Survey on Pain Detection using Machine Learning Models (Preprint)

Abstract

Pain, as a highly individualized experience, stands as a primary reason driving individuals towards seeking medical attention. The assessment of pain traditionally relies upon self-reported or input from caregivers. Yet, the former proves inadequate when dealing with non-communicative patients, while the latter may suffer from subjective caregiver biases, introducing errors. Furthermore, human-resource and time-resource make periodic reporting impractical. Consequently, the emergence of automated tools for pain assessment holds substantial potential. Multiple studies have been conducted to assess the feasibility of automated pain evaluation. In this comprehensive survey, we commence by offering an overview of pain and its underlying mechanisms. Subsequently, we examine existing literature encompassing various modalities proposed for automated pain recognition. These modalities encompass facial expressions, physiological signals, audio, and pupil dilation. Concluding our survey, we delve into the prevalent challenges and propose directions for the progressive advancement of this field.