Alexander M Zolotarev1,2, Brian J Hansen1, Ekaterina A Ivanova2, Katelynn M Helfrich1, Ning Li1,3, Paul M L Janssen1,3, Peter J Mohler1,3, Nahush A Mokadam3,4, Bryan A Whitson3,4, Maxim V Fedorov2, John D Hummel3,4,5, Dmitry V Dylov2, Vadim V Fedorov1,3. 1. Department of Physiology and Cell Biology and Bob and Corrine Frick Center for Heart Failure and Arrhythmia (A.M.Z., B.J.H., K.M.H., N.L., P.M.L.J., P.J.M., V.V.F.), The Ohio State University Wexner Medical Center, Columbus, OH. 2. Center of Computational and Data-Intensive Science and Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia (A.M.Z., E.A.I., M.V.F., D.V.D.). 3. Davis Heart and Lung Research Institute (N.L., P.M.L.J., P.J.M., N.A.M., B.A.W., J.D.H., V.V.F.), The Ohio State University Wexner Medical Center, Columbus, OH. 4. Division of Cardiac Surgery (N.A.M., B.A.W., J.D.H.), The Ohio State University Wexner Medical Center, Columbus, OH. 5. Department of Internal Medicine (J.D.H), The Ohio State University Wexner Medical Center, Columbus, OH.
Abstract
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 mm2 resolution) and 64-electrode MEM (higher density or lower density with 3 and 9 mm2 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.
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 mm2 resolution) and 64-electrode MEM (higher density or lower density with 3 and 9 mm2 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.
Authors: Chayakrit Krittanawong; Kipp W Johnson; Robert S Rosenson; Zhen Wang; Mehmet Aydar; Usman Baber; James K Min; W H Wilson Tang; Jonathan L Halperin; Sanjiv M Narayan Journal: Eur Heart J Date: 2019-07-01 Impact factor: 29.983
Authors: Zain Ul Abideen Asad; Ali Yousif; Muhammad Shahzeb Khan; Sana M Al-Khatib; Stavros Stavrakis Journal: Circ Arrhythm Electrophysiol Date: 2019-08-21
Authors: Arif Elvan; Andre C Linnenbank; Marnix W van Bemmel; Anand R Ramdat Misier; Peter Paul H M Delnoy; Willem P Beukema; Jacques M T de Bakker Journal: Circ Arrhythm Electrophysiol Date: 2009-12
Authors: Julian W E Jarman; Tom Wong; Pipin Kojodjojo; Hilmar Spohr; Justin E Davies; Michael Roughton; Darrel P Francis; Prapa Kanagaratnam; Vias Markides; D Wyn Davies; Nicholas S Peters Journal: Circ Arrhythm Electrophysiol Date: 2012-06-20
Authors: Awni Y Hannun; Pranav Rajpurkar; Masoumeh Haghpanahi; Geoffrey H Tison; Codie Bourn; Mintu P Turakhia; Andrew Y Ng Journal: Nat Med Date: 2019-01-07 Impact factor: 53.440
Authors: Caroline H Roney; Chris D Cantwell; Jason D Bayer; Norman A Qureshi; Phang Boon Lim; Jennifer H Tweedy; Prapa Kanagaratnam; Nicholas S Peters; Edward J Vigmond; Fu Siong Ng Journal: Circ Arrhythm Electrophysiol Date: 2017-05
Authors: Jichao Zhao; Brian J Hansen; Yufeng Wang; Thomas A Csepe; Lidiya V Sul; Alan Tang; Yiming Yuan; Ning Li; Anna Bratasz; Kimerly A Powell; Ahmet Kilic; Peter J Mohler; Paul M L Janssen; Raul Weiss; Orlando P Simonetti; John D Hummel; Vadim V Fedorov Journal: J Am Heart Assoc Date: 2017-08-22 Impact factor: 5.501
Authors: Lindsay J Young; Steve Antwi-Boasiako; Joel Ferrall; Loren E Wold; Peter J Mohler; Mona El Refaey Journal: Life Sci Date: 2022-04-03 Impact factor: 6.780
Authors: Aleksei V Mikhailov; Anuradha Kalyanasundaram; Ning Li; Shane S Scott; Esthela J Artiga; Megan M Subr; Jichao Zhao; Brian J Hansen; John D Hummel; Vadim V Fedorov Journal: J Mol Cell Cardiol Date: 2020-10-29 Impact factor: 5.000
Authors: Jordi Heijman; Henry Sutanto; Harry J G M Crijns; Stanley Nattel; Natalia A Trayanova Journal: Cardiovasc Res Date: 2021-06-16 Impact factor: 10.787