Computer Mediated Automatic Detection of Pain-Related Behavior: Prospect, Progress, Perils

Abstract

Pain is often characterized as a fundamentally subjective phenomenon; however, all pain assessment reduces the experience to observables, with strengths and limitations. Most evidence about pain derives from observations of pain-related behavior. There has been considerable progress in articulating the properties of behavioral indices of pain; especially, but not exclusively those based on facial expression. An abundant literature shows that a limited subset of facial actions, with homologs in several non-human species, encode pain intensity across the lifespan. Unfortunately, acquiring such measures remains prohibitively impractical in many settings because it requires trained human observers and is laborious. The advent of the field of affective computing, which applies computer vision and machine learning (CVML) techniques to the recognition of behavior, raised the prospect that advanced technology might overcome some of the constraints limiting behavioral pain assessment in clinical and research settings. Studies have shown that it is indeed possible, through CVML, to develop systems that track facial expressions of pain. There has since been an explosion of research testing models for automated pain assessment. More recently, researchers have explored the feasibility of multimodal measurement of pain-related behaviors. Commercial products that purport to enable automatic, real-time measurement of pain expression have also appeared. Though progress has been made, this field remains in its infancy and there is risk of overpromising on what can be delivered. Insufficient adherence to conventional principles for developing valid measures and drawing appropriate generalizations to identifiable populations could lead to scientifically dubious and clinically risky claims. There is a particular need for the development of databases containing samples from various settings in which pain may or may not occur, meticulously annotated according to standards that would permit sharing, subject to international privacy standards. Researchers and users need to be sensitive to the limitations of the technology (for e.g., the potential reification of biases that are irrelevant to the assessment of pain) and its potentially problematic social implications.

Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository

“…However, our study shows no benefit in using this approach. Although the pain-related FAUs are well described, there is still no consensus on whether the pain severity could depend on the frame-to-frame facial action unit movement (Prkachin and Hammal, 2021 ). To address this important defect, further research is required to explore the value-generated association between computer vision and rating by a trained rater.…”

“…The reliability of automated pain severity classification is still not robust enough for medication dosage decision for every ethnic group. Few studies have explicitly trained and tested classifiers on various population databases (Prkachin and Hammal, 2021 ). Our study discovered many misclassifications of moderate to severe pain into “no pain.” This may explain the spontaneous pain nature, whose behavior expression is significantly influenced by culture and environment.…”

“…These factors may impact the performance of the model. The challenge of developing an efficient model necessitates the use of databases that contain samples from different environments where pain may occur and are encrypted according to standards that enable sharing among international collaborations (Prkachin and Hammal, 2021 ).…”

Classification of elderly pain severity from automated video clip facial action units analysis: A study from a Thai data repository

“…However, our study shows no bene t in using this approach. Although the painrelated FAUs are well described, there is still no consensus on whether the pain severity could depend on the frame-to-frame facial action unit movement [1]. To address this important defect, further research is required to explore the value-generated association between computer vision and rating by a trained rater.…”

“…These factors may impact the performance of the model. The challenge of developing an e cient model necessitates the use of databases that contain samples from different environments where pain may occur and are encrypted according to standards that enable sharing among international collaborations [1].…”