TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding

Challenge:	Existing methods to automatically assign ICD codes ignore crucial information contained in structured medical data, which is hard to be captured from the noisy clinical notes.
Approach:	They propose to use a Tree-enhanced multimodal attention network to fuse tabular features and textual features into multimodal representations by enhancing the text representations with tree-based features.
Outcome:	The proposed method outperforms state-of-the-art methods on two MIMIC datasets.

Similar Papers

Overview

Challenge

Approach

Outcome

A Neural Architecture for Automated ICD Coding (P18-1)

Copied to clipboard

Pengtao Xie, Eric Xing

Challenge:	Medical coding is time-consuming, expensive, and error prone.
Approach:	They propose to use diagnosis descriptions (DDs) of a patient as inputs to select the most relevant ICD codes.
Outcome:	The proposed algorithms perform on a clinical dataset with 59K patient visits.

Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification (2024.lrec-main)

Copied to clipboard

Xindi Wang, Robert E. Mercer, Frank Rudzicz

Information Retrieval

Challenge:	Existing methods for ICD indexing use machine learning to assign subset of codes to medical records . experimental results show proposed method achieves state-of-the-art performance on a number of measures.
Approach:	They propose a method that uses a deep dilated residual convolution encoder to learn document representations across different lengths of the texts.
Outcome:	The proposed method achieves state-of-the-art performance on a number of measures.

Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings (2024.eacl-long)

Copied to clipboard

Goncalo Gomes, Isabel Coutinho, Bruno Martins

Semantic Text Processing

Challenge:	Existing approaches to assigning ICD codes to clinical text are time-consuming, labor intensive, and error-prone.
Approach:	They propose to adapt a Transformer-based model to a longformer model and use it to encode clinical narratives.
Outcome:	The proposed approach outperforms current state-of-the-art models in ICD coding with the label embeddings contributing to the good performance.

Ontological attention ensembles for capturing semantic concepts in ICD code prediction from clinical text (D19-62)

Copied to clipboard

Matus Falis, Maciej Pajak, Aneta Lisowska, Patrick Schrempf, Lucas Deckers, Shadia Mikhael, Sotirios Tsaftaris, Alison O’Neil

Semantic Text Processing

Challenge:	a semantically interpretable system for automated ICD coding of clinical text documents is presented . coding errors may result in unpaid claims and loss of revenue, authors argue .
Approach:	They propose a semantically interpretable system for automated ICD coding of clinical text documents.
Outcome:	The proposed system improves on the MIMIC-III dataset by 2.7% relative to the previous state of the art.

Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes (2020.acl-demos)

Copied to clipboard

Pengfei Cao, Chenwei Yan, Xiangling Fu, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu, Weifeng Chong

Explainability & Interpretability in NLP

Challenge:	Existing methods of automatic coding prediction have been successful, but the interpretability of predicted codes is a challenge.
Approach:	They propose an online system that can predict ICD codes for Chinese clinical notes by using a Dilated Convolutional Attention network with N-gram Matching mechanism.
Outcome:	The proposed system is able to provide supporting information in clinical decision making.

Evaluation and LLM-Guided Learning of ICD Coding Rationales (2026.eacl-long)

Copied to clipboard

Mingyang Li, Viktor Schlegel, Tingting Mu, Wuraola Oyewusi, Kai Kang, Goran Nenadic

Responsible & Trustworthy NLP

Challenge:	Existing studies on the explainability of ICD coding rely on attention-based rationales and qualitative assessments conducted by physicians.
Approach:	They propose to evaluate the explainability of rationales in ICD coding using a multi-granular rationale-annotated dataset.
Outcome:	The proposed model improves the explainability of rationales in ICD coding by using human-annotated rationale-announced rationale models.

Fusion: Towards Automated ICD Coding via Feature Compression (2021.findings-acl)

Copied to clipboard

Junyu Luo, Cao Xiao, Lucas Glass, Jimeng Sun, Fenglong Ma

Challenge:	Existing methods to assign ICD codes from unstructured clinical notes are noisy and prone to errors.
Approach:	They propose a feature compressed ICD coding model called Fusion to address this problem.
Outcome:	The proposed model outperforms existing models on two widely used datasets.

Scalable Wide and Deep Learning for Computer Assisted Coding (N18-3)

Copied to clipboard

Marilisa Amoia, Frank Diehl, Jesus Gimenez, Joel Pinto, Raphael Schumann, Fabian Stemmer, Paul Vozila, Yi Zhang

Programming Languages in NLP

Challenge:	In recent years the use of electronic medical records has accelerated resulting in large volumes of medical data when a patient visits a healthcare facility.
Approach:	They propose to use convolutional neural networks and logistic regression to build a machine learning based system for predicting ICD-10 codes from electronic medical records.
Outcome:	The proposed system can predict ICD-10 codes from electronic medical records using convolutional neural networks and logistic regression models.

Travel on the ICD Tree: Benchmarking Agentic Reasoning for ICD Coding from Chinese Electronic Medical Records (2026.findings-acl)

Copied to clipboard

Xinjie Xu, Yongqi Fan, Shuang-shuang Chen, Qi Ye, Weibin Guo, Xinxuan Hu

Semantic Text Processing

Challenge:	Accurate International Classification of Diseases (ICD) coding is crucial for hospital management and healthcare data governance.
Approach:	They propose a framework to evaluate ICD coding based on complete EMRs . they use a dataset of 560 real clinical records covering 434 common diseases .
Outcome:	The proposed framework explores the capability boundaries of large language models under different paradigms.

ICDAGENT: Empowering Agentic Large Language Models for Explainable Medical Coding (2026.acl-long)

Copied to clipboard

Ziyi Yin, Yuanpu Cao, Ting Wang, Jinghui Chen, Fenglong Ma

Responsible & Trustworthy NLP

Challenge:	Existing models lack convincing, human-understandable explanations, making them difficult for physicians to trust and use in practice.
Approach:	They propose a framework that aims to automatically assign ICD codes to clinical notes while providing explicit justifications for each assignment.
Outcome:	The proposed framework achieves effective ICD coding with accurate explanations using two collaborative LLM agents: a coding agent and a critical agent.