Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals

Masatake Kobayashi; Olivier Huttin; Martin Magnusson; João Pedro Ferreira; Erwan Bozec; Anne-Cecile Huby; Gregoire Preud'homme; Kevin Duarte; Zohra Lamiral; Kevin Dalleau; Emmanuel Bresso; Malika Smaïl-Tabbone; Marie-Dominique Devignes; Peter M Nilsson; Margret Leosdottir; Jean-Marc Boivin; Faiez Zannad; Patrick Rossignol; Nicolas Girerd; STANISLAS study

doi:10.1016/j.jcmg.2021.07.004

Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals

Masatake Kobayashi, Olivier Huttin, Martin Magnusson, João Pedro Ferreira, Erwan Bozec, Anne-Cecile Huby, Gregoire Preud'homme, Kevin Duarte, Zohra Lamiral, Kevin Dalleau, Emmanuel Bresso, Malika Smaïl-Tabbone, Marie-Dominique Devignes, Peter M Nilsson, Margret Leosdottir, Jean-Marc Boivin, Faiez Zannad, Patrick Rossignol, Nicolas Girerd, STANISLAS study

Research output: Contribution to journal › Article › peer-review

Abstract

OBJECTIVES: This study sought to identify homogenous echocardiographic phenotypes in community-based cohorts and assess their association with outcomes.

BACKGROUND: Asymptomatic cardiac dysfunction leads to a high risk of long-term cardiovascular morbidity and mortality; however, better echocardiographic classification of asymptomatic individuals remains a challenge.

METHODS: Echocardiographic phenotypes were identified using K-means clustering in the first generation of the STANISLAS (Yearly non-invasive follow-up of Health status of Lorraine insured inhabitants) cohort (N = 827; mean age: 60 ± 5 years; men: 48%), and their associations with vascular function and circulating biomarkers were also assessed. These phenotypes were externally validated in the Malmö Preventive Project cohort (N = 1,394; mean age: 67 ± 6 years; men: 70%), and their associations with the composite of cardiovascular mortality (CVM) or heart failure hospitalization (HFH) were assessed as well.

RESULTS: Three echocardiographic phenotypes were identified as "mostly normal (MN)" (n = 334), "diastolic changes (D)" (n = 323), and "diastolic changes with structural remodeling (D/S)" (n = 170). The D and D/S phenotypes had similar ages, body mass indices, cardiovascular risk factors, vascular impairments, and diastolic function changes. The D phenotype consisted mainly of women and featured increased levels of inflammatory biomarkers, whereas the D/S phenotype, consisted predominantly of men, displayed the highest values of left ventricular mass, volume, and remodeling biomarkers. The phenotypes were predicted based on a simple algorithm including e', left ventricular mass and volume (e'VM algorithm). In the Malmö cohort, subgroups derived from e'VM algorithm were significantly associated with a higher risk of CVM and HFH (adjusted HR in the D phenotype = 1.87; 95% CI: 1.04 to 3.37; adjusted HR in the D/S phenotype = 3.02; 95% CI: 1.71 to 5.34).

CONCLUSIONS: Among asymptomatic, middle-aged individuals, echocardiographic data-driven classification based on the simple e'VM algorithm identified profiles with different long-term HF risk. (4th Visit at 17 Years of Cohort STANISLAS-Stanislas Ancillary Study ESCIF [STANISLASV4]; NCT01391442).

Original language	English
Pages (from-to)	193-208
Journal	JACC: Cardiovascular Imaging
Volume	15
Issue number	2
Early online date	2021 Sept 15
DOIs	https://doi.org/10.1016/j.jcmg.2021.07.004
Publication status	Published - 2022

Subject classification (UKÄ)

Cardiac and Cardiovascular Systems

Access to Document

10.1016/j.jcmg.2021.07.004Licence: CC BY-NC-ND

Cite this

Kobayashi, M., Huttin, O., Magnusson, M., Ferreira, J. P., Bozec, E., Huby, A.-C., Preud'homme, G., Duarte, K., Lamiral, Z., Dalleau, K., Bresso, E., Smaïl-Tabbone, M., Devignes, M.-D., Nilsson, P. M., Leosdottir, M., Boivin, J.-M., Zannad, F., Rossignol, P., Girerd, N., & STANISLAS study (2022). Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals. JACC: Cardiovascular Imaging, 15(2), 193-208. https://doi.org/10.1016/j.jcmg.2021.07.004

