Principal component analysis and cluster analysis for measuring the local organisation of human atrial fibrillation

Abstract

The distribution of atrial electrogram types has been proposed to characterise human atrial fibrillation. The aim of this study was to provide computer procedures for evaluating the local organisation of intracardiac recordings during AF as an alternative to off-line manual classification. Principal component analysis (PCA) reduced the data set to a few representative activations, and cluster analysis (CA) measured the average dissimilarity between consecutive activations of an intracardiac signal. The data set consisted of 106 bipolar signals recorded on 11 patients during electrophysiological studies for catheter ablation. Performances of PCA and CA in distinguishing between organised (type I) and disorganised (type II/III, Wells criteria) were assessed, in comparison with manual reading, by evaluating the predictive parameters of the classification analysis. Both methods gave high accuracy (92% for PCA and 89% for CA), confirming the feasibility of on-line characterisation of AF. Sensitivity was lower than specificity (81% against 98% for PCA, and 77% against 97% for CA), with seven out of eight misclassifications of PCA in common with CA. Differences between manual and computer analysis may be related to the higher resolution of PCA and CA in the measurement of the organisation of atrial activations. These procedures are suitable for providing automatic (by CA) or semi-automatic (by PCA) measures of the extent of local organisation of AF in the pre-ablation treatment phase.

A method for quantifying atrial fibrillation organization based on wave-morphology similarity

“…In addition, a blanking period of 55 ms was imposed to avoid multiple detection of a single LAW. After wave recognition, the atrial activation times were estimated by calculating the barycenter of the waveform, i.e., as the time that divided in two equal parts the local area of the modulus of the signal [22]. For this purpose, a moving average noncausal filter with 90 coefficients was applied to the modulus of the original electrogram (1) For each detected LAW, the activation time was set on the positive zero crossing of which was closer to the local peak of .…”

Atrial Activity Extraction for Atrial Fibrillation Analysis Using Blind Source Separation

“…The multichannel signal processing standpoint adopted in the BSS approach aims at an effective utilization of the atrial information present in all ECG leads. Two main families of BSS techniques for AA extraction have been proposed, based on principal component analysis (PCA) [11], [12] and independent component analysis (ICA) [13], [14], respectively. PCA methods search for a solution, using secondorder statistics (SOSs), that decorrelates the input signals.…”

Ventricular activity cancellation in electrograms during atrial fibrillation with constraints on residuals’ power

“…The second one evaluates the beat-by-beat amplitude reduction of the peak of VA and is defined as VDR = 10log 10 R j s R j r (16) where j indicates the jth beat, R j s is the jth peak amplitude of the original AEG in a 100 ms window centered in the VA, and R j r is the jth peak amplitude of the residue (i.e., the amplitude of the residue signal at the same position of the peak on the original AEG). High positive values of VDR will indicate good performance of the algorithm.…”

“…AF organization can be described in terms of various characteristics of electrical activity of the fibrillating atria, such as the repeatability/regularity of the atrial activations [4][5][6], the correlation/synchronicity among electrograms recorded in different locations [7][8][9], or the similarity of the wave morphology [10].…”