Title: Analysis of restrictive pulmonary function abnormality using spirometric investigations and QPSO feature selection

Authors: Asaithambi Mythili; Subramanian Srinivasan; C. Manoharan Sujatha; Ganesan Kavitha; Swaminathan Ramakrishnan

Addresses: Department of Instrumentation Engineering, Anna University, Madras Institute of Technology Campus, Chennai, India ' Department of Instrumentation Engineering, Anna University, Madras Institute of Technology Campus, Chennai, India ' Department of Electronics and Communication Engineering, Anna University, CEG Campus, Chennai 600 025, India ' Department of Electronics Engineering, Anna University, Madras Institute of Technology Campus, Chennai, India ' Non-Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India

Abstract: Restrictive pulmonary disorders are leading cause of morbidity and mortality worldwide. Spirometric pulmonary function test is the most common method used to assess restrictive disorder. The sub-maximal effort of the patients may often lead to misclassification due to large interdependency among the spirometric parameters. Also, there is requirement that too many parameters are to be analysed by the physician. In this study, Quantum-behaved Particle Swarm Optimisation (QPSO) approach has been used for identification of significant features that are useful in disease diagnosis. Then the selected feature set is evaluated based on the error in prediction of FEV₁, PEF and FEV₆ using radial basis function neural network. Results show that QPSO is able to identify most significant features in both normal and restrictive. It is also observed that logistic model tree classifier achieves accuracy of 95%. This feature selection appears to aid in detection of pulmonary function disorders using spirometric investigations.

Keywords: pulmonary function test; spirometry; quantum PSO; particle swarm optimisation; restrictive pulmonary disorders; pulmonary function abnormality; QPSO feature selection; neural networks.

DOI: 10.1504/IJBET.2014.065803

International Journal of Biomedical Engineering and Technology, 2014 Vol.16 No.3, pp.195 - 208

Received: 12 Apr 2014
Accepted: 18 Aug 2014
Published online: 25 Apr 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article