Evaluation of Flow–Volume Spirometric Test Using Neural Network Based Prediction and Principal Component Analysis

In this work, an attempt has been made to enhance the diagnostic relevance of spirometric pulmonary function test using neural networks and Principal Component Analysis (PCA). For this study, flow–volume curves (N = 175) using spirometers were generated under standard recording protocol. A method based on neural network is used to predict the most significant parameter, FEV1. Further, PCA is used to analyze the interdependency of the parameters in the measured and predicted datasets. Results show that the back propagation neural network is able to predict FEV1 both in normal and abnormal cases. The variation in the magnitude and direction of parameters in the contribution of the principal components shows that FEV1 is a significant discriminator of normal and abnormal datasets and is further confirmed by the percentage variance in the first few principal components. It appears that this method of prediction and principal component analysis on the measured and predicted datasets could be useful for spirometric pulmonary function test with incomplete data.

[1]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

[2]  D. Johns,et al.  Spirometry The Measurement and Interpretation of Ventilatory Function in Clinical Practices , 1995 .

[3]  Swaminathan Ramakrishnan,et al.  ASSESSMENT AND CLASSIFICATION OF MECHANICAL STRENGTH COMPONENTS OF HUMAN FEMUR TRABECULAR BONE USING DIGITAL IMAGE PROCESSING AND NEURAL NETWORKS , 2007 .

[4]  Zhi-Hua Zhou,et al.  Artificial Neural Networks in Biomedicine - Paulo J.G. Lisboa, Emmanuel C. Ifeachor and Piotr S. Szczepaniak (Eds.), Springer-Verlag, London, 2000, ISBN 1-85233-005-8 , 2002, Artif. Intell. Medicine.

[5]  R. Mehra,et al.  Interpreting pulmonary function tests: recognize the pattern, and the diagnosis will follow. , 2003, Cleveland Clinic journal of medicine.

[6]  J. Truwit,et al.  Pulmonary edema Kyphoscoliosis Pulmonary fibrosis Fibrothorax Acute respiratory distress syndrome Pectus excavatum Langerhans cell histiocytosis Chest wall tumor Hypersensitivity pneumonitis Paralysis Connective tissue disorders Scleroderma Sarcoidosis , 2005 .

[7]  K. Gabriel,et al.  The biplot graphic display of matrices with application to principal component analysis , 1971 .

[8]  Swaminathan Ramakrishnan,et al.  Prediction of Forced Expiratory Volume in Pulmonary Function Test using Radial Basis Neural Networks and k-means Clustering , 2009, Journal of Medical Systems.

[9]  R O Crapo,et al.  Pulmonary-function testing. , 1994, The New England journal of medicine.

[10]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[11]  George-Christopher Vosniakos,et al.  Optimizing feedforward artificial neural network architecture , 2007, Eng. Appl. Artif. Intell..

[12]  F. Salaffi,et al.  The Differing Patterns of Subclinical Pulmonary Involvement in Connective Tissue Diseases as Shown by Application of Factor Analysis , 2000, Clinical Rheumatology.

[13]  T. Barreiro,et al.  An approach to interpreting spirometry. , 2004, American family physician.

[14]  F. Salaffi,et al.  Urticaria as a Presenting Manifestation of Adult-Onset Still’s Disease , 2000, Clinical Rheumatology.

[15]  José Ferrer,et al.  Using SOM and PCA for analysing and interpreting data from a P-removal SBR , 2008, Eng. Appl. Artif. Intell..

[16]  R. Giuliani,et al.  Assessment of respiratory system mechanics by artificial neural networks: an exploratory study. , 2001, Journal of applied physiology.

[17]  A. Leung,et al.  Composite spirometric-computed tomography outcome measure in early cystic fibrosis lung disease. , 2003, American journal of respiratory and critical care medicine.

[18]  S. Ramakrishnan,et al.  EXPERIMENTAL ANALYSIS ON HUMAN RESPIRATORY DYNAMICS USING FLOW-VOLUME SPIROMETRY AND COMBINED NEURAL NETWORKS , 2008 .

[19]  M. M. Wong,et al.  Optical properties of undoped and modulation-doped AlGaN/GaN single heterostructures grown by metalorganic chemical vapor deposition , 2001 .

[20]  P. Carnevali,et al.  Principal component analysis of chest wall movement in selected pathologies , 1998, Medical and Biological Engineering and Computing.

[21]  C. Jenkins,et al.  Traditional and patient-centred outcomes with three classes of asthma medication , 2005, European Respiratory Journal.

[22]  Igor Burstyn,et al.  Principal component analysis is a powerful instrument in occupational hygiene inquiries. , 2004, The Annals of occupational hygiene.

[23]  N. Wagner,et al.  Using spirometry results in occupational medicine and research: Common errors and good practice in statistical analysis and reporting , 2006 .

[24]  Ulmer Wt.  Lung function--clinical importance, problems, and new results. , 2003 .

[25]  Rakesh Kumar Sinha,et al.  Artificial Neural Network and Wavelet Based Automated Detection of Sleep Spindles, REM Sleep and Wake States , 2008, Journal of Medical Systems.

[26]  J. Hankinson,et al.  Standardisation of spirometry , 2005, European Respiratory Journal.

[27]  P. Zagrodzki,et al.  Pattern recognition methods in evaluation of the structure of the laboratory data biominerals, antioxidant enzymes, selected biochemical parameters, and pulmonary function of welders , 2007, Biological Trace Element Research.

[28]  R. Pierce,et al.  Spirometry: an essential clinical measurement. , 2005, Australian family physician.

[29]  Gi-Nam Wang,et al.  Predicting Extrusion Process Parameters Using Neural Networks , 2007 .

[30]  G. Efremidis,et al.  Lung function measurements in traditional bakers. , 2008, Acta bio-medica : Atenei Parmensis.

[31]  Paulo J. G. Lisboa,et al.  Artificial Neural Networks in Biomedicine , 2000, Perspectives in Neural Computing.