Open access
Jul 2026
Fine-Tuned Large Language Models for Detecting Social Isolation from Unstructured Clinical Notes
Objectives: This study aimed to leverage FLAN-T5-Large, BERT, RoBERTa, and Gemma-2-2B, with fine-tuning, to identify instances of social isolation and social support within unstructured clinical notes. Materials and Methods: Annotated clinical note spans containing social context cues were used to fine-tune each model....
L. Chinthala, C. Lemon, A. Shaban-Nejad et al.
· medRxiv · 0 citations