Improving Barrett’s Oesophagus Surveillance Scheduling with Large Language Models: A Structured Extraction Approach

Gastroenterology (GI) cancer surveillance scheduling relies on extracting structured data from unstructured clinical texts, such as endoscopy and pathology reports.Traditional Natural Language Processing (NLP) models have been employed for this task, but recent advances in Large Language Models (LLMs) present a new opportunity for automation without requiring extensive labelled datasets.In this study, we propose an LLM-based entity extraction and rule-based decision support framework for the prediction of Barrett's oesophagus (BO) surveillance timing.Our approach processes endoscopy and pathology reports to extract clinically relevant information and structures it into a standardised format, which is then used to determine appropriate surveillance intervals.We evaluate multiple state-of-the-art LLMs on real-world clinical datasets from two hospitals, assessing their performance in accuracy and runtime.The results demonstrate that LLMs, particularly Phi-4 and (DeepSeek distilled) Qwen-2.5, can effectively automate the extraction of BO surveillance-related information with high accuracy, while Phi-4 is also efficient during inference.We also compared the trade-offs between LLMs and finetuned BERT models.Our findings indicate that LLM-based extraction methods can support clinical decision-making by providing justifications from report extractions, reducing manual workload, and improving guideline adherence in BO surveillance scheduling.