Papers › Automatic ICD Coding Exploiting Discourse Structure and Reconciled Code Embeddings

Automatic ICD Coding Exploiting Discourse Structure and Reconciled Code Embeddings

1 Oct 2022COLING 2022 10archive 2025-07-28

Shurui Zhang, Bozheng Zhang, Fuxin Zhang, Bo Sang, Wanchun Yang

The International Classification of Diseases (ICD) is the foundation of global health statistics and epidemiology. The ICD is designed to translate health conditions into alphanumeric codes. A number of approaches have been proposed for automatic ICD coding, since manual coding is labor-intensive and there is a global shortage of healthcare workers. However, existing studies did not exploit the discourse structure of clinical notes, which provides rich contextual information for code assignment. In this paper, we exploit the discourse structure by leveraging section type classification and section type embeddings. We also focus on the class-imbalanced problem and the heterogeneous writing style between clinical notes and ICD code definitions. The proposed reconciled embedding approach is able to tackle them simultaneously. Experimental results on the MIMIC dataset show that our model outperforms all previous state-of-the-art models by a large margin. The source code is available at https://github.com/discnet2022/discnet

PaperPDFCode

Code

discnet2022/discnet officialmentioned in paperpytorch 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

EpidemiologyMedical Code Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Code Prediction MIMIC-III Discnet+RE Macro-AUC 95.6 #5 of 18 Archive leaderboard report
Medical Code Prediction MIMIC-III Discnet+RE Macro-F1 14.0 #5 of 18 Archive leaderboard report
Medical Code Prediction MIMIC-III Discnet+RE Micro-AUC 99.3 #5 of 18 Archive leaderboard report
Medical Code Prediction MIMIC-III Discnet+RE Micro-F1 58.8 #5 of 18 Archive leaderboard report
Medical Code Prediction MIMIC-III Discnet+RE Precision@15 61.4 #5 of 18 Archive leaderboard report
Medical Code Prediction MIMIC-III Discnet+RE Precision@8 76.5 #5 of 18 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.

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