Acoustic Feature Extraction and Sparse Representation of Neck Fluid Volume (NFV) in Patients with Obstructive Sleep Apnea (OSA)

Obstructive sleep apnea (OSA) is common in 10% of adults and is associated with increased cardiovascular morbidity and mortality. Furthermore, there is a 3-fold increase in OSA prevalence in fluid retaining patients such as those with heart failure. Evolving evidence suggests that fluid accumulation in the neck could narrow the upper airway (UA), increase its collapsibility, and contribute to OSA worsening. For this reason, we aim to determine whether: analysis of respiratory sounds can be used as a non-invasive technique to estimate neck fluid volume (NFV), respiratory sound analysis could predict variations in NFV due to fluid overloading, and the developed techniques could be used to investigate the role of increased NFV on the pathophysiology of OSA in patients with heart failure. The proposed
algorithms could lead to developing novel acoustic techniques to assess and alleviate the adverse effects of fluid accumulation in the neck on the pathophysiology of OSA.

Faculty Supervisor:

Frank Rudzicz

Student:

Partner:

iDAPT Somno Inc

Discipline:

Computer science

Sector:

Manufacturing

University:

University of Toronto

Program: