Page - 317 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

Estimationof InhalationFlowParameters forAsthmaMonitoringUsingAcoustic ZinebJEDDIa,b,1,MounirGHOGHOa,c andAdamBOHRd JohanPBOTKERd IsmailKASSOUb aInternationalUniversityofRabat,TICLab,Morocco bMohamedVUniversityRabat,Morocco c SchoolofEEE,TheUniversityofLeeds,UK dDepartmentofPharmacy,UniversityofCopenhagen,2100Copenhagen,Denmark Abstract. Asthma is one of themost prevalent diseases. To control this chronic respiratorycondition, inhalerdevices, suchas thedrypowder inhaler (DPI)andthe pressurizedmetered dose inhaler (pMDI), are prescribed. However, poor asthma management can significantly deteriorate the patients’ health and their quality of life in general. Through regular treatment, asthma patients frequently use inhaled medication inorder tohelp improving their respiratory system.Nevertheless, a lot ofpatientsdonot followthe inhalation techniqueas instructed, including incorrect useof the inhalerandunsatisfactorymedicationadherence.Thismayresult inpoor control of asthma and increased risk of asthma attacks. In this study, an innova- tive low-cost solution isproposed tomonitor the inhalationflowrate.Thisconsists of an acoustic add-on device that generates a soundwhen using the inhaler. This sound is correlated to the flow rate of the inhalation. The generated sound signal is capturedbya smart phoneand its features are extracted inorder to estimatepa- rameters such as the inspiratory flow rate (IFR), inspiratory volume over the first second (FIV1), total inspiratory lung volume or the inhalation capacity (IC) and other relevant inhalation parameters. Prior to feature extraction, the signal is first passed throughabandpassFIRfilter, and then the inhalationsegmentsaredetected using aBayesian sequential detection algorithm.The energy of the pre-processed signal is then used to estimate the inhalation parameters using linear regression. Theproposedmethod is showntohavegoodperformance (e.g. for IFRestimation: (R2=99%, p-value<0.0001). Keywords. Asthma, inhalation, acoustic signal, Add-on device, DPI inhalers, inspiratoryflowrate, inspiratorycapacity,FIV1. 1. Introduction Asthma is a common chronic disease that occurs in 1 to 18%of the population in dif- ferent countriesall over theworld. It is estimated thatmore than300millionpeople suf- 1Corresponding Author: Zineb Jeddi, International University of Rabat, TICLab, Morocco /Mohamed V University,Rabat,Morocco;E-mail: zineb.jeddi@uir.ac.ma SignalProcessingandMachineLearning Intelligent Environments 2019 A. Muñoz et al. (Eds.) © 2019 The authors and IOS Press. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0). doi:10.3233/AISE190059 317