Table 3 The performance of our model and the baseline models on the MIMIC-III dataset
From: Medical code prediction via capsule networks and ICD knowledge
Methods | Macro F1 (%) | Micro F1 (%) | Test loss (%) | Top-10 recall (%) |
|---|---|---|---|---|
CNN | 21.4 | 62.6 | 4.0 | 75.3 |
LSTM | 20.4 | 65.3 | 3.2 | 77.2 |
CapsNet | 21.8 | 64.7 | 3.5 | 76.1 |
BiCapsNetLE | 26.5 | 67.5 | 2.9 | 82.3 |