Evaluating Cardiac Impairment From Abnormal Respiratory Patterns: Insights From a Wireless Radar and Deep Learning...

Area of Science:

• Cardiology
• Sleep Medicine
• Biomedical Engineering

Background:

• The bidirectional relationship between heart function impairment and sleep-disordered breathing (SDB) is not fully understood.
• Echocardiography (2D-echo) is a key tool for assessing cardiac function, particularly left ventricular ejection fraction (LVEF).
• Wireless radar technology offers a non-contact method for monitoring physiological signals like respiration.

Purpose of the Study:

• To investigate the association between respiratory patterns detected by a wireless radar system and echocardiographic measurements of cardiac function.
• To explore how SDB indices relate to LVEF and the risk of heart failure progression.

Main Methods:

• Respiratory patterns were captured using a wireless radar framework in patients undergoing 2D-echo.
• Key SDB indices, including the respiratory disturbance index (RDI) and periodic breathing (PB) cycle length, were derived.
• Data were analyzed using regression models to determine the relationship between SDB indices and LVEF, with patients stratified by an LVEF of 50%.

Main Results:

• Patients with LVEF ≤50% exhibited significantly higher RDI and longer PB cycle lengths compared to those with LVEF >50%.
• Each unit increase in RDI was associated with a 0.22% decrease in LVEF, and each second increase in PB cycle length correlated with a 0.21% LVEF reduction.
• Elevated RDI and PB cycle length increased the risk of LVEF declining below 50% and were linked to higher NT-proBNP levels.

Conclusions:

• A wireless radar system, coupled with deep learning, effectively monitors respiratory patterns linked to cardiac function.
• The contactless nature of radar technology facilitates continuous assessment of cardiac function and SDB.
• This approach holds promise for integrated, long-term management of cardiac conditions and sleep disorders.