{"paper":{"title":"Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akram Mustafa, Mostafa Rahimi Azghadi, Usman Naseem","submitted_at":"2025-07-02T00:53:54Z","abstract_excerpt":"This study evaluates how well large language models (LLMs) can classify ICD-10 codes from hospital discharge summaries, a critical but error-prone task in healthcare. Using 1,500 summaries from the MIMIC-IV dataset and focusing on the 10 most frequent ICD-10 codes, the study tested 11 LLMs, including models with and without structured reasoning capabilities. Medical terms were extracted using a clinical NLP tool (cTAKES), and models were prompted in a consistent, coder-like format. None of the models achieved an F1 score above 57%, with performance dropping as code specificity increased. Reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03001","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.03001/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}