{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-label-attention-model-for-icd-coding-from","title":"A Label Attention Model for ICD Coding from Clinical Text","arxiv_id":"2007.06351","date":"2020-07-13","proceeding":null,"authors":["Thanh Vu","Dat Quoc Nguyen","Anthony Nguyen"],"abstract":"ICD coding is a process of assigning the International Classification of Disease diagnosis codes to clinical/medical notes documented by health professionals (e.g. clinicians). This process requires significant human resources, and thus is costly and prone to error. To handle the problem, machine learning has been utilized for automatic ICD coding. Previous state-of-the-art models were based on convolutional neural networks, using a single/several fixed window sizes. However, the lengths and interdependence between text fragments related to ICD codes in clinical text vary significantly, leading to the difficulty of deciding what the best window sizes are. In this paper, we propose a new label attention model for automatic ICD coding, which can handle both the various lengths and the interdependence of the ICD code related text fragments. Furthermore, as the majority of ICD codes are not frequently used, leading to the extremely imbalanced data issue, we additionally propose a hierarchical joint learning mechanism extending our label attention model to handle the issue, using the hierarchical relationships among the codes. Our label attention model achieves new state-of-the-art results on three benchmark MIMIC datasets, and the joint learning mechanism helps improve the performances for infrequent codes.","url_abs":"https://arxiv.org/abs/2007.06351v1","url_pdf":"https://arxiv.org/pdf/2007.06351v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-label-attention-model-for-icd-coding-from","repo_url":"https://github.com/aehrc/LAAT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-label-attention-model-for-icd-coding-from","repo_url":"https://github.com/joakimedin/medical-coding-reproducibility","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"medical-code-prediction","task_name":"Medical Code Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-code-prediction-on-mimic-iii","task":"Medical Code Prediction","dataset":"MIMIC-III","model":"JointLAAT","rank_in_archive_order":8,"of":18,"metrics":{"Macro-AUC":"92.1","Macro-F1":"10.7","Micro-AUC":"98.8","Micro-F1":"57.5","Precision@15":"59.0","Precision@5":"80.6","Precision@8":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iii","task":"Medical Code Prediction","dataset":"MIMIC-III","model":"LAAT","rank_in_archive_order":9,"of":18,"metrics":{"Macro-AUC":"91.9","Macro-F1":"9.9","Micro-AUC":"98.8","Micro-F1":"57.5","Precision@15":"59.1","Precision@5":"81.3","Precision@8":"73.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2007.06351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06351"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joakimedin/medical-coding-reproducibility","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aehrc/LAAT","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":4,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"4c5d457bd97c1765","entry":"AttentionLayer","repo":"aehrc/LAAT","repo_kind":"official","path":"src/models/attentions/attention_layer.py","file_url":"https://github.com/aehrc/LAAT/blob/HEAD/src/models/attentions/attention_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4c5d457bd97c1765"}},{"code_sha256_prefix":"7bde2c8ada72a8b5","entry":"LabelAttention","repo":"joakimedin/medical-coding-reproducibility","repo_kind":"listed","path":"src/models/laat.py","file_url":"https://github.com/joakimedin/medical-coding-reproducibility/blob/HEAD/src/models/laat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7bde2c8ada72a8b5"}},{"code_sha256_prefix":"8fce72e36ed56a1d","entry":"BaseModel","repo":"joakimedin/medical-coding-reproducibility","repo_kind":"listed","path":"src/models/laat.py","file_url":"https://github.com/joakimedin/medical-coding-reproducibility/blob/HEAD/src/models/laat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8fce72e36ed56a1d"}},{"code_sha256_prefix":"657373140d484555","entry":"BaseTextEncoder","repo":"joakimedin/medical-coding-reproducibility","repo_kind":"listed","path":"src/models/laat.py","file_url":"https://github.com/joakimedin/medical-coding-reproducibility/blob/HEAD/src/models/laat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"657373140d484555"}},{"code_sha256_prefix":"7d36992809c7e10b","entry":"LAAT","repo":"joakimedin/medical-coding-reproducibility","repo_kind":"listed","path":"src/models/laat.py","file_url":"https://github.com/joakimedin/medical-coding-reproducibility/blob/HEAD/src/models/laat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d36992809c7e10b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}