Papers for

insurance coding services

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Icd coding systems struggle with rare and complex medical cases

Understanding the Limits of Agentic ICD Coding

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.

Sat 12 SeptComputation and LanguageArtificial IntelligenceMachine Learning

The gist

ICD-10-CM codes help classify medical diagnoses but some codes are harder to assign than others. The authors studied how different AI and rule-based systems perform on common and rare codes in hospital records. They found that AI systems often miss rare codes, while workflow-based systems struggle with complex injury codes. An enhanced system that uses official guidelines helped improve coding for the toughest cases, but no system worked best for all types of codes.

Open → 2609.13806v1