Related Experiment Videos
Automatic Infants' Pain Assessment by Dynamic Facial Representation: Effects of Profile View, Gestational Age,
Ruicong Zhi1,2, Ghada Zamzmi Dmitry Zamzmi3, Dmitry Goldgof4
1School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China. zhirc_research@126.com.
Insights
Automated infant pain recognition uses facial expressions, analyzing temporal and geometric features. Gestational age significantly impacts pain assessment accuracy, necessitating individualized models.
Area of Science:
- Neonatal care and developmental pediatrics
- Biomedical engineering and machine learning
- Pain research and clinical assessment
Background:
- Infants undergoing painful procedures face risks to cognitive, neurological, and brain development.
- Inability to verbally communicate pain makes objective assessment challenging.
- Facial expressions are key indicators for automatic pain recognition in non-verbal infants.
Purpose of the Study:
- To propose a novel dynamic pain facial expression representation and fusion scheme for automatic infant pain assessment.
- To investigate the influence of individual variables (gestational age, gender, race) and facial views (profile vs. whole face) on pain recognition models.
- To establish the feasibility of profile-based infant pain assessment.
Main Methods:
- Developing a fusion scheme combining temporal appearance and geometric facial features for pain expression representation.
- Constructing and evaluating automatic infant pain assessment models considering gestational age, gender, race, and facial profile.
- Comparing the performance of profile-based assessment models against whole-face models.
Main Results:
- The proposed scheme effectively represents dynamic pain facial expressions for automated assessment.
- Gestational age was identified as the most significant factor influencing pain assessment accuracy.
- Profile-based infant pain assessment demonstrated feasibility and comparable performance to whole-face assessment.
Conclusions:
- Automated infant pain recognition is feasible using facial expression analysis, with profile views offering a viable alternative.
- Gestational age is a critical variable, requiring the development of specific pain assessment models for different gestational ages.
- This study pioneers the investigation of profile facial views and individual variables in infant pain recognition.
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.