ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects

Agrawal, Amulya; Chauhan, Aniket; Shetty, Manu Kumar; P, Girish M.; Gupta, Mohit; Gupta, Anubha

doi:10.1016/j.compbiomed.2022.105540

Cited by 23 publications

(9 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each CNN was subjected to a five-fold cross-validation grid search to find the most appropriate hyperparameters. Explored hyperparameters included the batch size = [4,8,16,32], learning rate = [0.001, 0.0001, 0.00001], and the number of last layer feature maps = [8,16,24,32]. All models were optimized by using the Adam optimizer with categorial cross-entropy being used as a loss function [51].…”

Section: Network Architecturementioning

confidence: 99%

xECGArch: A trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Goettling,

Hammer,

Malberg

et al. 2024

Preprint

View full text Add to dashboard Cite

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases (n = 9,854 ECGs) and achieved an F1 score of 95.43 % in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations (+24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

show abstract

Section: Network Architecturementioning

confidence: 99%

xECGArch: A trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Goettling,

Hammer,

Malberg

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Machine-learning and deep-learning models also need a high computing cost during model training. To improve the interpretability and transparency of these black box models, explainable AI models are currently used in various studies [38][39][40][41][42][43][44][45][46][47]. The collaboration of experts from biology, computer science and different fields can improve the transparency of such methods.…”

Section: Challenges In ML and Dlmentioning

confidence: 99%

From Code to Cure: The Impact of Artificial Intelligence in Biomedical Applications

Gromiha,

Preethi,

Pandey

2024

BioMedInformatics

View full text Add to dashboard Cite

show abstract

“…Agrawal et al [ 12 ] propose ECGiCOVIDNet, which is basically a one-dimensional convolutional neural network (1DCNN) for distinguishing ECG data of healthy subjects and post-COVID subjects. The study was motivated by the clinical observation that patients who had heart damages post-COVID did not always reflect underlying heart damages before the pandemic.…”

Section: Related Workmentioning

confidence: 99%

“…The authors in [ 10 ] have used SHAP to explain coronary heart disease's effect on heart failure mortality. Other notable explanations of the analysis of cardiac disorders through ECG signals have been observed in [ 11 , 12 ]. Apart from SHAP as mentioned earlier, we use SHAPASH, LIME, partial dependency plot (PDP), and DALEX for explaining the results in our study.…”

Section: Introductionmentioning

confidence: 99%

XAI–reduct: accuracy preservation despite dimensionality reduction for heart disease classification using explainable AI

Das

Sultana²,

Bhattacharya³

et al. 2023

J Supercomput

View full text Add to dashboard Cite

Machine learning (ML) has been used for classification of heart diseases for almost a decade, although understanding of the internal working of the black boxes, i.e., non-interpretable models, remain a demanding problem. Another major challenge in such ML models is the curse of dimensionality leading to resource intensive classification using the comprehensive set of feature vector (CFV). This study focuses on dimensionality reduction using explainable artificial intelligence, without negotiating on accuracy for heart disease classification. Four explainable ML models, using SHAP, were used for classification which reflected the feature contributions (FC) and feature weights (FW) for each feature in the CFV for generating the final results. FC and FW were taken into account in generating the reduced dimensional feature subset (FS). The findings of the study are as follows: (a) XGBoost classifies heart diseases best with explanations, with an increase in 2% in model accuracy over existing best proposals, (b) explainable classification using FS exhibits better accuracy than most of the literary proposals, and (c) with the increase in explainability, accuracy can be preserved using XGBoost classifier for classifying heart diseases, and (d) the top four features responsible for diagnosis of heart disease have been exhibited which have common occurrences in all the explanations reflected by the five explainable techniques used on XGBoost classifier based on feature contributions. To the best of our knowledge, this is first attempt to explain XGBoost classification for diagnosis of heart diseases using five explainable techniques.

show abstract

ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects

Cited by 23 publications

References 40 publications

xECGArch: A trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

xECGArch: A trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

From Code to Cure: The Impact of Artificial Intelligence in Biomedical Applications

XAI–reduct: accuracy preservation despite dimensionality reduction for heart disease classification using explainable AI

Contact Info

Product

Resources

About