Key result
A machine learning model applied to electrogram frequency spectra achieved an f1-score of 0.81 for detecting AF drivers using higher-density multielectrode mapping (P<0.05 vs lower-density).
Why the study?
AF driver detection by clinical surface-only multielectrode mapping has relied on subjective interpretation of activation maps.
Does machine learning applied to electrogram frequency spectra improve the accuracy of AF driver detection by multi-electrode mapping compared to optical mapping in explanted human atria?
Does machine learning applied to electrogram frequency spectra improve the accuracy of AF driver detection by multi-electrode mapping compared to optical mapping in explanted human atria?
Absolute Event Rate: 0.81% vs 0.66%
p-value: p=<0.05
A machine learning model pretrained on Fourier spectrum features accurately classifies AF drivers from multi-electrode mapping compared to an optical mapping gold-standard in explanted human atria.
May aid preclinical AF driver mapping; leaves open clinical translation and outcome impact.
Background: Atrial fibrillation (AF) can be maintained by localized intramural reentrant drivers. However, AF driver detection by clinical surface-only multielectrode mapping (MEM) has relied on subjective interpretation of activation maps. We hypothesized that application of machine learning to electrogram frequency spectra may accurately automate driver detection by MEM and add some objectivity to the interpretation of MEM findings. Methods: Temporally and spatially stable single AF drivers were mapped simultaneously in explanted human atria (n=11) by subsurface near-infrared optical mapping (NIOM; 0.3 mm 2 resolution) and 64-electrode MEM (higher density or lower density with 3 and 9 mm 2 resolution, respectively). Unipolar MEM and NIOM recordings were processed by Fourier transform analysis into 28 407 total Fourier spectra. Thirty-five features for machine learning were extracted from each Fourier spectrum. Results: Targeted driver ablation and NIOM activation maps efficiently defined the center and periphery of AF driver preferential tracks and provided validated annotations for driver versus nondriver electrodes in MEM arrays. Compared with analysis of single electrogram frequency features, averaging the features from each of the 8 neighboring electrodes, significantly improved classification of AF driver electrograms. The classification metrics increased when less strict annotation, including driver periphery electrodes, were added to driver center annotation. Notably, f1-score for the binary classification of higher-density catheter data set was significantly higher than that of lower-density catheter (0.81±0.02 versus 0.66±0.04, P <0.05). The trained algorithm correctly highlighted 86% of driver regions with higher density but only 80% with lower-density MEM arrays (81% for lower-density+higher-density arrays together). Conclusions: The machine learning model pretrained on Fourier spectrum features allows efficient classification of electrograms recordings as AF driver or nondriver compared with the NIOM gold-standard. Future application of NIOM-validated machine learning approach may improve the accuracy of AF driver detection for targeted ablation treatment in patients.
No takes yet. Share an insight, caveat, or question.
Zolotarev et al. (2020) studied Atrial fibrillation (n=11). Higher-density multielectrode mapping with machine learning vs. Lower-density multielectrode mapping with machine learning was evaluated on f1-score for binary classification of AF drivers (p=<0.05). A machine learning model applied to electrogram frequency spectra achieved an f1-score of 0.81 for detecting AF drivers using higher-density multielectrode mapping (P<0.05 vs lower-density).