Automatic Detection of Occluded Main Coronary Arteries of NSTEMI Patients with MI-MS ConvMixer + WSSE Without CAG
Mehmet Cagri Goktekin1, Evrim Gul1, Tolga Çakmak2
1Emergency Medicine Department, School of Medicine, Firat University, Elazig 23119, Turkey.
Insights
A novel deep learning model, the MI-MS ConvMixer, accurately detects coronary artery blockages in Non-ST-segment Elevation Myocardial Infarction (NSTEMI) patients using ECG data. This approach offers a promising tool for automated diagnosis, improving patient outcomes.
Area of Science:
- Cardiology
- Artificial Intelligence
- Biomedical Engineering
Background:
- Heart attacks are a leading global cause of death, with Non-ST-segment Elevation Myocardial Infarction (NSTEMI) posing long-term risks.
- Detecting coronary artery blockages in NSTEMI patients is challenging via ECG alone, often necessitating invasive coronary angiography (CAG).
- CAG carries risks for elderly patients and those with chronic conditions, highlighting the need for non-invasive diagnostic alternatives.
Purpose of the Study:
- To develop a novel deep learning approach for the automatic detection of occluded coronary arteries in NSTEMI patients.
- To create and utilize a new seven-class dataset of ECG signals, curated by expert cardiologists, for training and validation.
- To enhance diagnostic accuracy and reduce reliance on invasive procedures for NSTEMI patients.
Main Methods:
- Development of a Multi Input-Multi Scale (MI-MS) ConvMixer model capable of processing 12-channel ECG data simultaneously.
- The MI-MS ConvMixer architecture effectively highlights data regions at various scales, optimizing feature extraction without increased model complexity.
- Implementation of the Weighted Support Vector Machine (WSSE) algorithm to refine classification predictions based on feature importance weights.
Main Results:
- The MI-MS ConvMixer model, combined with the WSSE algorithm, achieved a diagnostic accuracy of 88.72% in classifying coronary artery blockages.
- The WSSE algorithm demonstrated an improvement in the performance of the Support Vector Machine (SVM) classifier.
- Extracted features from the deep learning model were effectively classified, demonstrating the model's predictive power.
Conclusions:
- The MI-MS ConvMixer model shows significant potential for advancing ECG signal classification in diagnosing coronary artery disease.
- This deep learning approach offers a promising tool for real-time, automated analysis in clinical settings, aiding NSTEMI patient management.
- The model's high sensitivity, specificity, and precision indicate its capability to substantially improve diagnostic outcomes.
Abstract:
Background/Objectives: Heart attacks are the leading cause of death in the world. There are two important classes of heart attack: ST-segment Elevation Myocardial Infarction (STEMI) and Non-ST-segment Elevation Myocardial Infarction (NSTEMI) patient groups. While the STEMI group has a higher mortality rate in the short term, the NSTEMI group is considered more dangerous and insidious in the long term. Blocked coronary arteries can be predicted from ECG signals in STEMI patients but not in NSTEMI patients. Therefore, coronary angiography (CAG) is inevitable for these patients. However, in the elderly and some patients with chronic diseases, if there is a single blockage, the CAG procedure poses a risk, so medication may be preferred. In this study, a novel deep learning-based approach is used to automatically detect the occluded main coronary artery or arteries in NSTEMI patients. For this purpose, a new seven-class dataset was created with expert cardiologists. Methods: A new Multi Input-Multi Scale (MI-MS) ConvMixer model was developed for automatic detection. The MI-MS ConvMixer model allows simultaneous training of 12-channel ECG data and highlights different regions of the data at different scales. In addition, the ConMixer structure provides high classification performance without increasing the complexity of the model. Moreover, to maximise the classifier performance, the WSSE algorithm was developed to adjust the classification prediction value according to the feature importance weights. Results: This algorithm improves the SVM classifier performance. The features extracted from this model were classified with the WSSE algorithm, and an accuracy of 88.72% was achieved. Conclusions: This study demonstrates the potential of the MI-MS ConvMixer model in advancing ECG signal classification for diagnosing coronary artery diseases, offering a promising tool for real-time, automated analysis in clinical settings. The findings highlight the model's ability to achieve high sensitivity, specificity, and precision, which could significantly improve.
More Related Videos
13:07Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
Published on: January 15, 2022
08:35Oxygenation-sensitive Cardiac MRI with Vasoactive Breathing Maneuvers for the Non-invasive Assessment of Coronary Microvascular Dysfunction
Published on: August 17, 2022
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:30Acute Coronary Syndrome I: Introduction
01:30Acute Coronary Syndrome III: Diagnostic Studies