Machine-learning-derived heart and brain age are independently associated with cognition

Olena Iakunchykova; Henrik Schirmer; Torgil Vangberg; Yunpeng Wang; Ernest D. Benavente; René van Es; Rutger R. van de Leur; Haakon Lindekleiv; Zachi I. Attia; Francisco Lopez-Jimenez; David A. Leon; Tom Wilsgaard

doi:10.1111/ene.15902

Machine-learning-derived heart and brain age are independently associated with cognition

Olena Iakunchykova, Henrik Schirmer, Torgil Vangberg, Yunpeng Wang, Ernest D. Benavente, René van Es, Rutger R. van de Leur, Haakon Lindekleiv, Zachi I. Attia, Francisco Lopez-Jimenez, David A. Leon, Tom Wilsgaard

Cardiovascular Medicine

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

Abstract

Background and purpose: A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. Methods: Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40–85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. Results: Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3–36) of the HDA effect on the tapping test score was mediated through BDA. Discussion: Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

Original language	English (US)
Pages (from-to)	2611-2619
Number of pages	9
Journal	European Journal of Neurology
Volume	30
Issue number	9
DOIs	https://doi.org/10.1111/ene.15902
State	Published - Sep 2023

Keywords

ECG
MRI
cognitive tests
deep neural networks
dementia

ASJC Scopus subject areas

Neurology
Clinical Neurology

Access to Document

10.1111/ene.15902

Cite this

@article{9cdd2ce173ad4e8398435d3b51bcbdff,

title = "Machine-learning-derived heart and brain age are independently associated with cognition",

abstract = "Background and purpose: A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. Methods: Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40–85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. Results: Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3–36) of the HDA effect on the tapping test score was mediated through BDA. Discussion: Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.",

keywords = "ECG, MRI, cognitive tests, deep neural networks, dementia",

author = "Olena Iakunchykova and Henrik Schirmer and Torgil Vangberg and Yunpeng Wang and Benavente, {Ernest D.} and {van Es}, Ren{\'e} and {van de Leur}, {Rutger R.} and Haakon Lindekleiv and Attia, {Zachi I.} and Francisco Lopez-Jimenez and Leon, {David A.} and Tom Wilsgaard",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors. European Journal of Neurology published by John Wiley & Sons Ltd on behalf of European Academy of Neurology.",

year = "2023",

month = sep,

doi = "10.1111/ene.15902",

language = "English (US)",

volume = "30",

pages = "2611--2619",

journal = "European Journal of Neurology",

issn = "1351-5101",

publisher = "Wiley-Blackwell",

number = "9",

}

TY - JOUR

T1 - Machine-learning-derived heart and brain age are independently associated with cognition

AU - Iakunchykova, Olena

AU - Schirmer, Henrik

AU - Vangberg, Torgil

AU - Wang, Yunpeng

AU - Benavente, Ernest D.

AU - van Es, René

AU - van de Leur, Rutger R.

AU - Lindekleiv, Haakon

AU - Attia, Zachi I.

AU - Lopez-Jimenez, Francisco

AU - Leon, David A.

AU - Wilsgaard, Tom

PY - 2023/9

Y1 - 2023/9

N2 - Background and purpose: A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. Methods: Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40–85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. Results: Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3–36) of the HDA effect on the tapping test score was mediated through BDA. Discussion: Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

AB - Background and purpose: A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. Methods: Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40–85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. Results: Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3–36) of the HDA effect on the tapping test score was mediated through BDA. Discussion: Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

KW - ECG

KW - MRI

KW - cognitive tests

KW - deep neural networks

KW - dementia

UR - http://www.scopus.com/inward/record.url?scp=85163064720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85163064720&partnerID=8YFLogxK

U2 - 10.1111/ene.15902

DO - 10.1111/ene.15902

M3 - Article

C2 - 37254942

AN - SCOPUS:85163064720

SN - 1351-5101

VL - 30

SP - 2611

EP - 2619

JO - European Journal of Neurology

JF - European Journal of Neurology

IS - 9

ER -

Machine-learning-derived heart and brain age are independently associated with cognition

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this