Abstract
Spirometry is the most commonly used test of lung function because the forced expiratory flow-volume (FV) curve is effort-independent and simultaneously sensitive to pathological processes in the lungs. Despite this, a method for the estimation of respiratory system parameters, based on this association, has not been yet proposed. The aim of this work was to explore a feedforward neural network (FFNN) approximating the inverse mapping between the FV curve and respiratory parameters. To this end, the sensitivity analysis of the reduced model for forced expiration has been carried out, showing its local identifiability and the importance of particular parameters. This forward model was then applied to simulate spirometric data (8000 elements), used for training, validating, optimizing and testing the FFNN. The suboptimal FFNN structure had 52 input neurons (for spirometric data), two hidden nonlinear layers with 30 and 20 neurons respectively, and 10 output neurons (for parameter estimates). The total relative error of estimation of individual parameters was between 11 and 28%. Parameter estimates yielded by this inverse FFNN will be used as starting points for a more precise local estimation algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pellegrino, R., Viegi, G., Brusasco, V., et al.: Interpretative strategies for lung function tests. Eur. Respir. J. 26(5), 948–968 (2005)
Lambert, R.K., Wilson, T.A., Hyatt, R.E., Rodarte, J.R.: A computational model for expiratory flow. J. Appl. Physiol. Respir. Environ. Exerc. Physiol. 52(1), 44–56 (1982)
Polak, A.G.: A forward model for maximum expiration. Comput. Biol. Med. 28(6), 613–625 (1998)
Polak, A.G., Lutchen, K.R.: Computational model for forced expiration from asymmetric normal lungs. Ann. Biomed. Eng. 31(8), 891–907 (2003)
Hedges, K.L., Tawhai, M.H.: Simulation of forced expiration in a biophysical model with homogeneous and clustered bronchoconstriction. J. Biomech. Eng. 138(6), 061008 (2016)
Polak, A.G., Wysoczański, D., Mroczka, J.: In silico study on the impact of heterogeneous narrowing of small airways on spirometry results. Eur. Respir. J. 50(suppl. 61), PA3008 (2017)
Lambert, R.K.: Sensitivity and specificity of the computational model for maximal expiratory flow. J. Appl. Physiol. Respir. Environ. Exerc. Physiol. 57(4), 958–970 (1984)
Lambert, R.K., Castile, R.G., Tepper, R.S.: Model of forced expiratory flows and airway geometry in infants. J. Appl. Physiol. 96(2), 688–692 (2004)
Lambert, R.K., Beck, K.C.: Airway area distribution from the forced expiration maneuver. J. Appl. Physiol. 97(2), 570–578 (2004)
Morlion, B., Polak, A.G.: Simulation of lung function evolution after heart-lung transplantation using a numerical model. IEEE Trans. Biomed. Eng. 52(7), 1180–1187 (2005)
Mroczka, J., Polak, A.G.: Reduced model for forced expiration and analysis of its sensitivity. In: Feng, D.D., Dubois, O., Zaytoon, J., Carson, E. (eds.) Modelling and Control in Biomedical Systems 2006 (Including Biological Systems), pp. 159–164. Elsevier, Oxford (2006)
Mroczka, J., Polak, A.G.: Selection of identifiable parameters from the reduced model for forced expiration. In: Magjarevic, R., Nagel, J.H. (eds.) World Congress on Medical Physics and Biomedical Engineering. IFMBE Proceedings, vol. 14, pp. 764–768. Springer, Berlin (2006). https://doi.org/10.1007/978-3-540-36841-0_180
Tikhonov, A.N., Goncharsky, A., Stepanov, V.V.: Numerical Methods for the Solution of Ill-Posed Problems. Kluwer, London (1995)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251–257 (1991)
Kůrková, V.: Kolmogorov’s theorem and multilayer neural networks. Neural Netw. 5(3), 501–506 (1992)
Ramuhalli, P., Udpa, L., Udpa, S.S.: Neural network-based inversion algorithms in magnetic flux leakage nondestructive evaluation. J. Appl. Phys. 93(10), 8274–8276 (2003)
Kabir, H., Wang, Y., Yu, M., Zhang, Q.J.: Neural network inverse modeling and applications to microwave filter design. IEEE Trans. Microw. Theory Tech. 56(4), 867–879 (2008)
Weibel, E.R.: Morphometry of the Human Lung. Springer, Berlin (1963). https://doi.org/10.1007/978-3-642-87553-3
Bogaard, J.M., Overbeek, S.E., Verbraak, A.F.M., et al.: Pressure-volume analysis of the lung with an exponential and linear-exponential model in asthma and COPD. Eur. Respir. J. 8(9), 1525–1531 (1995)
Kim, D., Son, J.S., Ko, S., Jeong, W., Lim, H.: Measurements of the length and diameter of main bronchi on three-dimensional images in Asian adult patients in comparison with the height of patients. J. Cardiothorac. Vasc. Anesth. 28(4), 890–895 (2014)
Canals, M., Novoa, F.F., Rosenmann, M.: A simple geometrical pattern for the branching distribution of the bronchial tree, useful to estimate optimality departures. Acta. Biotheor. 52(1), 1–16 (2004)
Hannallah, M.S., Benumof, J.L., Ruttimann, U.E.: The relationship between left mainstem bronchial diameter and patient size. J. Cardiothorac. Vasc. Anesth. 9(2), 119–121 (1995)
Majumdar, A., et al.: Relating airway diameter distributions to regular branching asymmetry in the lung. Phys. Rev. Lett. 95(16), 168101 (2005)
Brown, R.H., Mitzner, W.: Effect of lung inflation and airway muscle tone on airway diameter in vivo. J. Appl. Physiol. 80(5), 1581–1588 (1996)
Baldi, S., Miniati, M., Bellina, C.R., et al.: Relationship between extent of pulmonary emphysema by high-resolution computed tomography and lung elastic recoil in patients with chronic obstructive pulmonary disease. Am. J. Respir. Crit. Care Med. 164(4), 585–589 (2001)
Thomaseth, K., Cobelli, C.: Generalized sensitivity functions in physiological system identification. Ann. Biomed. Eng. 27(5), 607–616 (1999)
Polak, A.G.: Indirect measurements: combining parameter selection with ridge regression. Meas. Sci. Technol. 12(3), 278–287 (2001)
Quanjer, P.H., Tammeling, G.J., Cotes, J.E., et al.: Lung volumes and forced ventilatory flows. Eur. Respir. J. 6(suppl 16), 5–40 (1993)
Dötsch, H.G., Van den Hof, P.M.: Test for local structural identifiability of high-order non-linearly parametrized state space models. Automatica 32(6), 875–883 (1996)
Acknowledgments
This work was supported by the grant no. 2016/21/B/ST7/02233 from the National Science Centre, Poland.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Polak, A.G., Wysoczański, D., Mroczka, J. (2019). Estimation of Lung Properties Using ANN-Based Inverse Modeling of Spirometric Data. In: Rojas, I., Valenzuela, O., Rojas, F., Ortuño, F. (eds) Bioinformatics and Biomedical Engineering. IWBBIO 2019. Lecture Notes in Computer Science(), vol 11466. Springer, Cham. https://doi.org/10.1007/978-3-030-17935-9_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-17935-9_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-17934-2
Online ISBN: 978-3-030-17935-9
eBook Packages: Computer ScienceComputer Science (R0)