Cargando…

Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram

Early detection of left ventricular systolic dysfunction (LVSD) may prompt early care and improve outcomes for asymptomatic patients. Standard 12-lead ECG may be used to predict LVSD. We aimed to compare the performance of Machine Learning Algorithms (MLA) and physicians in predicting LVSD from a st...

Descripción completa

Detalles Bibliográficos
Autores principales: Golany, Tomer, Radinsky, Kira, Kofman, Natalia, Litovchik, Ilya, Young, Revital, Monayer, Antoinette, Love, Itamar, Tziporin, Faina, Minha, Ido, Yehuda, Yakir, Ziv-Baran, Tomer, Fuchs, Shmuel, Minha, Sa’ar
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9699306/
https://www.ncbi.nlm.nih.gov/pubmed/36431244
http://dx.doi.org/10.3390/jcm11226767
_version_ 1784839039443009536
author Golany, Tomer
Radinsky, Kira
Kofman, Natalia
Litovchik, Ilya
Young, Revital
Monayer, Antoinette
Love, Itamar
Tziporin, Faina
Minha, Ido
Yehuda, Yakir
Ziv-Baran, Tomer
Fuchs, Shmuel
Minha, Sa’ar
author_facet Golany, Tomer
Radinsky, Kira
Kofman, Natalia
Litovchik, Ilya
Young, Revital
Monayer, Antoinette
Love, Itamar
Tziporin, Faina
Minha, Ido
Yehuda, Yakir
Ziv-Baran, Tomer
Fuchs, Shmuel
Minha, Sa’ar
author_sort Golany, Tomer
collection PubMed
description Early detection of left ventricular systolic dysfunction (LVSD) may prompt early care and improve outcomes for asymptomatic patients. Standard 12-lead ECG may be used to predict LVSD. We aimed to compare the performance of Machine Learning Algorithms (MLA) and physicians in predicting LVSD from a standard 12-lead ECG. By utilizing a dataset of 13,820 pairs of ECGs and echocardiography, a deep residual convolutional neural network was trained for predicting LVSD (ejection fraction (EF) < 50%) from ECG. The ECGs of the test set (n = 850) were assessed for LVSD by the MLA and six physicians. The performance was compared using sensitivity, specificity, and C-statistics. The interobserver agreement between the physicians for the prediction of LVSD was moderate (κ = 0.50), with average sensitivity and specificity of 70%. The C-statistic of the MLA was 0.85. Repeating this analysis with LVSD defined as EF < 35% resulted in an improvement in physicians’ average sensitivity to 84% but their specificity decreased to 57%. The MLA C-statistic was 0.88 with this threshold. We conclude that although MLA outperformed physicians in predicting LVSD from standard ECG, prior to robust implementation of MLA in ECG machines, physicians should be encouraged to use this approach as a simple and readily available aid for LVSD screening.
format Online
Article
Text
id pubmed-9699306
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96993062022-11-26 Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram Golany, Tomer Radinsky, Kira Kofman, Natalia Litovchik, Ilya Young, Revital Monayer, Antoinette Love, Itamar Tziporin, Faina Minha, Ido Yehuda, Yakir Ziv-Baran, Tomer Fuchs, Shmuel Minha, Sa’ar J Clin Med Article Early detection of left ventricular systolic dysfunction (LVSD) may prompt early care and improve outcomes for asymptomatic patients. Standard 12-lead ECG may be used to predict LVSD. We aimed to compare the performance of Machine Learning Algorithms (MLA) and physicians in predicting LVSD from a standard 12-lead ECG. By utilizing a dataset of 13,820 pairs of ECGs and echocardiography, a deep residual convolutional neural network was trained for predicting LVSD (ejection fraction (EF) < 50%) from ECG. The ECGs of the test set (n = 850) were assessed for LVSD by the MLA and six physicians. The performance was compared using sensitivity, specificity, and C-statistics. The interobserver agreement between the physicians for the prediction of LVSD was moderate (κ = 0.50), with average sensitivity and specificity of 70%. The C-statistic of the MLA was 0.85. Repeating this analysis with LVSD defined as EF < 35% resulted in an improvement in physicians’ average sensitivity to 84% but their specificity decreased to 57%. The MLA C-statistic was 0.88 with this threshold. We conclude that although MLA outperformed physicians in predicting LVSD from standard ECG, prior to robust implementation of MLA in ECG machines, physicians should be encouraged to use this approach as a simple and readily available aid for LVSD screening. MDPI 2022-11-15 /pmc/articles/PMC9699306/ /pubmed/36431244 http://dx.doi.org/10.3390/jcm11226767 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Golany, Tomer
Radinsky, Kira
Kofman, Natalia
Litovchik, Ilya
Young, Revital
Monayer, Antoinette
Love, Itamar
Tziporin, Faina
Minha, Ido
Yehuda, Yakir
Ziv-Baran, Tomer
Fuchs, Shmuel
Minha, Sa’ar
Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
title Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
title_full Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
title_fullStr Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
title_full_unstemmed Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
title_short Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
title_sort physicians and machine-learning algorithm performance in predicting left-ventricular systolic dysfunction from a standard 12-lead-electrocardiogram
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9699306/
https://www.ncbi.nlm.nih.gov/pubmed/36431244
http://dx.doi.org/10.3390/jcm11226767
work_keys_str_mv AT golanytomer physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT radinskykira physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT kofmannatalia physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT litovchikilya physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT youngrevital physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT monayerantoinette physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT loveitamar physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT tziporinfaina physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT minhaido physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT yehudayakir physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT zivbarantomer physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT fuchsshmuel physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram
AT minhasaar physiciansandmachinelearningalgorithmperformanceinpredictingleftventricularsystolicdysfunctionfromastandard12leadelectrocardiogram