Human-assisted vs. deep learning feature extraction: an evaluation of ECG features extraction methods for arrhythmia classification using machine learning

• Autor(a) principal: Montenegro, Larissa
• Data de Publicação: 2022
• Outros Autores: Abreu, Mariana, Fred, Ana, Machado, José Manuel
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://hdl.handle.net/1822/80331
• topic: heart arrhythmia; convolutional neural network; support vector machines; handcrafted features; deep features; Engenharia e Tecnologia::Engenharia Médica; Science & Technology

The success of arrhythmia classification tasks with Machine Learning (ML) algorithms is based on the handcrafting extraction of features from Electrocardiography (ECG) signals. However, feature extraction is a time-consuming trial-and-error approach. Deep Neural Network (DNN) algorithms bypass the process of handcrafting feature extraction since the algorithm extracts the features automatically in their hidden layers. However, it is important to have access to a balanced dataset for algorithm training. In this exploratory research study, we will compare the evaluation metrics among Convolutional Neural Networks (1D-CNN) and Support Vector Machines (SVM) using a dataset based on the merged public ECG signals database TNMG and CINC17 databases. Results: Both algorithms showed good performance using the new, merged ECG database. For evaluation metrics, the 1D-CNN algorithm has a precision of 93.04%, an accuracy of 93.07%, a recall of 93.20%, and an F1-score of 93.05%. The SVM classifier (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> = 10, <i>C</i> = 10 × 10⁹) achieved the best classification metrics with two combined, handcrafted feature extraction methods: Wavelet transforms and R-peak Interval features, which achieved an overall precision of 89.04%, accuracy of 92.00%, recall of 94.20%, and F1-score of 91.54%. As an unique input feature and SVM (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>λ</mi><mo>=</mo><mn>10</mn><mo>,</mo><mi>C</mi><mo>=</mo><mn>100</mn></mrow></semantics></math></inline-formula>), wavelet transforms achieved precision, accuracy, recall, and F1-score metrics of 86.15%, 85.33%, 81.16%, and 83.58%. Conclusion: Researchers face a challenge in finding a broad dataset to evaluate ML models. One way to solve this problem, especially for deep learning models, is to combine several public datasets to increase the amount of data. The SVM and 1D-CNN algorithms showed positive results with the merge of databases, showing similar F1-score, precision, and recall during arrhythmia classification. Despite the favorable results for both of them, it should be considered that in the SVM, feature selection is a time-consuming trial-and-error process; meanwhile, CNN algorithms can reduce the workload significantly. The disadvantage of CNN algorithms is that it has a higher computational processing cost; moreover, in the absence of access to powerful computational processing, the SVM can be a reliable solution.