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.