From: Medical code prediction via capsule networks and ICD knowledge
Methods
Macro F1 (%)
Micro F1 (%)
Test loss (%)
Top-10 recall (%)
LRKSI [32]
19.6
55.7
5.5
73.8
RNNKSI [32]
24.4
66.2
3.0
79.8
CNNKSI [32]
23.7
63.7
3.9
77.5
CAML [16]
25.7
65.6
3.2
80.6
LEAM [13]
24.9
64.9
–
BiCapsNetLE
26.5
67.5
2.9
82.3