@article{b3894f900c70470da1eb53e8cd1e5049,

title = "Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals",

abstract = "OBJECTIVES: This study sought to identify homogenous echocardiographic phenotypes in community-based cohorts and assess their association with outcomes.BACKGROUND: Asymptomatic cardiac dysfunction leads to a high risk of long-term cardiovascular morbidity and mortality; however, better echocardiographic classification of asymptomatic individuals remains a challenge.METHODS: Echocardiographic phenotypes were identified using K-means clustering in the first generation of the STANISLAS (Yearly non-invasive follow-up of Health status of Lorraine insured inhabitants) cohort (N = 827; mean age: 60 ± 5 years; men: 48%), and their associations with vascular function and circulating biomarkers were also assessed. These phenotypes were externally validated in the Malm{\"o} Preventive Project cohort (N = 1,394; mean age: 67 ± 6 years; men: 70%), and their associations with the composite of cardiovascular mortality (CVM) or heart failure hospitalization (HFH) were assessed as well.RESULTS: Three echocardiographic phenotypes were identified as {"}mostly normal (MN){"} (n = 334), {"}diastolic changes (D){"} (n = 323), and {"}diastolic changes with structural remodeling (D/S){"} (n = 170). The D and D/S phenotypes had similar ages, body mass indices, cardiovascular risk factors, vascular impairments, and diastolic function changes. The D phenotype consisted mainly of women and featured increased levels of inflammatory biomarkers, whereas the D/S phenotype, consisted predominantly of men, displayed the highest values of left ventricular mass, volume, and remodeling biomarkers. The phenotypes were predicted based on a simple algorithm including e', left ventricular mass and volume (e'VM algorithm). In the Malm{\"o} cohort, subgroups derived from e'VM algorithm were significantly associated with a higher risk of CVM and HFH (adjusted HR in the D phenotype = 1.87; 95% CI: 1.04 to 3.37; adjusted HR in the D/S phenotype = 3.02; 95% CI: 1.71 to 5.34).CONCLUSIONS: Among asymptomatic, middle-aged individuals, echocardiographic data-driven classification based on the simple e'VM algorithm identified profiles with different long-term HF risk. (4th Visit at 17 Years of Cohort STANISLAS-Stanislas Ancillary Study ESCIF [STANISLASV4]; NCT01391442).",

author = "Masatake Kobayashi and Olivier Huttin and Martin Magnusson and Ferreira, {Jo{\~a}o Pedro} and Erwan Bozec and Anne-Cecile Huby and Gregoire Preud'homme and Kevin Duarte and Zohra Lamiral and Kevin Dalleau and Emmanuel Bresso and Malika Sma{\"i}l-Tabbone and Marie-Dominique Devignes and Nilsson, {Peter M} and Margret Leosdottir and Jean-Marc Boivin and Faiez Zannad and Patrick Rossignol and Nicolas Girerd and {STANISLAS study}",

year = "2022",

doi = "10.1016/j.jcmg.2021.07.004",

language = "English",

volume = "15",

pages = "193--208",

journal = "JACC: Cardiovascular Imaging",

issn = "1876-7591",

publisher = "Elsevier",

number = "2",

}

Kobayashi, M, Huttin, O, Magnusson, M, Ferreira, JP, Bozec, E, Huby, A-C, Preud'homme, G, Duarte, K, Lamiral, Z, Dalleau, K, Bresso, E, Smaïl-Tabbone, M, Devignes, M-D, Nilsson, PM , Leosdottir, M, Boivin, J-M, Zannad, F, Rossignol, P, Girerd, N & STANISLAS study 2022, 'Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals', JACC: Cardiovascular Imaging, vol. 15, no. 2, pp. 193-208. https://doi.org/10.1016/j.jcmg.2021.07.004

