Automated ICD Classification of Psychiatric Diagnoses: From Classical NLP to Large Language Models

TL;DR

This study explores automating psychiatric diagnosis coding from free-text descriptions using NLP and ML, highlighting the superior performance of transformer-based LLMs like e5_large.

Contribution

It evaluates various text representation methods, demonstrating that fine-tuned LLMs significantly improve ICD classification accuracy in psychiatric texts.

Findings

Transformer embeddings outperform traditional models.

e5_large achieved an F1_micro score of 0.866.

Adapting LLMs to clinical language addresses long-tail and ambiguity issues.

Abstract

Mental health has become a global priority, leading to a massive administrative burden in the coding of clinical diagnoses. This study proposes the automation of psychiatric diagnostic analysis by mapping free-text descriptions to the International Classification of Diseases (ICD) using Natural Language Processing (NLP) and Machine Learning (ML) techniques. Utilizing a specialized dataset of 145,513 Spanish psychiatric descriptions, various text representation paradigms were evaluated, ranging from classical frequency-based models (BoW, TF-IDF) to state-of-the-art Large Language Models (LLMs) such as e5\_large, BioLORD, and Llama-3-8B. Results indicate that transformer-based embeddings consistently outperform traditional methods by capturing implicit semantic cues and nuanced medical terminology. The e5\_large model, through end-to-end fine-tuning, achieved the highest performance with a $F1_{micro}$ score of 0.866. This research demonstrates that adapting LLMs to specific clinical nomenclature is essential for overcoming the challenges of ``long-tail'' label distributions and the inherent ambiguity of psychiatric discourse.