Use of hundreds of electrocardiographic biomarkers for prediction of mortality in postmenopausal women the women's health initiative

Eiran Z. Gorodeski, Hemant Ishwaran, Udaya B. Kogalur, Eugene H. Blackstone, Eileen Hsich, Zhu Ming Zhang, Mara Z. Vitolins, JoAnn E. Manson, J. David Curb, Lisa W. Martin, Ronald J. Prineas, Michael S. Lauer

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Background-Simultaneous contribution of hundreds of electrocardiographic (ECG) biomarkers to prediction of long-term mortality in postmenopausal women with clinically normal resting ECGs is unknown. Methods and Results-We analyzed ECGs and all-cause mortality in 33 144 women enrolled in the Women's Health Initiative trials who were without baseline cardiovascular disease or cancer and had normal ECGs by Minnesota and Novacode criteria. Four hundred and seventy-seven ECG biomarkers, encompassing global and individual ECG findings, were measured with computer algorithms. During a median follow-up of 8.1 years (range for survivors, 0.5 to 11.2 years), 1229 women died. For analyses, the cohort was randomly split into derivation (n=22 096; deaths, 819) and validation (n=11 048; deaths, 410) subsets. ECG biomarkers and demographic and clinical characteristics were simultaneously analyzed using both traditional Cox regression and random survival forest, a novel algorithmic machine-learning approach. Regression modeling failed to converge. Random survival forest variable selection yielded 20 variables that were independently predictive of long-term mortality, 14 of which were ECG biomarkers related to autonomic tone, atrial conduction, and ventricular depolarization and repolarization. Conclusions-We identified 14 ECG biomarkers from among hundreds that were associated with long-term prognosis using a novel random forest variable selection methodology. These biomarkers were related to autonomic tone, atrial conduction, ventricular depolarization, and ventricular repolarization. Quantitative ECG biomarkers have prognostic importance and may be markers of subclinical disease in apparently healthy postmenopausal women.

Original languageEnglish
Pages (from-to)521-532
Number of pages12
JournalCirculation: Cardiovascular Quality and Outcomes
Volume4
Issue number5
DOIs
StatePublished - Sep 1 2011
Externally publishedYes

Fingerprint

Women's Health
Biomarkers
Mortality
Electrocardiography
Survival
Survivors
Cohort Studies
Cardiovascular Diseases
Demography
Forests
Neoplasms

Keywords

  • Electrocardiography
  • Epidemiology
  • Prognosis
  • Women

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Cite this

Use of hundreds of electrocardiographic biomarkers for prediction of mortality in postmenopausal women the women's health initiative. / Gorodeski, Eiran Z.; Ishwaran, Hemant; Kogalur, Udaya B.; Blackstone, Eugene H.; Hsich, Eileen; Zhang, Zhu Ming; Vitolins, Mara Z.; Manson, JoAnn E.; Curb, J. David; Martin, Lisa W.; Prineas, Ronald J.; Lauer, Michael S.

In: Circulation: Cardiovascular Quality and Outcomes, Vol. 4, No. 5, 01.09.2011, p. 521-532.

Research output: Contribution to journalArticle

Gorodeski, EZ, Ishwaran, H, Kogalur, UB, Blackstone, EH, Hsich, E, Zhang, ZM, Vitolins, MZ, Manson, JE, Curb, JD, Martin, LW, Prineas, RJ & Lauer, MS 2011, 'Use of hundreds of electrocardiographic biomarkers for prediction of mortality in postmenopausal women the women's health initiative', Circulation: Cardiovascular Quality and Outcomes, vol. 4, no. 5, pp. 521-532. https://doi.org/10.1161/CIRCOUTCOMES.110.959023
Gorodeski, Eiran Z. ; Ishwaran, Hemant ; Kogalur, Udaya B. ; Blackstone, Eugene H. ; Hsich, Eileen ; Zhang, Zhu Ming ; Vitolins, Mara Z. ; Manson, JoAnn E. ; Curb, J. David ; Martin, Lisa W. ; Prineas, Ronald J. ; Lauer, Michael S. / Use of hundreds of electrocardiographic biomarkers for prediction of mortality in postmenopausal women the women's health initiative. In: Circulation: Cardiovascular Quality and Outcomes. 2011 ; Vol. 4, No. 5. pp. 521-532.
@article{64a1d122fcda4d6681d25d9a3d6d164f,
title = "Use of hundreds of electrocardiographic biomarkers for prediction of mortality in postmenopausal women the women's health initiative",
abstract = "Background-Simultaneous contribution of hundreds of electrocardiographic (ECG) biomarkers to prediction of long-term mortality in postmenopausal women with clinically normal resting ECGs is unknown. Methods and Results-We analyzed ECGs and all-cause mortality in 33 144 women enrolled in the Women's Health Initiative trials who were without baseline cardiovascular disease or cancer and had normal ECGs by Minnesota and Novacode criteria. Four hundred and seventy-seven ECG biomarkers, encompassing global and individual ECG findings, were measured with computer algorithms. During a median follow-up of 8.1 years (range for survivors, 0.5 to 11.2 years), 1229 women died. For analyses, the cohort was randomly split into derivation (n=22 096; deaths, 819) and validation (n=11 048; deaths, 410) subsets. ECG biomarkers and demographic and clinical characteristics were simultaneously analyzed using both traditional Cox regression and random survival forest, a novel algorithmic machine-learning approach. Regression modeling failed to converge. Random survival forest variable selection yielded 20 variables that were independently predictive of long-term mortality, 14 of which were ECG biomarkers related to autonomic tone, atrial conduction, and ventricular depolarization and repolarization. Conclusions-We identified 14 ECG biomarkers from among hundreds that were associated with long-term prognosis using a novel random forest variable selection methodology. These biomarkers were related to autonomic tone, atrial conduction, ventricular depolarization, and ventricular repolarization. Quantitative ECG biomarkers have prognostic importance and may be markers of subclinical disease in apparently healthy postmenopausal women.",
keywords = "Electrocardiography, Epidemiology, Prognosis, Women",
author = "Gorodeski, {Eiran Z.} and Hemant Ishwaran and Kogalur, {Udaya B.} and Blackstone, {Eugene H.} and Eileen Hsich and Zhang, {Zhu Ming} and Vitolins, {Mara Z.} and Manson, {JoAnn E.} and Curb, {J. David} and Martin, {Lisa W.} and Prineas, {Ronald J.} and Lauer, {Michael S.}",
year = "2011",
month = "9",
day = "1",
doi = "10.1161/CIRCOUTCOMES.110.959023",
language = "English",
volume = "4",
pages = "521--532",
journal = "Circulation: Cardiovascular Quality and Outcomes",
issn = "1941-7713",
publisher = "Lippincott Williams and Wilkins",
number = "5",

