Towards Automatically Filling Questionnaires from Clinical Records with Large Language Models

Abstract

The use of large language models in healthcare is rapidly growing. In this work, we are interested in analyzing the capabilities of large language models in filling questionnaires related to clinical practices, where the information needed to answer each specific question is contained in the clinical records of a given patient. We present preliminary experiments on a publicly available dataset in the English language, with very promising results that show the great potential of the approach and motivate further research in this challenging direction.