Deep Learning Based Prediction of Atrial Fibrillation Disease Progression with Endocardial Electrograms in a Canine Model.
Deep Learning Based Prediction of Atrial Fibrillation Disease Progression with Endocardial Electrograms in a Canine Model.
复制标题
DOI：
10.22489/cinc.2020.291
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Ranjan R
中科院分区：
文献类型：
--
作者：
Hunt B;Kwan E;McMillan M;Dosdall D;MacLeod R;Ranjan R
我们试图确定心内膜波阵面的电模式是否含有房颤(AF)疾病进展特有的成分。犬持续性房颤模型7只，雌性，体重29±2 kg，植入刺激器后1个月、3个月、6个月用电极篮导管心内膜标测。然后训练一个50层的残差网络，将半秒的电信号样本映射到它们的源时间点。训练后的网络最终验证准确率为51.6%，测试准确率为48.5%。从测试数据集输入的1个月、3个月和6个月的F1分数分别为24%、59%和53%。采用深度学习的方法，根据房颤的时间序列进行房颤的区分是可行的。这对于根据疾病进展来区分治疗是有希望的，尽管早期时间点的低准确率可能是识别新生房颤的障碍。
We sought to determine whether electrical patterns in endocardial wavefronts contained elements specific to atrial fibrillation (AF) disease progression. A canine paced model (n=7, female mongrel, 29±2 kg) of persistent AF was endocardially mapped with a 64-electrode basket catheter during periods of AF at 1 month, 3 month, and 6 months post-implant of stimulator. A 50-layer residual network was then trained to map half-second electrogram samples to their source timepoint. The trained network achieved final validation and testing accuracies of 51.6 and 48.5% respectively. Per class F1 scores were 24%, 59%, and 53% for 1 month, 3 month, and 6 month inputs from the testing dataset. Differentiation of AF based on its time progression was shown to be feasible with a deep learning method. This is promising for differentiating treatment based on disease progression though low accuracy with earlier timepoints may be an obstacle to identifying nascent AF.
登录
查看更多内容
影响因子：
37.8
作者：
MORILLO, CA;KLEIN, GJ;GUIRAUDON, CM
通讯作者：
GUIRAUDON, CM
DOI：
10.1111/j.1540-8167.2010.01798.x
发表时间：
2010-11-01
影响因子：
2.7
作者：
Balk, Ethan M.;Garlitski, Ann C.;Ip, Stanley
通讯作者：
Ip, Stanley
影响因子：
37.8
作者：
Miyasaka, Yoko;Barnes, Marion E.;Tsang, Teresa S. M.
通讯作者：
Tsang, Teresa S. M.
影响因子：
2.7
作者：
Frick, M;Frykman, V;Rosenqvist, M
通讯作者：
Rosenqvist, M