Spirometry-based airways disease simulation and recognition using Machine Learning approaches
This provides a proof of concept for physicians to potentially automate disease diagnosis from spirometry, but it is incremental as it uses simulated data and requires validation on real-world cases.
The study tackled automated recognition of airways diseases using spirometry data by simulating healthy, fibrosis, and asthma breathing patterns with a linear bi-compartment model and testing machine learning models, achieving at least 99% accuracy on synthetic data.
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.