{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/automated-medical-coding-on-mimic-iii-and","title":"Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study","arxiv_id":"2304.10909","date":"2023-04-21","proceeding":null,"authors":["Joakim Edin","Alexander Junge","Jakob D. Havtorn","Lasse Borgholt","Maria Maistro","Tuukka Ruotsalo","Lars Maaløe"],"abstract":"Medical coding is the task of assigning medical codes to clinical free-text documentation. Healthcare professionals manually assign such codes to track patient diagnoses and treatments. Automated medical coding can considerably alleviate this administrative burden. In this paper, we reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. In previous work, the macro F1 score has been calculated sub-optimally, and our correction doubles it. We contribute a revised model comparison using stratified sampling and identical experimental setups, including hyperparameters and decision boundary tuning. We analyze prediction errors to validate and falsify assumptions of previous works. The analysis confirms that all models struggle with rare codes, while long documents only have a negligible impact. Finally, we present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models. We release our code, model parameters, and new MIMIC-III and MIMIC-IV training and evaluation pipelines to accommodate fair future comparisons.","url_abs":"https://arxiv.org/abs/2304.10909v1","url_pdf":"https://arxiv.org/pdf/2304.10909v1.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":"automated-medical-coding-on-mimic-iii-and","repo_url":"https://github.com/joakimedin/medical-coding-reproducibility","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"medical-code-prediction","task_name":"Medical Code Prediction"}],"methods":[],"datasets_introduced":[{"slug":"mimic-iv-icd-10","name":"MIMIC-IV ICD-10","full_name":""},{"slug":"mimic-iv-icd-9","name":"MIMIC-IV ICD-9","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-10","model":"PLM-ICD","rank_in_archive_order":1,"of":6,"metrics":{"AUC Macro":"96.6","AUC Micro":"99.2","Exact Match Ratio":"0.4","F1 Macro":"21.1","F1 Micro":"58.5","Precision@15":"55.0","Precision@8":"69.9","R-Prec":"57.9","mAP":"61.9"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-10","model":"LAAT","rank_in_archive_order":2,"of":6,"metrics":{"AUC Macro":"95.4","AUC Micro":"99.0","Exact Match Ratio":"0.4","F1 Macro":"20.3","F1 Micro":"57.9","Precision@15":"54.3","Precision@8":"68.9","R-Prec":"57.2","mAP":"60.6"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-10","model":"MultiResCNN","rank_in_archive_order":3,"of":6,"metrics":{"AUC Macro":"94.5","AUC Micro":"99.0","Exact Match Ratio":"0.4","F1 Macro":"21.1","F1 Micro":"56.9","Precision@15":"53.5","Precision@8":"67.8","R-Prec":"56.1","mAP":"59.3"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-10","model":"CAML","rank_in_archive_order":4,"of":6,"metrics":{"AUC Macro":"91.1","AUC Micro":"98.5","Exact Match Ratio":"0.3","F1 Macro":"16.0","F1 Micro":"55.4","Precision@15":"52.2","Precision@8":"66.8","R-Prec":"54.5","mAP":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-10","model":"Bi-GRU","rank_in_archive_order":5,"of":6,"metrics":{"AUC Macro":"92.4","AUC Micro":"98.3","Exact Match Ratio":"0.3","F1 Macro":"10.6","F1 Micro":"50.1","Precision@15":"47.7","Precision@8":"62.6","R-Prec":"49.6","mAP":"51.1"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-10","model":"CNN","rank_in_archive_order":6,"of":6,"metrics":{"AUC Macro":"87.9","AUC Micro":"97.5","Exact Match Ratio":"0.3","F1 Macro":"8.0","F1 Micro":"47.2","Precision@15":"45.7","Precision@8":"60.3","R-Prec":"47.3","mAP":"48.2"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-9","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-9","model":"PLM-ICD","rank_in_archive_order":1,"of":6,"metrics":{"AUC Macro":"97.2","AUC Micro":"99.4","Exact Match Ratio":"1.0","F1 Macro":"29.8","F1 Micro":"62.6","Precision@15":"53.5","Precision@8":"70.0","R-Prec":"62.7","mAP":"68.0"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-9","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-9","model":"LAAT","rank_in_archive_order":2,"of":6,"metrics":{"AUC Macro":"96.0","AUC Micro":"99.3","Exact Match Ratio":"0.9","F1 Macro":"26.4","F1 Micro":"61.7","Precision@15":"52.7","Precision@8":"68.9","R-Prec":"61.7","mAP":"66.3"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-9","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-9","model":"MultiResCNN","rank_in_archive_order":3,"of":6,"metrics":{"AUC Macro":"95.1","AUC Micro":"99.2","Exact Match Ratio":"0.8","F1 Macro":"27.7","F1 Micro":"60.4","Precision@15":"51.8","Precision@8":"67.6","R-Prec":"60.4","mAP":"64.7"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-9","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-9","model":"Bi-GRU","rank_in_archive_order":4,"of":6,"metrics":{"AUC Macro":"93.8","AUC Micro":"98.8","Exact Match Ratio":"0.7","F1 Macro":"16.6","F1 Micro":"55.5","Precision@15":"47.8","Precision@8":"64.1","R-Prec":"55.8","mAP":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-9","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-9","model":"CAML","rank_in_archive_order":5,"of":6,"metrics":{"AUC Macro":"90.7","AUC Micro":"98.8","Exact Match Ratio":"0.6","F1 Macro":"19.3","F1 Micro":"58.6","Precision@15":"50.3","Precision@8":"66.3","R-Prec":"58.5","mAP":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-9","task":"Medical Code Prediction","dataset":"MIMIC-IV ICD-9","model":"CNN","rank_in_archive_order":6,"of":6,"metrics":{"AUC Macro":"89.4","AUC Micro":"98.1","Exact Match Ratio":"0.6","F1 Macro":"12.6","F1 Micro":"52.4","Precision@15":"45.6","Precision@8":"61.3","R-Prec":"52.9","mAP":"55.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.10909","atlas_url":"https://app.syntology.ai/?focus=2304.10909","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2304.10909"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.10909\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.10909"},"call":"get_concepts_for_paper(arxiv_id=\"2304.10909\")"}],"by_repo":[{"repo":"joakimedin/medical-coding-reproducibility","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2007.06351"],"harvested_for_calls":[{"arxiv_id":"2007.06351","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.06351"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.06351\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f075af4c137c93f3a326ea000a361c2dc70cffd7c906348b5d922993e921fa22","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}