TY - JOUR

T1 - Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals

AU - Kobayashi, Masatake

AU - Huttin, Olivier

AU - Magnusson, Martin

AU - Ferreira, João Pedro

AU - Bozec, Erwan

AU - Huby, Anne-Cecile

AU - Preud'homme, Gregoire

AU - Duarte, Kevin

AU - Lamiral, Zohra

AU - Dalleau, Kevin

AU - Bresso, Emmanuel

AU - Smaïl-Tabbone, Malika

AU - Devignes, Marie-Dominique

AU - Nilsson, Peter M

AU - Leosdottir, Margret

AU - Boivin, Jean-Marc

AU - Zannad, Faiez

AU - Rossignol, Patrick

AU - Girerd, Nicolas

AU - STANISLAS study

PY - 2022

Y1 - 2022

N2 - OBJECTIVES: This study sought to identify homogenous echocardiographic phenotypes in community-based cohorts and assess their association with outcomes.BACKGROUND: Asymptomatic cardiac dysfunction leads to a high risk of long-term cardiovascular morbidity and mortality; however, better echocardiographic classification of asymptomatic individuals remains a challenge.METHODS: Echocardiographic phenotypes were identified using K-means clustering in the first generation of the STANISLAS (Yearly non-invasive follow-up of Health status of Lorraine insured inhabitants) cohort (N = 827; mean age: 60 ± 5 years; men: 48%), and their associations with vascular function and circulating biomarkers were also assessed. These phenotypes were externally validated in the Malmö Preventive Project cohort (N = 1,394; mean age: 67 ± 6 years; men: 70%), and their associations with the composite of cardiovascular mortality (CVM) or heart failure hospitalization (HFH) were assessed as well.RESULTS: Three echocardiographic phenotypes were identified as "mostly normal (MN)" (n = 334), "diastolic changes (D)" (n = 323), and "diastolic changes with structural remodeling (D/S)" (n = 170). The D and D/S phenotypes had similar ages, body mass indices, cardiovascular risk factors, vascular impairments, and diastolic function changes. The D phenotype consisted mainly of women and featured increased levels of inflammatory biomarkers, whereas the D/S phenotype, consisted predominantly of men, displayed the highest values of left ventricular mass, volume, and remodeling biomarkers. The phenotypes were predicted based on a simple algorithm including e', left ventricular mass and volume (e'VM algorithm). In the Malmö cohort, subgroups derived from e'VM algorithm were significantly associated with a higher risk of CVM and HFH (adjusted HR in the D phenotype = 1.87; 95% CI: 1.04 to 3.37; adjusted HR in the D/S phenotype = 3.02; 95% CI: 1.71 to 5.34).CONCLUSIONS: Among asymptomatic, middle-aged individuals, echocardiographic data-driven classification based on the simple e'VM algorithm identified profiles with different long-term HF risk. (4th Visit at 17 Years of Cohort STANISLAS-Stanislas Ancillary Study ESCIF [STANISLASV4]; NCT01391442).

AB - OBJECTIVES: This study sought to identify homogenous echocardiographic phenotypes in community-based cohorts and assess their association with outcomes.BACKGROUND: Asymptomatic cardiac dysfunction leads to a high risk of long-term cardiovascular morbidity and mortality; however, better echocardiographic classification of asymptomatic individuals remains a challenge.METHODS: Echocardiographic phenotypes were identified using K-means clustering in the first generation of the STANISLAS (Yearly non-invasive follow-up of Health status of Lorraine insured inhabitants) cohort (N = 827; mean age: 60 ± 5 years; men: 48%), and their associations with vascular function and circulating biomarkers were also assessed. These phenotypes were externally validated in the Malmö Preventive Project cohort (N = 1,394; mean age: 67 ± 6 years; men: 70%), and their associations with the composite of cardiovascular mortality (CVM) or heart failure hospitalization (HFH) were assessed as well.RESULTS: Three echocardiographic phenotypes were identified as "mostly normal (MN)" (n = 334), "diastolic changes (D)" (n = 323), and "diastolic changes with structural remodeling (D/S)" (n = 170). The D and D/S phenotypes had similar ages, body mass indices, cardiovascular risk factors, vascular impairments, and diastolic function changes. The D phenotype consisted mainly of women and featured increased levels of inflammatory biomarkers, whereas the D/S phenotype, consisted predominantly of men, displayed the highest values of left ventricular mass, volume, and remodeling biomarkers. The phenotypes were predicted based on a simple algorithm including e', left ventricular mass and volume (e'VM algorithm). In the Malmö cohort, subgroups derived from e'VM algorithm were significantly associated with a higher risk of CVM and HFH (adjusted HR in the D phenotype = 1.87; 95% CI: 1.04 to 3.37; adjusted HR in the D/S phenotype = 3.02; 95% CI: 1.71 to 5.34).CONCLUSIONS: Among asymptomatic, middle-aged individuals, echocardiographic data-driven classification based on the simple e'VM algorithm identified profiles with different long-term HF risk. (4th Visit at 17 Years of Cohort STANISLAS-Stanislas Ancillary Study ESCIF [STANISLASV4]; NCT01391442).

U2 - 10.1016/j.jcmg.2021.07.004

DO - 10.1016/j.jcmg.2021.07.004

M3 - Article

C2 - 34538625

SN - 1876-7591

VL - 15

SP - 193

EP - 208

JO - JACC: Cardiovascular Imaging

JF - JACC: Cardiovascular Imaging

IS - 2

ER -

Machine Learning-Derived Echocardiographic Phenotypes Predict Heart Failure Incidence in Asymptomatic Individuals

Abstract

Subject classification (UKÄ)

Access to Document

Fingerprint

Cite this