Prediction of ICD Codes with Clinical BERT Embeddings and Text Augmentation with Label Balancing using MIMIC-III

Anish Philip; Brent Biseda; Gaurav Desai; Haifeng Lin

REVIEW

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2008.10492 v1 pith:W5XCLSRG submitted 2020-08-24 cs.CL cs.AI

Prediction of ICD Codes with Clinical BERT Embeddings and Text Augmentation with Label Balancing using MIMIC-III

Brent Biseda , Gaurav Desai , Haifeng Lin , Anish Philip This is my paper

classification cs.CL cs.AI

keywords augmentationcodespredictiontextbalancingbertclinicalcode

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

This paper achieves state of the art results for the ICD code prediction task using the MIMIC-III dataset. This was achieved through the use of Clinical BERT (Alsentzer et al., 2019). embeddings and text augmentation and label balancing to improve F1 scores for both ICD Chapter as well as ICD disease codes. We attribute the improved performance mainly to the use of novel text augmentation to shuffle the order of sentences during training. In comparison to the Top-32 ICD code prediction (Keyang Xu, et. al.) with an F1 score of 0.76, we achieve a final F1 score of 0.75 but on a total of the top 50 ICD codes.

Prediction of ICD Codes with Clinical BERT Embeddings and Text Augmentation with Label Balancing using MIMIC-III

discussion (0)