Single-lead electrocardiogram quality assessment in the context of paroxysmal atrial fibrillation through phase space plots
[EN] Current wearable electrocardiogram (ECG) recording systems have great potential to revolutionize early diagnosis of paroxysmal atrial fibrillation (AF). They are able to continuously acquire an ECG signal for long weeks and then increase the probability of detecting first brief, intermittent si...
| Autores: | , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2024 |
| País: | España |
| Institución: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | inglés |
| OAI Identifier: | oai:riunet.upv.es:10251/203675 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/203675 |
| Access Level: | acceso abierto |
| Palabra clave: | Signal quality assessment Paroxysmal atrial fibrillation Phase space portraits Machine learning classifiers Deep learning algorithms TECNOLOGIA ELECTRONICA |
| Sumario: | [EN] Current wearable electrocardiogram (ECG) recording systems have great potential to revolutionize early diagnosis of paroxysmal atrial fibrillation (AF). They are able to continuously acquire an ECG signal for long weeks and then increase the probability of detecting first brief, intermittent signs of the arrhythmia. However, the recorded signal is often broadly corrupted by noise and artifacts, and accurate assessment of its quality to avoid automated misdiagnosis and false alarms of AF is still an unsolved challenge. In this context, the present work is pioneer in exploring the usefulness of transforming the single-lead ECG signal into two common phase space (PS) representations, such as the Poincare plot and the first order difference graph, for evaluation of its quality. Several machine and deep learning models fed with features and images derived from these PS portraits reported a better performance than well-known previous methods, even when they were trained and validated on two separate databases. Indeed, in binary classification of high- and low-quality ECG excerpts, the generated PS-based algorithms reported a discriminant power greater than 85%, misclassifying less than 20% of high-quality AF episodes and non -normal rhythms as noisy excerpts. Moreover, because both PS reconstructions do not require any mathematical transformation, these algorithms also spent much less time in classifying each ECG excerpt in validation and testing stages than previous methods. As a consequence, ECG transformation to both PS portraits enables novel, simple, effective, and computational low-cost techniques, based both on machine and deep learning classifiers, for ECG quality assessment. |
|---|