}

TY - JOUR

T1 - Use of hundreds of electrocardiographic biomarkers for prediction of mortality in postmenopausal women the women's health initiative

AU - Gorodeski, Eiran Z.

AU - Ishwaran, Hemant

AU - Kogalur, Udaya B.

AU - Blackstone, Eugene H.

AU - Hsich, Eileen

AU - Zhang, Zhu Ming

AU - Vitolins, Mara Z.

AU - Manson, JoAnn E.

AU - Curb, J. David

AU - Martin, Lisa W.

AU - Prineas, Ronald J.

AU - Lauer, Michael S.

PY - 2011/9/1

Y1 - 2011/9/1

N2 - Background-Simultaneous contribution of hundreds of electrocardiographic (ECG) biomarkers to prediction of long-term mortality in postmenopausal women with clinically normal resting ECGs is unknown. Methods and Results-We analyzed ECGs and all-cause mortality in 33 144 women enrolled in the Women's Health Initiative trials who were without baseline cardiovascular disease or cancer and had normal ECGs by Minnesota and Novacode criteria. Four hundred and seventy-seven ECG biomarkers, encompassing global and individual ECG findings, were measured with computer algorithms. During a median follow-up of 8.1 years (range for survivors, 0.5 to 11.2 years), 1229 women died. For analyses, the cohort was randomly split into derivation (n=22 096; deaths, 819) and validation (n=11 048; deaths, 410) subsets. ECG biomarkers and demographic and clinical characteristics were simultaneously analyzed using both traditional Cox regression and random survival forest, a novel algorithmic machine-learning approach. Regression modeling failed to converge. Random survival forest variable selection yielded 20 variables that were independently predictive of long-term mortality, 14 of which were ECG biomarkers related to autonomic tone, atrial conduction, and ventricular depolarization and repolarization. Conclusions-We identified 14 ECG biomarkers from among hundreds that were associated with long-term prognosis using a novel random forest variable selection methodology. These biomarkers were related to autonomic tone, atrial conduction, ventricular depolarization, and ventricular repolarization. Quantitative ECG biomarkers have prognostic importance and may be markers of subclinical disease in apparently healthy postmenopausal women.

AB - Background-Simultaneous contribution of hundreds of electrocardiographic (ECG) biomarkers to prediction of long-term mortality in postmenopausal women with clinically normal resting ECGs is unknown. Methods and Results-We analyzed ECGs and all-cause mortality in 33 144 women enrolled in the Women's Health Initiative trials who were without baseline cardiovascular disease or cancer and had normal ECGs by Minnesota and Novacode criteria. Four hundred and seventy-seven ECG biomarkers, encompassing global and individual ECG findings, were measured with computer algorithms. During a median follow-up of 8.1 years (range for survivors, 0.5 to 11.2 years), 1229 women died. For analyses, the cohort was randomly split into derivation (n=22 096; deaths, 819) and validation (n=11 048; deaths, 410) subsets. ECG biomarkers and demographic and clinical characteristics were simultaneously analyzed using both traditional Cox regression and random survival forest, a novel algorithmic machine-learning approach. Regression modeling failed to converge. Random survival forest variable selection yielded 20 variables that were independently predictive of long-term mortality, 14 of which were ECG biomarkers related to autonomic tone, atrial conduction, and ventricular depolarization and repolarization. Conclusions-We identified 14 ECG biomarkers from among hundreds that were associated with long-term prognosis using a novel random forest variable selection methodology. These biomarkers were related to autonomic tone, atrial conduction, ventricular depolarization, and ventricular repolarization. Quantitative ECG biomarkers have prognostic importance and may be markers of subclinical disease in apparently healthy postmenopausal women.

KW - Electrocardiography

KW - Epidemiology

KW - Prognosis

KW - Women

UR - http://www.scopus.com/inward/record.url?scp=80054756085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054756085&partnerID=8YFLogxK

U2 - 10.1161/CIRCOUTCOMES.110.959023

DO - 10.1161/CIRCOUTCOMES.110.959023

M3 - Article

C2 - 21862719

AN - SCOPUS:80054756085

VL - 4

SP - 521

EP - 532

JO - Circulation: Cardiovascular Quality and Outcomes

JF - Circulation: Cardiovascular Quality and Outcomes

SN - 1941-7713

IS - 5

ER -