Diagnosis of atrial fibrillation based on arterial pulse wave foot point detection using artificial neural networks

Unai Zalabarria; Eloy Irigoyen; Andrew Lowe

doi:10.1016/j.cmpb.2020.105681

Diagnosis of atrial fibrillation based on arterial pulse wave foot point detection using artificial neural networks

Comput Methods Programs Biomed. 2020 Dec:197:105681. doi: 10.1016/j.cmpb.2020.105681. Epub 2020 Aug 1.

Authors

Unai Zalabarria¹, Eloy Irigoyen², Andrew Lowe³

Affiliations

¹ Department of Systems Engineering and Automation, Faculty of Engineering of the UPV/EHU, Bilbao, 48013, Spain. Electronic address: unai.zalabarria@ehu.eus.
² Department of Systems Engineering and Automation, Faculty of Engineering of the UPV/EHU, Bilbao, 48013, Spain.
³ Institute of Biomedical Technologies, School of Engineering, Mathematical and Computer Sciences, Auckland University of Technology, Auckland, 1010, New Zealand.

PMID: 32771834
DOI: 10.1016/j.cmpb.2020.105681

Abstract

Background: Atrial fibrillation (AF) is a common arrhythmia that is strongly related to the risk of stroke. Some methods in the literature approach AF diagnosis based on cardiovascular signals of several minutes in length. However, many traditional methods utilized to monitor health status in terms of AF rely on electrocardiograms, which are time consuming and require specialized equipment to collect. By contrast, more practical systems focus on noninvasively collected short-term cardiovascular signals, such as arterial pulse waveforms (APWs).

Methods: In this paper, an AF diagnosis algorithm based on the processing of parameters extracted from short-length heart period (HP) measures is proposed. The HP is obtained by locating foot points (FPOs) in 10-second epochs of APW signals. The algorithm consists of two main stages. First, five parameters representative of the APW morphology are extracted to train an artificial neural network (ANN) model for FPO detection. The moving interpolation difference method and an improved second derivative maximum method are employed for APW parameter extraction. Second, 13 temporal-domain, frequency-domain and nonlinear HP parameters are extracted from the previously identified FPOs. These are subsequently orthogonalized using principal component analysis to train a second ANN for effective AF diagnosis.

Results: Both ANNs were trained and validated on a labeled data set with 20-fold cross-validation, achieving a mean sensitivity and specificity of 97.53% and 90.13%, respectively, for AF diagnosis and an F1 score of 99.18% for FPO identification.

Conclusions: This paper presents a validated solution for the diagnosis of AF from APW records using parameters derived from HP measures. In addition, compared to that of a commercial BP+ device, improved FPO detection performance is achieved, making the proposed algorithm a strong candidate for the automatic detection of FPOs in oscillometric devices.

Keywords: Arterial pulse waveform; Artificial intelligence; Artificial neural network; Atrial fibrillation; Foot point.

MeSH terms

Algorithms
Arteries
Atrial Fibrillation* / diagnosis
Electrocardiography
Humans
Neural Networks, Computer