Design and Development of Smartphone-Enabled Spirometer With a Disease Classification System Using Convolutional Neural Network.

Spirometry is one of the most basic of pulmonary function tests, and the measurements of this test, such as forced vital capacity, forced expiratory volume in the first second, and peak expiratory flow, play an important role in the diagnosis of obstructive lung diseases, such as chronic obstructive pulmonary disease and asthma. The lack of point-of-care, primary care, and personalized applications prohibits individuals from monitoring their own lung conditions beyond the hospital visit. This article presents the design and development of a low-cost, portable, smartphone-enabled spirometer with an automatic disease classification system based on the spirometric signal using the convolutional neural network. The classification model was trained using data, stored in the device, and the best model was extracted with an accuracy of 98.98%, which outperforms other classification models, such as long short-term memory network, deep belief network, and stacked autoencoder. The pretrained model has been imported in the smartphone device for real-time classification of spirometry. [ABSTRACT FROM AUTHOR]

Copyright of IEEE Transactions on Instrumentation & Measurement is the property of IEEE and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)