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

TL;DR

This study demonstrates that machine learning models can accurately classify airways diseases using simulated spirometry data, offering a potential tool for rapid, automated diagnosis in clinical settings.

Contribution

It introduces a simulation-based framework for disease recognition using machine learning on spirometry data, highlighting high classification accuracy on synthetic datasets.

Findings

All models except Naive bias achieved over 99% accuracy.

Simulation effectively differentiates healthy, fibrosis, and asthma breathing patterns.

Proof of concept for machine learning-based airways disease detection.

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.