Evaluation of forced expiratory volume prediction in spirometric test using Principal Component Analysis
by Anandan Kavitha, Manoharan Sujatha, Swaminathan Ramakrishnan
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 5, No. 2/3, 2011

Abstract: In this work, an attempt has been made to evaluate the clinical relevance of lung function spirometric test using neural network based prediction and Principal Component Analysis (PCA). Flow–volume curves generated using spirometer on subjects (N = 175) under standard recording protocol were used for the present study. The most significant spirometric parameter FEV1 predicted using Radial basis function neural networks (RBFNN) incorporating k-means clustering method was considered further for analysing the interdependency of spirometric parameters. PCA was performed on the measured and predicted datasets to analyse the interdependency among the parameters. Results demonstrate that PCA confirms the consistency in prediction of FEV₁ for normal subjects. It appears that this method of prediction and principal component analysis could be useful in explaining the significance of FEV₁ in assessing the lung function abnormalities for spirometric pulmonary function test with incomplete data.

Online publication date: Wed, 21-Jan-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com