Spirometric data analysis by support vector machine

Abstract

A spirometer is an apparatus for measuring the volume of air inspired and expired by the lungs. Spirometry is one of the most widely applied clinical tests in respiratory medicine to diagnose obstructive and to rule out restrictive pulmonary diseases. In this work, attempt has been made to predict pattern recognition accuracy using support vector regression in order to enhance the spirometric investigations. Support vector machine constructs a hyperplane or set of hyperplanes in a high-or infinite- dimensional space, which can be used for classification, regression, or other tasks. We have collected data from different hospitals. The acquired data are then used to predict pattern recognition accuracy. Since this method is useful in diagnosing the pulmonary abnormalities with incomplete data and data with poor recording. We applied the SVM to construct the prediction model and select Polynomial Function as the kernel function.