基于模式识别和集成CNN-LSTM的阵发性房颤预测模型
杨萍,王丹,康子健,李童,付利华,余悦任

Prediction model of paroxysmal atrial fibrillation based on pattern recognition and ensemble CNN-LSTM
Ping YANG,Dan WANG,Zi-jian KAGN,Tong LI,Li-hua FU,Yue-ren YU
表 5 模型在跨患者模式下的实验结果
Tab.5 Experimental results of models under inter-patient paradigm
文献 训练集 测试集 ACC/% SEN/% SPE/%
Thong等[28] 76.0 68.0 86.0
Zong等[29] 80.0
本研究方法 P06~P25,n11~n50 P01~p05,n01~n10 86.9 82.4 90.0
P01~P05,P11~P25,n01~n10,n21~n50 P06~P10,n11~n20 70.6 60.0 73.1
P01~p10,p16~p25,n01~n20,n31~n50 P11~p15,n31~n30 77.9 76.9 78.2
P01~p15,P21~p25,n01~n30,n41~n50 P16~p20,n31~n40 89.9 89.7 89.9
P01~p20,n01~n40 P21~p25,n41~n50 78.5 67.2 83.1
平均值 80.6 75.7 82.7