What does this research mean for the field?

A hybrid deep learning model integrating ResNet-50 with Squeeze-and-Excitation blocks and LSTM networks enables joint learning of spatial and temporal features from ECG scalograms, achieving 99.20% accuracy in classifying cardiovascular diseases. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 1, 2025IEEE AccessOpen Access

The proposed hybrid deep learning model achieved a classification accuracy of 99.20%, with precision, recall, and F1-scores exceeding 0.99.

View Full Paper

Ask AI

Bookmark

Why the study?

Accurate and robust classification of ECG signals for arrhythmia detection remains challenging due to noise, data imbalance, and the complexity of integrating spatial and temporal features.

Population

ECG signals comprising Arrhythmia, Congestive Heart Failure, and Normal Sinus Rhythm

Comparison

Hybrid deep learning model integrating ResNet-50, SE blocks, and LSTM networks

Design

Model development and validation study

Authors

NKNeeraj Singh Kathayat ARA. Pravin Renold

Discussion

Member takes

Overview

Should not yet change ECG workflows; hypothesis-generating for hybrid DL models pending prospective validation.

Structured PICO

Population

ECG signals from a balanced dataset comprising three classes: Arrhythmia (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR)

Intervention

Hybrid deep learning model integrating ResNet-50 with Squeeze-and-Excitation (SE) blocks and Long Short-Term Memory (LSTM) networks using Continuous Wavelet Transform (CWT) scalograms

Outcome

Classification accuracysurrogate

A novel hybrid deep learning model combining ResNet-50, SE blocks, and LSTM achieved >99% accuracy in classifying ECG signals into arrhythmia, heart failure, and normal sinus rhythm.

Cite This Study

Kathayat et al. (2025) studied this question.

synapsesocial.com/papers/6a1a2d359dd58c84b95b6233 https://doi.org/10.1109/access.2025.3605279

View Full Paper

Ask AI

Bookmark

January 1, 2025IEEE AccessOpen Access

The proposed hybrid deep learning model achieved a classification accuracy of 99.20%, with precision, recall, and F1-scores exceeding 0.99.

View Full Paper

Ask AI

Bookmark

Why the study?

Accurate and robust classification of ECG signals for arrhythmia detection remains challenging due to noise, data imbalance, and the complexity of integrating spatial and temporal features.

Population

ECG signals comprising Arrhythmia, Congestive Heart Failure, and Normal Sinus Rhythm

Comparison

Hybrid deep learning model integrating ResNet-50, SE blocks, and LSTM networks

Design

Model development and validation study

Authors

NKNeeraj Singh Kathayat ARA. Pravin Renold

Discussion

Member takes

Overview

Should not yet change ECG workflows; hypothesis-generating for hybrid DL models pending prospective validation.

Structured PICO

Population

ECG signals from a balanced dataset comprising three classes: Arrhythmia (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR)

Intervention

Hybrid deep learning model integrating ResNet-50 with Squeeze-and-Excitation (SE) blocks and Long Short-Term Memory (LSTM) networks using Continuous Wavelet Transform (CWT) scalograms

Outcome

Classification accuracysurrogate

A novel hybrid deep learning model combining ResNet-50, SE blocks, and LSTM achieved >99% accuracy in classifying ECG signals into arrhythmia, heart failure, and normal sinus rhythm.

Cite This Study

Kathayat et al. (2025) studied this question.

synapsesocial.com/papers/6a1a2d359dd58c84b95b6233 https://doi.org/10.1109/access.2025.3605279

View Full Paper

Ask AI

Bookmark