# Multimodal Dual-Encoder Retrieval for Automated ICD Coding

arXiv: https://arxiv.org/abs/2610.04263 · HTML: https://mlsanity.com/paper/2610.04263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences](https://mlsanity.com/paper/2201.11838/) (2022)
- [Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding](https://mlsanity.com/paper/2203.01515/) (2022)
- [Approximate Nearest Neighbor Search in High Dimensions](https://mlsanity.com/paper/1806.09823/) (2018)
- [Multimodal Machine Learning for Automated ICD Coding](https://mlsanity.com/paper/1810.13348/) (2018)
- [Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation](https://mlsanity.com/paper/2405.19093/) (2024)
- [TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding](https://mlsanity.com/paper/2305.18576/) (2023)

## Abstract (arXiv)

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.