Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/34606
Title: Cardiac Comorbidities in COPD Patients Explained Through HRV Analysis and Respiratory Indices
Authors: Romero, Daniel
Blanco-Almazan, Dolores
Groenendaal, Willemijn
Lijnen, Lien
SMEETS, Christophe 
RUTTENS, David 
Catthoor, Francky
Jane, Raimon
Issue Date: 2020
Publisher: IEEE
Source: 2020 COMPUTING IN CARDIOLOGY, (Art N° 316).
Abstract: Chronic obstructive pulmonary disease (COPD) patients exhibit depressed heart rate variability (HRV), while comorbidities may worsen the patients' prognosis. We investigated whether HRV analyis, clinical markers of disease severity and respiratory function, may explain the presence of cardiac-related comorbidities. Several HRV indices were evaluated in 46 COPD patients before a 6-minute walk test (6MWT). Maximum heart rate (HRmax) and walked distance (Dist) were measured during the test, while heart rate recovery (HRR) was estimated immediately afterwards. All these features and the patient characteristics were used to identify cardiac-related comorbidities (COPDco, n=11). A logistic regression classifier with regularization was used for modeling and feature selection, while model assessment was performed by leave-one-out cross-validation. Only 4 features were needed to accurately identify comorbidities with overall performance metrics AUC=84%, sensitivity=73% specificity=83%. The feature subset included the ratio given by the forced expiratory volume and the forced vital capacity ((FEV1/FVC), the normalized HRR at minute 3, the Borg-scale of exertional dyspnea and the normalized LF power. These features could provide relevant information for early identification of cardiac comorbidities in COPD patients.
Notes: Romero, D (corresponding author), Ave E Maristany 16, Barcelona 08019, Spain.
dromero@ibecbarcelona.eu
Document URI: http://hdl.handle.net/1942/34606
ISBN: 978-1-7281-7382-5
DOI: 10.22489/CinC.2020.316
ISI #: WOS:000657257000044
Category: C1
Type: Proceedings Paper
Validations: ecoom 2022
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
CinC2020316.pdfPublished version172.3 kBAdobe PDFView/Open
Show full item record

WEB OF SCIENCETM
Citations

1
checked on May 1, 2024

Page view(s)

36
checked on Sep 7, 2022

Download(s)

12
checked on Sep 7, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.