Automatic Infants’ Pain Assessment by Dynamic Facial Representation: Effects of Profile View, Gestational Age, Gender, and Race

Abstract

Infants’ early exposure to painful procedures can have negative short and long-term effects on cognitive, neurological, and brain development. However, infants cannot express their subjective pain experience, as they do not communicate in any language. Facial expression is the most specific pain indicator, which has been effectively employed for automatic pain recognition. In this paper, dynamic pain facial expression representation and fusion scheme for automatic pain assessment in infants is proposed by combining temporal appearance facial features and temporal geometric facial features. We investigate the effects of various factors that influence pain reactivity in infants, such as individual variables of gestational age, gender, and race. Different automatic infant pain assessment models are constructed, depending on influence factors as well as facial profile view, which affect the model ability of pain recognition. It can be concluded that the profile-based infant pain assessment is feasible, as its performance is almost as good as that of the whole face. Moreover, gestational age is the most influencing factor for pain assessment, and it is necessary to construct specific models depending on it. This is mainly because of a lack of behavioral communication ability in infants with low gestational age, due to limited neurological development. To our best knowledge, this is the first study investigating infants’ pain recognition, highlighting profile facial views and various individual variables.

Identification of Neonatal Infant Pain Assessment Tools as a Possibility of Their Application in Clinical Practice in Croatia: An Integrative Literature Review

“…Facial expression, crying, and motor activity are the most commonly used behavioral indicators of pain in preterm and full-term neonates (Anand et al, 2007;de Melo et al, 2014). Facial expression is the most specific pain indicator that is effectively used for automatic pain recognition and is stronger and more consistent than other behavioral indicators (Zamzmi et al, 2018;Zhi et al, 2018). Facial movements associated with pain in infants include deepening of the nasolabial furrow, lowering of the eyebrows, narrowing of the eyes, vertical and horizontal stretching of the mouth, lip aprons, lip opening, tongue protrusion, tensed tongue and chin bones (Zamzmi et al, 2018).…”

Interpretação e reconhecimento de padrões para avaliação de dor em imagens faciais de recém-nascidos

“…Para o processo de classificação, foram avaliados hiperplanos estatísticos gerados através da combinação PCA+MLDA, aplicadaàs bases de imagens faciais de recém-nascidos investigadas (COPE e UNIFESP), mostrando que podemos separar estas bases entre imagens de dor e não-dor utilizando estes métodos lineares. Os resultados de acurácia obtidos através do arcabouço construído neste trabalho atingiram níveis consideráveis, quando comparados com trabalhos da mesmaárea [Zhi et al 2018, Nanni et al 2010, dado que para a base COPE a taxa de acurácia utilizando leave-one-out foi de mais de 95%, ultrapassando os valores obtidos até então utilizando esta mesma base de imagens.…”

Atlas of neonatal face images using triangular Meshes

“…Recentemente, tem havido um interesse crescente em compreender as respostas comportamentais relacionadasà dor baseadas, principalmente, em expressões faciais [8]- [16]. A análise automática de dor em imagens faciaisé um tópico emergente em inteligência artificial dado o aumento de demanda por monitoramentos de dor contínuos e consistentes em clínicas e centros de saúde de recém-nascidos.…”