Papers › Medical Code Prediction from Discharge Summary: Document to Sequence BERT using...

Medical Code Prediction from Discharge Summary: Document to Sequence BERT using Sequence Attention

15 Jun 2021arXiv:2106.07932archive 2025-07-28

Tak-Sung Heo, Yongmin Yoo, Yeongjoon Park, Byeong-Cheol Jo, Kyungsun Kim

Clinical notes are unstructured text generated by clinicians during patient encounters. Clinical notes are usually accompanied by a set of metadata codes from the International Classification of Diseases(ICD). ICD code is an important code used in various operations, including insurance, reimbursement, medical diagnosis, etc. Therefore, it is important to classify ICD codes quickly and accurately. However, annotating these codes is costly and time-consuming. So we propose a model based on bidirectional encoder representations from transformers (BERT) using the sequence attention method for automatic ICD code assignment. We evaluate our approach on the medical information mart for intensive care III (MIMIC-III) benchmark dataset. Our model achieved performance of macro-averaged F1: 0.62898 and micro-averaged F1: 0.68555 and is performing better than a performance of the state-of-the-art model using the MIMIC-III dataset. The contribution of this study proposes a method of using BERT that can be applied to documents and a sequence attention method that can capture important sequence in-formation appearing in documents.

Paper PDF Code

Code

HeoTaksung/Document-to-Sequence-BERT officialmentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Medical Code Prediction Medical Diagnosis Multi-Label Text Classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Multi-Label Text Classification	MIMIC-III-50	D2SBERT using Sequence Attention	Micro-F1	68.555	#1 of 2	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections