ECG-Lens: Benchmarking ML & DL Models on PTB-XL Dataset

2026-04-17 · Source: Artificial Intelligence · Field: Science & Research — Health & Medical Research, Artificial Intelligence & Machine Learning, Engineering & Applied Sciences · Depth: Advanced, quick

Summary

A study benchmarked three traditional machine learning algorithms (Decision Tree Classifier, Random Forest Classifier, Logistic Regression) and three deep learning models (Simple CNN, LSTM, Complex CNN (ECG-Lens)) for automated classification of 12-lead electrocardiogram (ECG) signals using the PTB-XL dataset. The deep learning models were trained on raw ECG signals, leveraging data augmentation via the Stationary Wavelet Transform (SWT) to improve performance and diversity. Evaluation across accuracy, precision, recall, F1-score, and ROC-AUC metrics revealed that the ECG-Lens model achieved the highest performance, with 80% classification accuracy and a 90% ROC-AUC. This indicates that complex CNN architectures significantly outperform traditional ML methods for raw 12-lead ECG data classification.

Key takeaway

For AI Engineers developing cardiovascular disease diagnostic tools, this study provides a clear benchmark: deep learning models, especially complex CNNs like ECG-Lens, offer superior performance on raw 12-lead ECG data compared to traditional ML. You should prioritize exploring and implementing advanced CNN architectures and consider SWT for data augmentation to achieve higher accuracy and ROC-AUC in your classification systems.

Key insights

Complex CNNs significantly outperform traditional ML for automated 12-lead ECG classification on raw data.

Principles

• Deep learning excels at raw signal feature extraction.
• Data augmentation enhances model performance and diversity.

Method

Deep learning models were trained on raw ECG signals, with data augmentation using Stationary Wavelet Transform (SWT) to preserve signal characteristics.

In practice

• Use complex CNNs for ECG signal classification.
• Apply SWT for ECG data augmentation.

Topics

• ECG Classification
• PTB-XL Dataset
• Deep Learning Models
• Machine Learning Benchmarking
• Convolutional Neural Networks

Best for: AI Engineer, AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• ECG-Lens: Benchmarking ML & DL Models on PTB-XL Dataset — Deep learning models, especially complex CNNs, significantly outperform traditional ML for raw 12-lead ECG classification.
• Benchmarks and methods for 3D medical image retrieval — The 3D-MIR benchmark and methods advance medical image retrieval by providing standardized evaluation and multi-modal search strategies.
• A Multimodal and Explainable Machine Learning Approach to Diagnosing Multi-Class Ejection Fraction from Electrocardiograms — Multimodal machine learning can accurately stratify LVEF from ECG and EHR data, enhancing accessibility.
• Convolutional neural networks quantify antibiotic resistance in Mycobacterium tuberculosis with diagnostic grade accuracy and predict treatment response — CNNs can predict antibiotic MICs from genomic data with clinical accuracy, leveraging diverse biological features.
• CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation — Adapting clinical ECG foundation models via lead transformation and progressive fine-tuning enables robust wearable cognitive load assessment.
• Can AI help predict which heart-failure patients will worsen within a year? — PULSE-HF is a deep-learning model forecasting heart failure worsening via ECGs, achieving high accuracy in LVEF decline prediction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.