Automated ICD Classification of Psychiatric Diagnoses: From Classical NLP to Large Language Models
For clinical coding in mental health, this work demonstrates that transformer-based LLMs significantly outperform classical methods, addressing long-tail label distributions and ambiguity.
This study automates psychiatric diagnosis coding by mapping free-text descriptions to ICD codes using NLP and ML, achieving a top F1_micro score of 0.866 with a fine-tuned e5_large model on a Spanish dataset of 145,513 descriptions.
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.