From: Assistant diagnosis with Chinese electronic medical records based on CNN and BiLSTM with phrase-level and word-level attentions
Methods
Precisionmacro(%)
Recallmacro(%)
F ‐ scoremacro(%)
Accuracy (%)
FCNBLA
92.31
90.46
91.29
92.78
SVM-TFIDF
88.37
87.73
88.02
90.76
CNN
89.94
89.40
89.64
91.97
RCNN
91.21
89.97
90.54
92.51
BiLSTM
90.91
89.45
90.10
92.13