High-fidelity parameter-efficient fine-tuning for joint recognition and linking of diagnoses to ICD-10 in non-standard primary care notes

Joint recognition and ICD-10 linking of diagnoses in bilingual, non-standard Spanish and Catalan primary-care notes is challenging. We evaluate Parameter-Efficient Fine-Tuning (PEFT) techniques as a resource-conscious alternative to full fine-tuning (FFT) for multi-label clinical text classification. On a corpus of 21,812 Catalan and Spanish clinical notes from Catalonia, we compared the PEFT techniques LoRA, DoRA, LoHA, LoKR, and QLoRA applied to multilingual transformers (BERT, RoBERTa, DistilBERT, mDeBERTa). FFT delivered the best strict Micro-F1 (63.0), but BERT-QLoRA scored 62.2, only 0.8 points lower, while reducing trainable parameters by 67.5% and memory by 33.7%. Training on combined bilingual data consistently improved generalization across individual languages. The small FFT margin was confined to rare labels, indicating limited benefit from updating all parameters. Among PEFT techniques, QLoRA offered the strongest accuracy–efficiency balance; LoRA and DoRA were competitive, whereas LoHA and LoKR incurred larger losses. Adapter rank mattered: ranks below 128 sharply degraded Micro-F1. The substantial memory savings enable deployment on commodity GPUs while delivering performance very close to FFT. PEFT, particularly QLoRA, supports accurate and memory-efficient joint entity recognition and ICD-10 linking in multilingual, low-resource clinical settings.