aiqbench analysis
This research introduces a multimodal dual-encoder retrieval framework combined with LLM-based re-ranking to address scalability and transparency issues in automated ICD coding. By integrating structured EHR data with unstructured clinical notes through gated fusion, the approach improves precision over traditional dense multi-label classifiers while providing clinically relevant explanations for rare disease codes. The study demonstrates that this retrieval-and-rank architecture offers a practical alternative to existing methods for handling large-scale medical code prediction.
Multimodal Dual-Encoder Retrieval for Automated ICD Coding
arXiv:2610.04263v1 Announce Type: cross Abstract: 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.
Abstract: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.
Information Retrieval (cs.IR); Computation and Language (cs.CL)
arXiv:2610.04263 [cs.IR]
(or arXiv:2610.04263v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2610.04263 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 281 words
Related coverage
Six Principles of Voice Design: Designing for the Ear and Encoding It into Agent Script
Salesforce Blog · Oct 8, 2026
[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
Latent Space · Oct 16, 2026
NeoMME: an efficient Multimodal-native and Multilingual Encoder
Hugging Face · Sep 3, 2026
Promptimus: Improving already good LLM prompts with zero manual engineering
Amazon Science · May 14, 2026