Skip to main content
. Author manuscript; available in PMC: 2018 Nov 1.
Published in final edited form as: Proceedings (IEEE Int Conf Bioinformatics Biomed). 2017 Dec 18;2017:764–769. doi: 10.1109/BIBM.2017.8217752

TABLE III.

Performance of predicting medical codes of the next visit. The average and standard error of Top-k recall (k=20, 30, 40) are provided.

Model Top-20 recall Top-30 recall Top-40 recall
Concatenation-One 0.489±0.004 0.590±0.004 0.661±0.004
SVD 0.478±0.004 0.588±0.004 0.652±0.004
LDA 0.431±0.004 0.530±0.004 0.605±0.004
Codes-JointSG 0.499±0.003 0.592±0.003 0.662±0.003
Words-JointSG 0.437±0.004 0.536±0.004 0.609±0.004
Concatenation-JointSG 0.506±0.003 0.599±0.003 0.670±0.003