TY - GEN
T1 - Ranking predictors of complications following a drug eluting stent procedure using support vector machines
AU - Gouripeddi, Ramkiran K.
AU - Balasubramanian, V. N.
AU - Panchanathan, Sethuraman
AU - Harris, J.
AU - Bhaskaran, A.
AU - Siegel, R. M.
PY - 2009
Y1 - 2009
N2 - Predictive and risk stratification models using machine learning algorithms such as Support Vector Machines (SVMs), have been used in cardiology and medicine to improve patient care and prognosis. In this work, we have used SVM based Recursive Feature Elimination (SVM-RFE) methods to select patient attributes/features relevant to the etio-pathogenesis of complications following a drug eluting stent (DES) procedure. With a high dimensional feature space (145 features, in our case), and comparatively few patients, there is a high risk of 'over-fitting'. Also, for the model to be clinically relevant, the number of patient features need to be reduced to a manageable number, to be used in patient care. SVM-RFE selects subsets of patient features that have maximal influence on the risk of a complication. In our results, when compared with our initial model with all the 145 features, we obtained better performance of the classifiers with 75 top ranked patient features, a 50% reduction in the original dimensionality of the data space. There was a universal improvement in performance of all SVMs with different kernels and parameters. This method of feature ranking helps to determine the most informative patient features. Use of these relevant features improves the prediction of complications following a DES procedure.
AB - Predictive and risk stratification models using machine learning algorithms such as Support Vector Machines (SVMs), have been used in cardiology and medicine to improve patient care and prognosis. In this work, we have used SVM based Recursive Feature Elimination (SVM-RFE) methods to select patient attributes/features relevant to the etio-pathogenesis of complications following a drug eluting stent (DES) procedure. With a high dimensional feature space (145 features, in our case), and comparatively few patients, there is a high risk of 'over-fitting'. Also, for the model to be clinically relevant, the number of patient features need to be reduced to a manageable number, to be used in patient care. SVM-RFE selects subsets of patient features that have maximal influence on the risk of a complication. In our results, when compared with our initial model with all the 145 features, we obtained better performance of the classifiers with 75 top ranked patient features, a 50% reduction in the original dimensionality of the data space. There was a universal improvement in performance of all SVMs with different kernels and parameters. This method of feature ranking helps to determine the most informative patient features. Use of these relevant features improves the prediction of complications following a DES procedure.
UR - http://www.scopus.com/inward/record.url?scp=77952717199&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77952717199&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77952717199
SN - 9781424472819
T3 - Computers in Cardiology
SP - 345
EP - 348
BT - Computers in Cardiology 2009, CinC 2009
T2 - 36th Annual Conference of Computers in Cardiology, CinC 2009
Y2 - 13 September 2009 through 16 September 2009
ER -