Feasibility Study of Forced Oscillometry in the Prediction of Chronic Respiratory Diseases Using Machine Learning Approaches

What this Trial Is About

Researchers are evaluating the use of machine learning methods to predict patterns of chronic respiratory diseases like asthma and COPD. This observational study focuses on how clinical information combined with pulmonary function tests can help identify different respiratory disease patterns. The study aims to improve the interpretation of lung function using advanced mathematical algorithms applied to oscillometry data. The study compares the results of impulse oscillometry, a technique that measures lung mechanics using sound waves, with traditional spirometry tests. Participants will undergo these lung function tests so researchers can assess and compare the respiratory patterns detected by each method. The machine learning approaches will be evaluated for their ability to recognize patterns associated with various chronic respiratory diseases. Participants will be adults aged 18 to 90 years with confirmed diagnoses of COPD, asthma, or interstitial lung disease and available spirometry data. The main outcome measured is the oscillometric breathing pattern over one year, alongside spirometry results. The study involves reviewing clinical and lung function data to monitor respiratory patterns and aims to gather information about the feasibility of using oscillometry and machine learning for disease prediction. The study is sponsored by Fundació Institut de Recerca de l'Hospital de la Santa Creu i Sant Pau and will run until September 2026.

Oscillometry and Machine Learning Approaches