infoscience.tind.io:169229$$qGLOBAL_SET$$pconf$$pSTI
000169229 917Z8 $$x112915
000169229 937__ $$aEPFL-CONF-169229
000169229 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000169229 980__ $$aCONF