ACL Findings2026
Travel on the ICD Tree: Benchmarking Agentic Reasoning for ICD Coding from Chinese Electronic Medical Records
Xinjie Xu, Yongqi Fan, Shuang-shuang Chen, Qi Ye, Weibin Guo, Xinxuan Hu
Abstract
Accurate International Classification of Diseases (ICD) coding is crucial for hospital management and healthcare data governance. In clinical practice, straightforward cases can often be matched directly to ICD codes via diagnostic text, establishing retrieval-based methods as the baseline. More advanced approaches leverage large language models to rerank these results. However, real-world coding scenarios are typically more complex, demanding reasoning that goes beyond superficial descriptions. For instance, it involves synthesizing key information such as disease subtype, anatomical location, and complications from complex progress notes to accurately identify the primary diagnosis. However, a comprehensive evaluation framework for ICD coding based on complete EMRs is still lacking. To address these challenges, we constructed the Code4Detail dataset, which comprises 560 real clinical records covering 434 common diseases across 19 core chapters of ICD-10. To systematically explore the capability boundaries of large language models under different paradigms, we further propose the Travel on the ICD Tree (ToT-ICD) evaluation framework. Unlike the conventional retrieval-recall approach, ToT-ICD treats ICD coding as a structured exploration process across a hierarchical taxonomy. We design an agentic workflow that integrates similarity retrieval, path-guided navigation, and dynamic backtracking, enabling logical reasoning and decision-making under coding rules.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on8
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- OneRec-Think: In-Text Reasoning for Generative RecommendationZhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang et al.ACL 2026 · 48 citations
- Multi-Label Few-Shot ICD Coding as Autoregressive Generation with PromptZhichao Yang, Sunjae Kwon, Zonghai Yao, Hong YuAAAI 2023 · 29 citations
- MedCoT: Medical Chain of Thought via Hierarchical ExpertJiaxiang Liu, Yuan Wang, Jiawei Du, Joey Zhou et al.EMNLP 2024 · 15 citations
- LGFat-RGCN: Faster Attention with Heterogeneous RGCN for Medical ICD Coding GenerationZhenghan Chen, Changzeng Fu, Ruoxue Wu, Ye Wang et al.ACM MM 2023 · 7 citations
Related papers
- Code Like Humans: A Multi-Agent Solution for Medical CodingAndreas Geert Motzfeldt, Joakim Edin, Casper L. Christensen, Christian Hardmeier et al.EMNLP Findings 2025 · 5 citations
- ICDAGENT: Empowering Agentic Large Language Models for Explainable Medical CodingZiyi Yin, Yuanpu Cao, Ting Wang, Jinghui Chen et al.ACL 2026
- Large Language Models Are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated RationalesTaeyoon Kwon, Kai Tzu-iunn Ong, Dongjin Kang, Seungjun Moon et al.AAAI 2024 · 71 citations
- Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive LearningChang Lu, Chandan K. Reddy, Ping Wang, Yue NingNeurIPS 2023 · 10 citations
- A Two-Stage Decoder for Efficient ICD CodingThanh-Tung Nguyen, Viktor Schlegel, Abhinav Ramesh Kashyap, Stefan WinklerACL Findings 2023 · 11 citations
