Detection of atrial fibrillation episodes using multiple heart rate variability features in different time periods

Abstract

Circadian variations of cardiac diseases have been well known. For example, atrial fibrillation (AF) episodes show nocturnal predominance. In this study, we have developed multiple formulas that detect AF episodes in different times of the day. Heart rate variability features were calculated from randomly sampled three min ECG data. Logistic regression analyses were performed to generate three formulas for the entire day, daytime, and evening time. Compared to the first formula that disregarded the time of the day, the second formula for the daytime detection detected AF episodes more accurately (95.2% vs. 99.3%), whereas third formula for the evening time detection did less accurately (93.8%). These results suggest the detection of AF episodes might become more accurate by considering the time-dependent changes of HRV features. In addition, the detection method for the evening time requires further investigation.

Detection of atrial fibrillation using contactless facial video monitoring

“…(14), (15), (16) These are : Standard Deviation of Normal to Normal cardiac contractions from ECG and peak interval for the pulsatile signal (SDNN), Root means square differences of intervals (RMSSD), Lorenz plot method: standard deviation of the minor axis (SD1) and of the major axis (SD2). These factors were computed from the RR intervals detected from the ECG signals (manual and automatic measurements) and the pulse intervals extracted from the VPG waveforms.…”

Robust genetic programming‐based detection of atrial fibrillation using RR intervals

“…These features are popular predictive parameters in AF detection literature (e.g. Kim et al ., ; Mohebbi & Ghassemian, ). The box‐plots and the feature space plots of the three selected features are presented in Figures and , respectively.…”

“…The irregularity in RR intervals has previously been obtained by simple methods which try to quantify randomness of RR intervals such as variance of RR intervals (Tateno & Glass, 2000Logan & Healey, 2005). More complicated methods for AF detection usually construct a model to determine the RR irregularity such as neural network (Guler & Ubeyli, 2005;Kara & Okandan, 2007;Polat & Gunes, 2007), Markov (Young et al, 1999) and logistic regression (Kim et al, 2008) models. Mohebbi and Ghassemian (2008), Asl et al (2008) and Ubeyli (2009) used a support vector machine algorithm to detect AF episodes using the linear and non-linear features of HRV.…”

Pro-Detection of Atrial Fibrillation Using Mixture of Experts

“…Several researchers have addressed the AF arrhythmia detection problem using the ECG signals directly or by analyzing the heart rate variability signal [28]- [33]. Table 3 shows the testing results obtained by different methods.…”

“…More precise approaches for AF detection commonly build a model to define RR irregularity. Some of these methods involve neural networks [3], the Markov model [15], and logistic regression [16]. Mohebbi and Ghassemian [17] used a support vector machine algorithm to detect AF episodes using the linear and nonlinear features of HRV.…”