PaperScope
LIVE · 2026-09-15 05:40 UTC

Understanding the Limits of Agentic ICD Coding

Chong Yock Eng, Yushi Cao, Yiming Chen, Kezhi Mao, Hongchao Jiang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.13806 v1
Category
Submitted
2026-09-12

Abstract

ICD-10-CM codes are alphanumeric codes used in the US to classify diagnoses and injuries for medical billing and epidemiological reporting. Standard ICD-10-CM benchmarks report aggregate metrics that obscure performance on complex coding scenarios. We evaluate neural, workflow, and agentic systems on a rarity-stratified set of MIMIC-IV discharge summaries and identify two orthogonal failure modes. Neural classifiers exhibit a 0.43 micro-F1 gap between rare and common codes. Workflow systems handle rare codes well but score near zero on injury and external cause codes that require multi-step guideline following. A tool-augmented agentic configuration with structured access to official ICD-10-CM reference materials recovers up to 0.34 micro-F1 on this subset. No single system dominates across all conditions.

Comment: Accepted to EMNLP 2026 Main Conference

arXiv abs page · PDF · same-day batch