The main objective of the study is to assess the potential of time-frequency representation and analysis of pulmonary sounds collected with an electronic stethoscope, as part of the routine monitoring of patients with cystic fibrosis, COPD or pulmonary fibrosis.
Secondary objectives The other objectives of this study are : 1. To evaluate the ability to detect changes in lung sounds, following optimization of the time-frequency representation. 2. To evaluate the ability to quantify differences in the severity of the pathological sounds detected using artificial intelligence and a supervised learning method. Conduct of research This is a single-center, non-randomized, open-label study involving 60 male and female patients aged 18 to 65, eligible for a scheduled consultation as part of their usual pathological follow-up (routine care). Lung sound recordings will be made during the same consultation, after obtaining the patient's non-opposition. Recordings will be made using a 3M Littmann© model 3200 electronic stethoscope. The stethoscope works with Eko software, which will be installed on a touch-sensitive tablet or computer, enabling local storage of recorded data. Whatever the patient's pathology, the physician will listen to 10 lung sites defined in the protocol. At least one breath per pulmonary site will be recorded during the consultation. If a patient comes back for a consultation before the end of the recruitment period, a new lung sound recording will be performed.
Study Type
OBSERVATIONAL
Enrollment
23
The lung sound recordings will be made during a consultation scheduled as part of the patient's usual follow-up, after obtaining the patient's non-opposition.
Hôpitaux Universitaire de Strasbourg
Strasbourg, Bas-Rhin, France
GHRMSA - Hôpital Emile Muller
Mulhouse, Haut-Rhin, France
Lung sounds visible in their representation as time-frequency images
Pulmonary sounds will be recorded with an electronic stethoscope at each scheduled visit and processed with artificial intelligence using a supervised learning method.
Time frame: At inclusion
Classification of sounds by severity
Pulmonary sounds will be recorded with an electronic stethoscope at each scheduled visit and processed with artificial intelligence using a supervised learning method.
Time frame: At inclusion
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.