2026-03-15T05:56:09Z https://kagawa-u.repo.nii.ac.jp/oai

oai:kagawa-u.repo.nii.ac.jp:02000920 2025-04-30T04:27:58Z 2

Detection of atrial fibrillation from pulse waves using convolution neural networks and recurrence-based plots Kitajima, Hiroyuki 北島, 博之 キタジマ, ヒロユキ 武田, 健太郎 タケダ, ケンタロウ takeda, kentaro Ishizawa, Makoto 石澤, 真 イシザワ, マコト 合原, 一幸 アイハラ, カズユキ Aihara, Kazuyuki Minamino, Tetsuo 南野, 哲男 ミナミノ, テツオ We propose a classification method for distinguishing atrial fibrillation from sinus rhythm in pulse-wave measurements obtained with a blood pressure monitor. This method combines recurrence-based plots with convolutional neural networks. Moreover, we devised a novel plot, with which our classification achieved specificity of 97.5%, sensitivity of 98.4%, and accuracy of 98.6%. These criteria are higher than previously reported results for measurements obtained with blood pressure monitors and are almost equal to statistical measures for methods based on electrocardiographs and photoplethysmographs. journal article American Institute of Physics 2025-03-14 VoR application/pdf Chaos: An Interdisciplinary Journal of Nonlinear Science 3 35 1089-7682 https://kagawa-u.repo.nii.ac.jp/record/2000920/files/Chaos_35-3_0111.pdf https://kagawa-u.repo.nii.ac.jp/records/2000920 eng https://pubmed.ncbi.nlm.nih.gov/40085670/ https://doi.org/10.1063/5.0212068 © 2025 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND) license open access