Facial Action Unit Detection on ICU Data for Pain Assessment

TL;DR

This paper evaluates the performance of facial action unit detection tools on real-world ICU data to improve automated pain assessment, highlighting challenges like lighting and device interference, and emphasizing the need for ICU-specific training.

Contribution

It demonstrates the limitations of existing facial analysis tools on ICU data and advocates for training models specifically on real-world ICU conditions for effective pain assessment.

Findings

OpenFace and AU R-CNN performance is affected by ICU conditions.

Current models achieve state-of-the-art results in controlled environments.

Training on ICU data is necessary for clinically reliable pain assessment.

Abstract

Current day pain assessment methods rely on patient self-report or by an observer like the Intensive Care Unit (ICU) nurses. Patient self-report is subjective to the individual and suffers due to poor recall. Pain assessment by manual observation is limited by the number of administrations per day and staff workload. Previous studies showed the feasibility of automatic pain assessment by detecting Facial Action Units (AUs). Pain is observed to be associated with certain facial action units (AUs). This method of pain assessment can overcome the pitfalls of present-day pain assessment techniques. All the previous studies are limited to controlled environment data. In this study, we evaluated the performance of OpenFace an open-source facial behavior analysis tool and AU R-CNN on the real-world ICU data. Presence of assisted breathing devices, variable lighting of ICUs, patient orientation with respect to camera significantly affected the performance of the models, although these showed the state-of-the-art results in facial behavior analysis tasks. In this study, we show the need for automated pain assessment system which is trained on real-world ICU data for clinically acceptable pain assessment system.