Skip to main content
. 2018 Oct 24;1:60. doi: 10.1038/s41746-018-0067-8

Fig. 3.

Fig. 3

Performance comparison on PP. We compare the per-disease code F1 score between baseline LSTM model and DeepTag model on the PP dataset. The disease codes are sorted from the least frequent to the most frequent in the training dataset, which comes from CSU