This study focuses on the task of data annotation in Intensive Care Units (ICUs), a crucial aspect for implementing machine learning solutions in healthcare. The process of data annotation, which involves expanding on existing data to make it more useful for later use in the machine-learning pipeline, is complex and time-consuming. The study aims to understand how clinicians approach this task and identify the potential differences in the annotation workflow between different staff roles. The ultimate goal is to define the requirements for a software tool that could make data annotation more effective and time-efficient. The findings will contribute to the development of better tools for clinicians and improve patient outcomes.
Publication date: 2 Oct 2023
Project Page: 1arXiv:2309.16500v1 [cs.HC] 28 Sep 2023
Paper: https://arxiv.org/pdf/2309.16500
