Retrieval-Augmented Generation for ICD-10 Coding in German Clinical Texts - A Technical Case Report

Manual ICD-10 coding of German clinical texts is time-consuming and error-prone. This project aims to develop a semi-automated pipeline for efficient coding of unstructured medical documentation.

Existing approaches often rely on fine-tuned language models that require large datasets and perform poorly on rare codes, particularly in low-resource languages such as German.

The proposed system integrates Named Entity Recognition, semantic and lexical retrieval, abbreviation resolution, and context-aware normalization within a Retrieval-Augmented Generation (RAG) framework using a compact generative model.

The pipeline utilizes Sentence-BERT embeddings, FAISS indexing, and the Mistral-Small-Instruct model. ICD codes are assigned through a combination of semantic similarity and generative refinement among the top retrieval candidates.

Major sources of error were found in semantic retrieval and diagnosis normalization. Future improvements should focus on domain-specific German embeddings, more robust abbreviation handling, and enhanced context-aware prompting to increase accuracy and usability in clinical environments.