Acoustic features are independently associated with heart failure and pulmonary hypertension

Abstract Introduction Acoustic analysis of speech has discriminated decompensated acute heart failure (HF). Speech rate (SR) and cepstral peak prominence (CPP) variation are among features previously evaluated. However, the association between SR and CPP and chronic stable HF with and without pulmon...

Full description

Saved in:
Bibliographic Details
Main Authors: Jaskanwal Deep S. Sara, Keiko Ishikawa, Yan Li, D.M. Anisuzzaman, Lilach O. Lerman, Amir Lerman, Diana Orbelo
Format: Article
Language:English
Published: Wiley 2025-08-01
Series:ESC Heart Failure
Subjects:
Online Access:https://doi.org/10.1002/ehf2.15309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849407225881165824
author Jaskanwal Deep S. Sara
Keiko Ishikawa
Yan Li
D.M. Anisuzzaman
Lilach O. Lerman
Amir Lerman
Diana Orbelo
author_facet Jaskanwal Deep S. Sara
Keiko Ishikawa
Yan Li
D.M. Anisuzzaman
Lilach O. Lerman
Amir Lerman
Diana Orbelo
author_sort Jaskanwal Deep S. Sara
collection DOAJ
description Abstract Introduction Acoustic analysis of speech has discriminated decompensated acute heart failure (HF). Speech rate (SR) and cepstral peak prominence (CPP) variation are among features previously evaluated. However, the association between SR and CPP and chronic stable HF with and without pulmonary hypertension (PH) as well as PH alone have not been previously studied. Methods Patients evaluated for HF and/or PH in the outpatient setting recorded a standardized text read out loud from which a sentence was extracted and analysed to extract pre‐specified acoustic features including SR and CPP calculated for voiced speech (CPP‐V) and in all speech (CPP‐All). Patients were grouped depending on the presence or absence of disease (HF and/or PH) and symptoms. Linear regression models were fitted to determine the association between each acoustic feature and disease status. Results In total, 2153 patients were included: age 65.32 ± 17.18 years; male n = 1246 (57.9%); 879 had HF (40.8%), 542 had PH (25.2%) and 777 had no disease and no symptoms (36.1%). After adjustment for age and sex, SR was significantly lower in patients with PH only [estimated coefficient, 95% confidence interval (CI): −0.14, −0.21 to −0.06, P = 0.0006], HF only (−0.11, −0.17 to −0.05, P = 0.0002) and HF with PH (−0.17, −0.24 to −0.10, P < 0.0001) compared with no disease. CPP‐V differed in patients with PH only (0.37, 0.16–0.57, P = 0.0004) and CPP‐All differed significantly compared with patients without disease (0.23, 0.08–0.38, P = 0.0025). Conclusions SR is significantly slower in patients with HF alone, PH alone and HF and PH combined compared with patients without disease. CPP also differs significantly in patients with PH compared with controls. These findings suggest that acoustic analysis may be useful in discriminating chronic stable HF and PH, offering promise for the development of non‐invasive screening methods for HF and PH.
format Article
id doaj-art-5257bb44dbfa489e8cca1cb131f631db
institution Kabale University
issn 2055-5822
language English
publishDate 2025-08-01
publisher Wiley
record_format Article
series ESC Heart Failure
spelling doaj-art-5257bb44dbfa489e8cca1cb131f631db2025-08-20T03:36:08ZengWileyESC Heart Failure2055-58222025-08-011242946295710.1002/ehf2.15309Acoustic features are independently associated with heart failure and pulmonary hypertensionJaskanwal Deep S. Sara0Keiko Ishikawa1Yan Li2D.M. Anisuzzaman3Lilach O. Lerman4Amir Lerman5Diana Orbelo6Department of Cardiovascular Medicine Mayo College of Medicine Rochester Minnesota USADepartment of Communication Sciences and Disorders University of Kentucky Lexington Kentucky USADepartment of Biostatistics Mayo Clinic Rochester Minnesota USADepartment of Cardiovascular Medicine Mayo College of Medicine Rochester Minnesota USADivision of Nephrology and Hypertension Mayo Clinic Rochester Minnesota USADepartment of Cardiovascular Medicine Mayo College of Medicine Rochester Minnesota USADivision of Laryngology Mayo Clinic College of Medicine Rochester Minnesota USAAbstract Introduction Acoustic analysis of speech has discriminated decompensated acute heart failure (HF). Speech rate (SR) and cepstral peak prominence (CPP) variation are among features previously evaluated. However, the association between SR and CPP and chronic stable HF with and without pulmonary hypertension (PH) as well as PH alone have not been previously studied. Methods Patients evaluated for HF and/or PH in the outpatient setting recorded a standardized text read out loud from which a sentence was extracted and analysed to extract pre‐specified acoustic features including SR and CPP calculated for voiced speech (CPP‐V) and in all speech (CPP‐All). Patients were grouped depending on the presence or absence of disease (HF and/or PH) and symptoms. Linear regression models were fitted to determine the association between each acoustic feature and disease status. Results In total, 2153 patients were included: age 65.32 ± 17.18 years; male n = 1246 (57.9%); 879 had HF (40.8%), 542 had PH (25.2%) and 777 had no disease and no symptoms (36.1%). After adjustment for age and sex, SR was significantly lower in patients with PH only [estimated coefficient, 95% confidence interval (CI): −0.14, −0.21 to −0.06, P = 0.0006], HF only (−0.11, −0.17 to −0.05, P = 0.0002) and HF with PH (−0.17, −0.24 to −0.10, P < 0.0001) compared with no disease. CPP‐V differed in patients with PH only (0.37, 0.16–0.57, P = 0.0004) and CPP‐All differed significantly compared with patients without disease (0.23, 0.08–0.38, P = 0.0025). Conclusions SR is significantly slower in patients with HF alone, PH alone and HF and PH combined compared with patients without disease. CPP also differs significantly in patients with PH compared with controls. These findings suggest that acoustic analysis may be useful in discriminating chronic stable HF and PH, offering promise for the development of non‐invasive screening methods for HF and PH.https://doi.org/10.1002/ehf2.15309acoustic analysisatherosclerosisbiomarkerscardiovascular diseasetelemedicinevoice features
spellingShingle Jaskanwal Deep S. Sara
Keiko Ishikawa
Yan Li
D.M. Anisuzzaman
Lilach O. Lerman
Amir Lerman
Diana Orbelo
Acoustic features are independently associated with heart failure and pulmonary hypertension
ESC Heart Failure
acoustic analysis
atherosclerosis
biomarkers
cardiovascular disease
telemedicine
voice features
title Acoustic features are independently associated with heart failure and pulmonary hypertension
title_full Acoustic features are independently associated with heart failure and pulmonary hypertension
title_fullStr Acoustic features are independently associated with heart failure and pulmonary hypertension
title_full_unstemmed Acoustic features are independently associated with heart failure and pulmonary hypertension
title_short Acoustic features are independently associated with heart failure and pulmonary hypertension
title_sort acoustic features are independently associated with heart failure and pulmonary hypertension
topic acoustic analysis
atherosclerosis
biomarkers
cardiovascular disease
telemedicine
voice features
url https://doi.org/10.1002/ehf2.15309
work_keys_str_mv AT jaskanwaldeepssara acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension
AT keikoishikawa acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension
AT yanli acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension
AT dmanisuzzaman acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension
AT lilacholerman acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension
AT amirlerman acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension
AT dianaorbelo acousticfeaturesareindependentlyassociatedwithheartfailureandpulmonaryhypertension