EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Signal-Guided Multitask Learning for Myocardial Infarction Classification Using Images of Electrocardiogram

Bo Eun Park, Byungeun Shon, Jungrae Cho, Min-Su Jung, Jong Sung Park, Myeong Seop Kim, Eunkyu Lee, Hyohun Choi, Hyuk Kyoon Park, Yoon Jung Park, Hong Nyun Kim, Namkyun Kim und 7 weitere

Cardiology · 2024

DOI: 10.1159/000542399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cardiology, 2024. Verfasst von Bo Eun Park und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Kyungpook National University Hospital, Daegu, Republic of Korea. Hauptthemen laut MEDLINE: Electrocardiography, Myocardial Infarction, Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The diagnosis of myocardial infarction (MI) needs to be swift and accurate, but definitively diagnosing it based on the first test encountered in clinical practice, the electrocardiogram (ECG), is not an easy task. The purpose of the study was to develop a deep learning (DL) algorithm using multitask learning method to differentiate patients experiencing MI from those without coronary artery disease using image-based ECG data.

Methods

A DL model was developed based on 11,227 ECG images. We developed a new ECG interpretation algorithm through signal-guided multitask learning, building on a previously published single-task algorithm. The utility of this model was evaluated by testing 51 physicians in interpreting ECGs with and without the assistance of the DL model.

Results

The proposed model demonstrated superior performance, achieving 90.56% accuracy, 83.82% sensitivity, 93.02% specificity, 81.44% precision, and an F1 score of 82.61% in discriminating MI ECG. Overall, the median accuracy of ECG interpretation improved from 62% to 68% with the DL algorithm. Trainees and specialists in internal medicine experienced significant accuracy increases (60–66% for trainees, 72–80% for specialists). In the MI group, NSTEMI accuracy was notably lower than STEMI (33% vs. 80%, p < 0.001), but the DL algorithm improved interpretative capabilities in both NSTEMI and STEMI.

Conclusions

Signal-guided multitask DL algorithm demonstrated superior performance compared with previous single-task algorithm. The DL algorithm supports the physicians’ decision discriminating MI ECGs from non-MI ECGs. The improvement was consistent in subgroups of STEMI and NSTEMI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographyMyocardial InfarctionDeep LearningHumansAlgorithmsMaleFemaleMiddle AgedSensitivity and Specificity

Stichwörter der Autor:innen

Artificial intelligenceDeep learningElectrocardiogramMyocardial infarction

Autor:innen und Institutionen

  • Department of Internal Medicine, Kyungpook National University Hospital, Daegu, Republic of Korea.
  • School of Medicine, Kyungpook National University, Daegu, Republic of Korea.
  • Department of Medical Informatics, Kyungpook National University, Daegu, Republic of Korea.
  • Research Center for Artificial Intelligence in Medicine, Kyungpook National University Hospital, Deagu, Republic of Korea.
  • Kyungpook National University Chilgok Hospital, Daegu, Republic of Korea.

Zitieren

APA

Park, B. E., Shon, B., Cho, J., Jung, M. S., Park, J. S., Kim, M. S., Lee, E., Choi, H., Park, H. K., Park, Y. J., Kim, H. N., Kim, N., Bae, M. H., Lee, J. H., Yang, D. H., Park, H. S., Cho, Y., Jeong, S., & Jang, S. Y. (2024). Signal-Guided Multitask Learning for Myocardial Infarction Classification Using Images of Electrocardiogram. Cardiology. https://doi.org/10.1159/000542399

Vancouver

Park BE, Shon B, Cho J, Jung MS, Park JS, Kim MS, et al. Signal-Guided Multitask Learning for Myocardial Infarction Classification Using Images of Electrocardiogram. Cardiology. 2024. doi:10.1159/000542399

BibTeX
@article{Park2024,
  author = {Park, Bo Eun and Shon, Byungeun and Cho, Jungrae and Jung, Min-Su and Park, Jong Sung and Kim, Myeong Seop and Lee, Eunkyu and Choi, Hyohun and Park, Hyuk Kyoon and Park, Yoon Jung and Kim, Hong Nyun and Kim, Namkyun and Bae, Myung Hwan and Lee, Jang Hoon and Yang, Dong Heon and Park, Hun Sik and Cho, Yongkeun and Jeong, Sungmoon and Jang, Se Yong},
  title = {Signal-Guided Multitask Learning for Myocardial Infarction Classification Using Images of Electrocardiogram},
  journal = {Cardiology},
  year = {2024},
  doi = {10.1159/000542399}
}
Kostenlos starten →