NCT07447596

Oscillometry and Machine Learning Approaches

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

• Status: Recruiting
• Phase: —
• Study type: Observational
• Enrollment: 50 (estimated)
• Sponsor: Fundació Institut de Recerca de l'Hospital de la Santa Creu i Sant Pau · Academic / Other
• Sex: All
• Age: 18 Years – 99 Years
• Healthy volunteers: Accepted

Summary

Unicentric retrospective study designed to analyses the performance of various machine learning approaches to predict patterns of chronic respiratory diseases such as asthma, based mainly on clinical information and respiratory spirometry/oscillometry.

Detailed description

Impulse oscillometry is a technique that allows evaluation of pulmonary mechanics through the application of sound waves of different frequencies, collecting the oscillations produced in the patient in response. The use of mathematical algorithms in the interpretation of oscillometry improves the evaluation of pulmonary function. The aim of the present study is to evaluate machine learning approaches to recognize respiratory patterns of different diseases.

Conditions

• Asthma COPD

Interventions

Type	Name	Description
OTHER	1	Compare oscillometry results with spirometryClick to apply

Timeline

• Start date: 2025-10-15
• Primary completion: 2026-07-15
• Completion: 2026-09-01
• First posted: 2026-03-03
• Last updated: 2026-03-03

Locations

1 site across 1 country: Spain