Causality extraction from medical text using Large Language Models (LLMs)

Abstract: This study explores the potential of natural LLMs, including LLMs, to extract causal relations from medical texts, specifically from Clinical Practice Guidelines (CPGs). The outcomes causality extraction from Clinical Practice Guidelines for gestational diabetes are presented, marking a first in the field. We report on a set of experiments using variants of BERT (BioBERT, DistilBERT, and BERT) and using LLMs, namely GPT-4 and LLAMA2. Our experiments show that BioBERT performed better than other models, including the LLMs, with an average F1-score of 0.72. GPT-4 and LLAMA2 results show similar performance but less consistency. We also release the code and an annotated a corpus of causal statements within the Clinical Practice Guidelines for gestational diabetes.