open access

Online first
Original article
Published online: 2021-04-16
Get Citation

Machine learning versus classic electrocardiographic criteria for the detection of echocardiographic left ventricular hypertrophy in a pre-participation cohort

Daniel Y.Z. Lim, Gerald Sng, Wilbert H.H. Ho, Wang Hankun, Ching-Hui Sia, Joshua S.W. Lee, Xiayan Shen, Benjamin Y.Q. Tan, Edward C.Y. Lee, Mayank Dalakoti, Wang Kang Jie, Clarence K.W. Kwan, Weien Chow, Ru San Tan, Carolyn S.P. Lam, Terrance S.J. Chua, Tee Joo Yeo, Daniel T.T. Chong
Pubmed: 33885269

open access

Online first
Original article
Published online: 2021-04-16

Abstract

ABSTRACT Background: Classical electrocardiographic (ECG) criteria for left ventricular hypertrophy (LVH) are well studied in older populations and patients with hypertension. Their utility in young pre-participation cohorts is unclear. Aims: We aimed to develop machine learning models for detection of echocardiogram-diagnosed LVH from ECG, and compare these modelswith classical criteria. Methods: Between November 2009 and December 2014, pre-participation screening ECG and subsequent echocardiographic data was collected from 17310 males aged 16 to 23, who reported for medical screening prior to military conscription.A final diagnosis of LVH was made on echocardiography, defined by a left ventricular mass index >115g/m2. The continuous and thresholded forms of classical ECG criteria (Sokolow-Lyon, Romhilt-Estes, Modified Cornell, Cornell Product and Cornell) were compared against machine learning models (Logistic Regression, GLMNet, Random Forests, Gradient Boosting Machines) using receiver-operating characteristics (ROC) curve analysis. We also compared the important variables identified by machine learning models with the input variables of classical criteria. Results: Prevalence of echocardiographic LVH in this population was 0.82% (143/17310). Classical ECG criteria had poor performance in predicting LVH. Machine learning methods achieved superior performance –Logistic Regression (AUC=0.811, 95% CI=0.738-0.884), GLMNet (AUC=0.873, 95% CI=0.817-0.929), Random Forest (AUC=0.824, 95% CI=0.749-0.898), Gradient Boosting Machines (AUC=0.800, 95% CI=0.738-0.862). Conclusions: Machine learning methods are superior to classical ECG criteria in diagnosing echocardiographic LVH in the context of pre-participation screening.

Abstract

ABSTRACT Background: Classical electrocardiographic (ECG) criteria for left ventricular hypertrophy (LVH) are well studied in older populations and patients with hypertension. Their utility in young pre-participation cohorts is unclear. Aims: We aimed to develop machine learning models for detection of echocardiogram-diagnosed LVH from ECG, and compare these modelswith classical criteria. Methods: Between November 2009 and December 2014, pre-participation screening ECG and subsequent echocardiographic data was collected from 17310 males aged 16 to 23, who reported for medical screening prior to military conscription.A final diagnosis of LVH was made on echocardiography, defined by a left ventricular mass index >115g/m2. The continuous and thresholded forms of classical ECG criteria (Sokolow-Lyon, Romhilt-Estes, Modified Cornell, Cornell Product and Cornell) were compared against machine learning models (Logistic Regression, GLMNet, Random Forests, Gradient Boosting Machines) using receiver-operating characteristics (ROC) curve analysis. We also compared the important variables identified by machine learning models with the input variables of classical criteria. Results: Prevalence of echocardiographic LVH in this population was 0.82% (143/17310). Classical ECG criteria had poor performance in predicting LVH. Machine learning methods achieved superior performance –Logistic Regression (AUC=0.811, 95% CI=0.738-0.884), GLMNet (AUC=0.873, 95% CI=0.817-0.929), Random Forest (AUC=0.824, 95% CI=0.749-0.898), Gradient Boosting Machines (AUC=0.800, 95% CI=0.738-0.862). Conclusions: Machine learning methods are superior to classical ECG criteria in diagnosing echocardiographic LVH in the context of pre-participation screening.
Get Citation
Supp./Additional Files (1)
Supplementary file 1
Download
169KB
About this article
Title

Machine learning versus classic electrocardiographic criteria for the detection of echocardiographic left ventricular hypertrophy in a pre-participation cohort

Journal

Kardiologia Polska (Polish Heart Journal)

Issue

Online first

Article type

Original article

Published online

2021-04-16

Pubmed

33885269

Authors

Daniel Y.Z. Lim
Gerald Sng
Wilbert H.H. Ho
Wang Hankun
Ching-Hui Sia
Joshua S.W. Lee
Xiayan Shen
Benjamin Y.Q. Tan
Edward C.Y. Lee
Mayank Dalakoti
Wang Kang Jie
Clarence K.W. Kwan
Weien Chow
Ru San Tan
Carolyn S.P. Lam
Terrance S.J. Chua
Tee Joo Yeo
Daniel T.T. Chong

Important: This website uses cookies. More >>

The cookies allow us to identify your computer and find out details about your last visit. They remembering whether you've visited the site before, so that you remain logged in - or to help us work out how many new website visitors we get each month. Most internet browsers accept cookies automatically, but you can change the settings of your browser to erase cookies or prevent automatic acceptance if you prefer.

By VM Media Sp. z o.o. VM Group Sp.k., ul. Świętokrzyska 73 , 80–180 Gdańsk, Poland

phone:+48 58 320 94 94, fax:+48 58 320 94 60, e-mail: viamedica@viamedica.pl