Integrating multimodal information in machine learning for classifying acute myocardial infarction

• Type of Material: Article
• Authors: Ran Xiao, Emory University; Cheng Ding, Georgia Institute of Technology & Emory University; Xiao Hu, Emory University; Gari Clifford, Emory University; David Wright, Emory University; Amit Shah, Emory University; Salah Al-Zaiti, University of Pittsburgh; Jessica K Zègre-Hemsey, University of North Carolina
• Language: English
• Date: 2023-04-01
• Publisher: IOP Publishing Ltd
• Publication Version: Final Published Version
• Copyright Statement: © 2023 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1088/1361-6579/acc77f
• Title of Journal or Parent Work: PHYSIOLOGICAL MEASUREMENT
• Volume: 44
• Issue: 4
• Keywords: Biophysics; ELECTROCARDIOGRAM; ST-SEGMENT EPISODES; Physiology; Technology; AUTOMATED DETECTION; Engineering; electrocardiography; myocardial infarction; deep learning; machine learning; ECG; Life Sciences & Biomedicine; Engineering, Biomedical; Science & Technology; acute coronary syndrome
• Research Categories: Engineering, Biomedical; Health Sciences, Nursing; Health Sciences, Medicine and Surgery; Biology, Bioinformatics

Abstract

Objective. Prompt identification and recognization of myocardial ischemia/infarction (MI) is the most important goal in the management of acute coronary syndrome. The 12-lead electrocardiogram (ECG) is widely used as the initial screening tool for patients with chest pain but its diagnostic accuracy remains limited. There is early evidence that machine learning (ML) algorithms applied to ECG waveforms can improve performance. Most studies are designed to classify MI from healthy controls and thus are limited due to the lack of consideration of ECG abnormalities from other cardiac conditions, leading to false positives. Moreover, clinical information beyond ECG has not yet been well leveraged in existing ML models. Approach. The present study considered downstream clinical implementation scenarios in the initial model design by dichotomizing study recordings from a public large-scale ECG dataset into a MI class and a non-MI class with the inclusion of MI-confounding conditions. Two experiments were conducted to systematically investigate the impact of two important factors entrained in the modeling process, including the duration of ECG, and the value of multimodal information for model training. A novel multimodal deep learning architecture was proposed to learn joint features from both ECG and patient demographics. Main results. The multimodal model achieved better performance than the ECG-only model, with a mean area under the receiver operating characteristic curve of 92.1% and a mean accuracy of 87.4%, which is on par with existing studies despite the increased task difficulty due to the new class definition. By investigation of model explainability, it revealed the contribution of patient information in model performance and clinical concordance of the model’s attention with existing clinical insights. Significance. The findings in this study help guide the development of ML solutions for prompt MI detection and move the models one step closer to real-world clinical applications.