Skip to Main content Skip to Navigation
New interface
Conference papers

Spirometry-based airways disease simulation and recognition using Machine Learning approaches

Riccardo Di Dio 1, 2 André Galligo 1, 2 Angelos Mantzaflaris 1, 2 Benjamin Mauroy 2 
1 AROMATH - AlgebRe, geOmetrie, Modelisation et AlgoriTHmes
CRISAM - Inria Sophia Antipolis - Méditerranée , NKUA - National and Kapodistrian University of Athens
Abstract : The purpose of this study is to provide means to physicians for automated and fast recognition of airways diseases. In this work, we mainly focus on measures that can be easily recorded using a spirometer. The signals used in this framework are simulated using the linear bi-compartment model of the lungs. This allows us to simulate ventilation under the hypothesis of ventilation at rest (tidal breathing). By changing the resistive and elastic parameters, data samples are realized simulating healthy, fibrosis and asthma breathing. On this synthetic data, different machine learning models are tested and their performance is assessed. All but the Naive bias classifier show accuracy of at least 99%. This represents a proof of concept that Machine Learning can accurately differentiate diseases based on manufactured spirometry data. This paves the way for further developments on the topic, notably testing the model on real data.
Complete list of metadata
Contributor : Angelos Mantzaflaris Connect in order to contact the contributor
Submitted on : Friday, November 5, 2021 - 9:40:49 AM
Last modification on : Thursday, February 17, 2022 - 4:03:57 PM


Files produced by the author(s)



Riccardo Di Dio, André Galligo, Angelos Mantzaflaris, Benjamin Mauroy. Spirometry-based airways disease simulation and recognition using Machine Learning approaches. LION 2021 - 15th Learning and Intelligent Optimization Conference, Jun 2021, Athens, Greece. pp.98-112, ⟨10.1007/978-3-030-92121-7_8⟩. ⟨hal-03326950v2⟩



Record views


Files downloads