Metraipolis › archive › dc_60dec3bec825
Multimodal Dual-Encoder Retrieval for Automated ICD Coding — arXiv:2610.04263
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04263
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:28:43.883Z
- SHA-256 of the archived text
a7e2ab96730ff5d146c9e02986556f62e0ec8f90cd467eb61f2164e568474bc6- Stable URL of this page
https://metraipolis.com/documento/dc_60dec3bec825
How to cite
Multimodal Dual-Encoder Retrieval for Automated ICD Coding — arXiv:2610.04263 — arXiv, https://arxiv.org/abs/2610.04263 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_60dec3bec825 (Metraipolis archive dc_60dec3bec825, sha256 a7e2ab96730ff5d146c9e02986556f62e0ec8f90cd467eb61f2164e568474bc6)
BibTeX
@misc{dc60dec3bec825,
title = {Multimodal Dual-Encoder Retrieval for Automated ICD Coding — arXiv:2610.04263},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04263},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_60dec3bec825; sha256 a7e2ab96730ff5d146c9e02986556f62e0ec8f90cd467eb61f2164e568474bc6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04263. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accurate International Classification of Diseases (ICD) coding is crucial for large-scale clinical research, documentation, and billing. There are three primary problems with current ICD prediction methods: (1) They are unable to comprehend multimodal patient data because they rely on either structured EHR data or unstructured clinical notes. (2) They also struggle with scalability to a larger amount of ICD codes (9K+ codes in ICD-9), as traditional classifiers need dense output layers and often do not generalize well to long tail rare diseases. (3) They lack transparency for clinical use. To address these challenges, this research proposes a two-stage framework that first retrieves ICD codes using a multimodal dual-encoder retrieval model, where structured and unstructured patient data are integrated through gated fusion. The second stage refines the top-k retrieved candidates with an LLM-based re-ranker that provides ranked codes with clinically relevant explanations. Our experiments show that the proposed approach improves Micro-F1 and Precision over a multimodal dual-fusion classifier baseline. These improvements demonstrate that combining a gated multimodal retrieval system with LLM-based re-ranking is a practical alternative to dense multi-label classification for automated ICD coding. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.04263 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:20.405Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).