A Deep and Interpretable Learning Approach for Long-Term ECG Clinical Noise Classification
Objective: In Long-Term Monitoring (LTM), noise significantly impacts the quality of the electrocardiogram (ECG), posing challenges for accurate diagnosis and time-consuming analysis. The clinical severity of noise refers to the difficulty in interpreting the clinical content of the ECG, in contrast...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universidad de Alcalá (UAH) |
| Repositorio: | e_Buah Biblioteca Digital Universidad de Alcalá |
| Idioma: | inglés |
| OAI Identifier: | oai:ebuah.uah.es:10017/64316 |
| Acceso en línea: | http://hdl.handle.net/10017/64316 https://dx.doi.org/10.1109/TBME.2024.3454545 |
| Access Level: | acceso abierto |
| Palabra clave: | Clinical noise severity Convolutional neural networks (CNN) Deep learning (DL) Electrocardiogram (ECG) Long-term monitoring (LTM) Medicina Medicine |
| Sumario: | Objective: In Long-Term Monitoring (LTM), noise significantly impacts the quality of the electrocardiogram (ECG), posing challenges for accurate diagnosis and time-consuming analysis. The clinical severity of noise refers to the difficulty in interpreting the clinical content of the ECG, in contrast to the traditional approach based on quantitative severity. In a previous study, we trained Machine Learning (ML) algorithms using a data repository labeled according to the clinical severity. In this work, we explore Deep Learning (DL) models in the same database to design architectures that provide explainability of the decision making process. Methods: We have developed two sets of Convolutional Neural Networks (CNNs): a 1-D CNN model designed from scratch, and pre-trained 2-D CNNs fine-tuned through transfer learning. Additionally, we have designed two Autoencoder (AE) architectures to provide model interpretability by exploiting the data regionalization in the latent spaces. Results: The DL systems yield superior classification performance than the previous ML approaches, achieving an F1-score up to 0.84in the test set considering patient separation to avoid intra–patient overfitting. The interpretable architectures have shown similar performance with the advantage of qualitative explanations. Conclusions: The integration of DL and interpretable systems has proven to be highly effective in classifying clinical noise in LTM ECG recordings. This approach can enhance clinicians’ confidence in clinical decision support systems based on learning methods, a key point for this technology transfer. Significance: The proposed systems can help healthcare professionals to discriminate the parts of the ECG that contain valuable information to provide a diagnosis. |
|---|