Blood Oxygen, Sleep Disordered Breathing, and Respiratory Instability in Patients With Chronic Heart Failure - PROST Subanalysis

A Real-Time Respiration Monitoring and Classification System Using a Depth Camera and Radars

Respiration rate (RR) and respiration patterns (RP) are considered early indicators of physiological conditions and cardiorespiratory diseases. In this study, we addressed the problem of contactless estimation of RR and classification of RP of one person or two persons in a confined space under realistic conditions. We used three impulse radio ultrawideband (IR-UWB) radars and a 3D depth camera (Kinect) to avoid any blind spot in the room and to ensure that at least one of the radars covers the monitored subjects. This article proposes a subject localization and radar selection algorithm using a Kinect camera to allow the measurement of the respiration of multiple people placed at random locations. Several different experiments were conducted to verify the algorithms proposed in this work. The mean absolute error (MAE) between the estimated RR and reference RR of one-subject and two-subjects RR estimation are 0.61±0.53 breaths/min and 0.68±0.24 breaths/min, respectively. A respiratory pattern classification algorithm combining feature-based random forest classifier and pattern discrimination algorithm was developed to classify different respiration patterns including eupnea, Cheyne-Stokes respiration, Kussmaul respiration and apnea. The overall classification accuracy of 90% was achieved on a test dataset. Finally, a real-time system showing RR and RP classification on a graphical user interface (GUI) was implemented for monitoring two subjects.

Changes in lung to finger circulation time measured via cardiopulmonary polygraphy in patients with varying types of heart disease

Cardiopulmonary polygraphy (PG) demonstrates not only parameters for sleep disordered breathing (SDB) but also hemodynamics. We previously developed a software that detects lung to fingertip circulation time (LFCT) derived from PG dataset and reported that those LFCT reflected the cardiac output. The purpose of this study is to investigate how the LFCT changes during clinical course and whether reflects the impact of in-hospital treatment on cardiac function. Consecutive patients (N = 89) who admitted to the cardiovascular division, underwent PG at the early and late phase of admission. Parameters for SDB and LFCT were compared between an acute decompensated heart failure (ADHF) group (n = 51) and non-ADHF group (n = 38). ADHF group was further divided into subgroups: preserved ejection fraction (pEF) (EF > 40%) and reduced EF (rEF) (EF ≤ 40%). Using our original algorithm, we obtained LFCT values from all of the patients, though 29.4% of ADHF and 44.7% of non-ADHF had no or mild SDB. LFCT significantly shortened in the ADHF-rEF group, in contrast to ADHF-pEF group or non-ADHF group (ADHF-rEF group: 26.9 ± 7.6 to 24.2 ± 6.1 s, p = 0.01; ADHF-pEF group: 25.3 ± 7.3 to 25.3 ± 6.9 s, p = 0.98; non-ADHF group: 21.5 ± 5.5 to 21.9 ± 5.0 s, p = 0.65). The respiratory disorder index in the ADHF group improved after treatment, irrespective of EF (pEF: 26.9 ± 16.1 to 15.8 ± 11.9/h, p < 0.01; rEF: 27.0 ± 16.5 to 20.7 ± 13.6/h, p = 0.03). Automatic detection of LFCT was feasible in almost all cardiac patients. LFCT value changed according to the heart failure treatment in ADHF-rEF patients and reflected cardiac function. LFCT might be a useful indicator of effective cardiac disease treatment.