Analysis of Relevant Features from Photoplethysmographic Signals for Atrial Fibrillation Classification.

Atrial Fibrillation (AF) is the most common cardiac arrhythmia found in clinical practice. It affects an estimated 33.5 million people, representing approximately 0.5% of the world's population. Electrocardiogram (ECG) is the main diagnostic criterion for AF. Recently, photoplethysmography (PPG) has emerged as a simple and portable alternative for AF detection. However, it is not completely clear which are the most important features of the PPG signal to perform this process. The objective of this paper is to determine which are the most relevant features for PPG signal analysis in the detection of AF. This study is divided into two stages: (a) a systematic review carried out following the Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies (PRISMA-DTA) statement in six databases, in order to identify the features of the PPG signal reported in the literature for the detection of AF, and (b) an experimental evaluation of them, using machine learning, in order to determine which have the greatest influence on the process of detecting AF. Forty-four features were found when analyzing the signal in the time, frequency, or time-frequency domains. From those 44 features, 27 were implemented, and through machine learning, it was found that only 11 are relevant in the detection process. An algorithm was developed for the detection of AF based on these 11 features, which obtained an optimal performance in terms of sensitivity (98.43%), specificity (99.52%), and accuracy (98.97%).

Systematic Review on Features Extracted from PPG Signals for the Detection of Atrial Fibrillation.

PROBLEM: Atrial Fibrillation (AF) is the most common sustained cardiac arrhythmia. It constitutes one of the leading cardiovascular health problems, affecting 33.5 million people of the world's population. AF detection is commonly made by an Electrocardiogram (EEG). Nevertheless, with the advances in biomedical sensors, innovative approaches have emerged on detecting AF based on the analysis of signals acquired by photoplethysmography (PPG) sensors. OBJECTIVE: This paper aims to provide a systematic review to determine the features that have been used to detect Atrial Fibrillation in PPG signals. METHODS: A systematic review of six databases (Pubmed, Science Direct, Scopus, IEEE Xplore, Engineering Village y Mendeley) was carried out following the PRISMA-DTA statement (Preferred Reporting Items for Systematic Reviews and Meta-Analyses on Diagnostic Test Accuracy). RESULTS: This article provides an analysis of the features extracted for the detection of Atrial Fibrillation in photoplethysmography signals from 16 studies. It was found 44 features: 29 were extracted from the signal analyzed in the time domain, 12 from the signal analyzed in the frequency domain, and 3 from the signal analyzed in the time-frequency domain. CONCLUSIONS: The systematic review allowed obtaining the features reported in the literature with higher performance in the detection of AF in terms of sensitivity, specificity, and accuracy. It was possible to observe a clear tendency to analyze the PPG signal in the time domain, although some studies have obtained better performance in the classification of AF when analyzing features in the frequency and time-frequency domains.