MedDCR: Learning to Design Agentic Workflows for Medical Coding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Jiyang, Nassar, Islam, Vu, Thanh, Zhong, Xu, Lin, Yang, Liu, Tongliang, Duong, Long, Li, Yuan-Fang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908659493109760
author Zheng, Jiyang
Nassar, Islam
Vu, Thanh
Zhong, Xu
Lin, Yang
Liu, Tongliang
Duong, Long
Li, Yuan-Fang
author_facet Zheng, Jiyang
Nassar, Islam
Vu, Thanh
Zhong, Xu
Lin, Yang
Liu, Tongliang
Duong, Long
Li, Yuan-Fang
contents Medical coding converts free-text clinical notes into standardized diagnostic and procedural codes, which are essential for billing, hospital operations, and medical research. Unlike ordinary text classification, it requires multi-step reasoning: extracting diagnostic concepts, applying guideline constraints, mapping to hierarchical codebooks, and ensuring cross-document consistency. Recent advances leverage agentic LLMs, but most rely on rigid, manually crafted workflows that fail to capture the nuance and variability of real-world documentation, leaving open the question of how to systematically learn effective workflows. We present MedDCR, a closed-loop framework that treats workflow design as a learning problem. A Designer proposes workflows, a Coder executes them, and a Reflector evaluates predictions and provides constructive feedback, while a memory archive preserves prior designs for reuse and iterative refinement. On benchmark datasets, MedDCR outperforms state-of-the-art baselines and produces interpretable, adaptable workflows that better reflect real coding practice, improving both the reliability and trustworthiness of automated systems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedDCR: Learning to Design Agentic Workflows for Medical Coding
Zheng, Jiyang
Nassar, Islam
Vu, Thanh
Zhong, Xu
Lin, Yang
Liu, Tongliang
Duong, Long
Li, Yuan-Fang
Artificial Intelligence
Multiagent Systems
Medical coding converts free-text clinical notes into standardized diagnostic and procedural codes, which are essential for billing, hospital operations, and medical research. Unlike ordinary text classification, it requires multi-step reasoning: extracting diagnostic concepts, applying guideline constraints, mapping to hierarchical codebooks, and ensuring cross-document consistency. Recent advances leverage agentic LLMs, but most rely on rigid, manually crafted workflows that fail to capture the nuance and variability of real-world documentation, leaving open the question of how to systematically learn effective workflows. We present MedDCR, a closed-loop framework that treats workflow design as a learning problem. A Designer proposes workflows, a Coder executes them, and a Reflector evaluates predictions and provides constructive feedback, while a memory archive preserves prior designs for reuse and iterative refinement. On benchmark datasets, MedDCR outperforms state-of-the-art baselines and produces interpretable, adaptable workflows that better reflect real coding practice, improving both the reliability and trustworthiness of automated systems.
title MedDCR: Learning to Design Agentic Workflows for Medical Coding
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2511.13361