MM-GradCAM: an improved multimodal GradCAM method with 1D and 2D ECG data for detection of cardiac arrhythmia
Fatma Murat Duranay1, Ender Murat2, Özal Yıldırım3
1Department of Electrical and Electronics Engineering, Firat University, Elazığ, Turkey.
Insights
This study introduces MM-GradCAM, an AI method enhancing cardiac arrhythmia diagnosis by explaining both electrocardiogram (ECG) signals and images. This approach boosts trust and accuracy in AI-driven medical diagnostics.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Imaging
Background:
- Cardiac arrhythmia is a major global cause of death, necessitating early and accurate diagnosis.
- Electrocardiogram (ECG) analysis is crucial for diagnosing cardiac arrhythmias.
- Deep learning models show promise in automated ECG interpretation but often lack clinical transparency due to their "black box" nature.
Purpose of the Study:
- To develop an explainable artificial intelligence (XAI) method for cardiac arrhythmia detection.
- To provide interpretability for both 1D ECG signal and 2D ECG image data.
- To enhance clinical confidence and transparency in AI-based medical diagnostic tools.
Main Methods:
- Developed an innovative MM-GradCAM method combining 1D ECG signal and 2D ECG image data formats.
- Utilized a 17-layer Convolutional Neural Network (CNN) for four-class arrhythmia detection on a dataset of over 10,000 patients.
- Generated separate explainability outputs for each data format (signal and image).
Main Results:
- The CNN model achieved 93.07% accuracy for the signal form and 97.44% accuracy for the image form.
- Explainability maps generated by MM-GradCAM were validated by a cardiologist for interpretability and clinical significance.
- The study demonstrated the effectiveness of MM-GradCAM in providing transparent insights into AI diagnostic decisions.
Conclusions:
- MM-GradCAM offers a pioneering approach to explainability in medical AI, specifically for cardiac arrhythmia diagnosis.
- The method enhances the reliability and transparency of AI applications in healthcare.
- This work has the potential to significantly improve patient outcomes through more trustworthy AI diagnostics.
Abstract:
As cardiac arrhythmia remains one of the leading causes of death worldwide, early and accurate diagnosis of cardiac arrhythmia is critical to improving patient outcomes. Electrocardiogram (ECG) analysis plays a critical role in the diagnosis of these diseases, and recent advances in deep learning have led to significant advances in automated ECG interpretation. However, the "black box" nature of these models limits clinical confidence and highlights the need for explainable artificial intelligence methods. This study presents an innovative MM-GradCAM method that combines two different data formats, providing explainability for both 1D ECG signal and 2D ECG image data. Using a dataset of more than 10,000 patients, a 17-layer CNN model capable of four-class arrhythmia detection was developed and separate explainability outputs were obtained for each data form. The resulting explainability maps were evaluated by a cardiologist and the interpretability and clinical significance of the model were verified. The signal form achieved 93.07% accuracy, while the image form achieved 97.44% accuracy. As a pioneering approach for explainability in medical diagnosis, MM-GradCAM has the potential to increase reliability and transparency in medical AI applications.
Related Concept Videos
01:16ECG Interpretation of Arrhythmias I: Sinus Arrhythmias
Types of Arrhythmias
Sinus Node Arrhythmias
Sinus Bradycardia: Originating from the sinoatrial (SA) node, sinus bradycardia involves slower impulses, resulting in a heart rate of less than 60 beats per minute (bpm). Causes include sleep, vagal stimulation, beta-blockers, hypothyroidism,...
01:25ECG Interpretation of Arrhythmias II: Atrial, Junctional and Ventricular Arrhythmias
01:28Mechanism of Cardiac Arrhythmias
01:25Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
01:24ECG Interpretation of Rhythms
Components of the Electrocardiogram
The primary components of a normal ECG waveform in Normal sinus rhythm(NSR) include the P wave, PR interval, QRS complex, ST segment, T wave, and occasionally a U wave.
ECG waveforms are divided by vertical and horizontal lines at standard intervals.
The horizontal axis measures time and rate, and the vertical axis measures amplitude or voltage....
01:25Statistical Methods for Analyzing Epidemiological Data