Pain Action Unit Detection in Critically Ill Patients

Nerella, Subhash; Cupka, Julie; Ruppert, Matthew M.; Tighe, Patrick J.; Rashidi, Parisa

doi:10.1109/compsac51774.2021.00094

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This innovation has the potential to offer valuable solutions for evaluating pain within this population, a challenge often noted by clinicians and family members alike. 21 Beyond addressing this pressing need, the application of image-based pain detection has the added advantage of mitigating the intrinsic subjectivity inherent in human pain assessments, 31 – 33 thereby reducing associated inaccuracies. Our findings reflect a noteworthy aspect of this subjectivity.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automated facial recognition system using deep learning for pain assessment in adults with cerebral palsy

Sabater-Gárriz,

Gaya-Morey,

Buades-Rubio

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

Objective Assessing pain in individuals with neurological conditions like cerebral palsy is challenging due to limited self-reporting and expression abilities. Current methods lack sensitivity and specificity, underlining the need for a reliable evaluation protocol. An automated facial recognition system could revolutionize pain assessment for such patients. The research focuses on two primary goals: developing a dataset of facial pain expressions for individuals with cerebral palsy and creating a deep learning-based automated system for pain assessment tailored to this group. Methods The study trained ten neural networks using three pain image databases and a newly curated CP-PAIN Dataset of 109 images from cerebral palsy patients, classified by experts using the Facial Action Coding System. Results The InceptionV3 model demonstrated promising results, achieving 62.67% accuracy and a 61.12% F1 score on the CP-PAIN dataset. Explainable AI techniques confirmed the consistency of crucial features for pain identification across models. Conclusion The study underscores the potential of deep learning in developing reliable pain detection systems using facial recognition for individuals with communication impairments due to neurological conditions. A more extensive and diverse dataset could further enhance the models’ sensitivity to subtle pain expressions in cerebral palsy patients and possibly extend to other complex neurological disorders. This research marks a significant step toward more empathetic and accurate pain management for vulnerable populations.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Observational behavioral scales are the most used tools to assess pain in this population. 30 However, their use is not without controversy, as they can yield subjective, observer-dependent data, 31 – 33 and some may lack specificity or sensitivity. 34 Observers might also confuse other emotions, such as fear or stress, for pain.…”

Section: Introductionmentioning

confidence: 99%

Automated facial recognition system using deep learning for pain assessment in adults with cerebral palsy

Sabater-Gárriz,

Gaya-Morey,

Buades-Rubio

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

show abstract

“…Our ndings were inconsistence with the Nerella et al study (2021), which resulted in the correlation of AU25, 26, and 43 with pain. The difference between the results can be justi ed for many reasons; they focused on the adult population, different races, and hospital patients who are critically ill 34 . While our study aimed to assess pain in children who are receiving IANB.…”

Section: Discussionmentioning

confidence: 99%

Analyzing the Facial Action Units associated with genuine and fake pain caused by inferior alveolar nerve block in Syrian children: a cross-sectional study

Alkhouli

Al‐Nerabieah

Dashash

2023

Preprint

View full text Add to dashboard Cite

This study aimed to investigate the association between facial action units (FAUs) and pain levels in Syrian children, focusing on both genuine and fake pain expressions. A total of 300 Syrian children aged 6-9 years participated in the study. Pain levels were assessed using a validated pain scale (FLACC), and facial expressions were analyzed using the Facial Action Coding System (FACS). The children were asked to mimic their feelings after receiving a dental injection to elicit fake pain expressions. Statistical analysis, including multinomial logistic regression and chi-square tests, was conducted to determine the AUs associated with each pain level and to compare the differences between real and fake pain expressions. The results revealed significant associations between specific AUs and pain levels. For real pain expressions, the most activated AUs across different pain levels with positive coefficient values of correlation (P-value ＜0.01) were analyzed. In contrast, for fake pain expressions, AU12 and AU38 were consistently observed to be the most activated. These findings suggest that certain AUs are uniquely associated with fake pain expressions, distinct from those observed in real pain expressions. Furthermore, there were no significant differences between boys and girls in terms of their genuine and fake pain expressions, indicating a similar pattern of AU activation (P-value ＞0.05). It was concluded that AUs 4, 6, 41, and 46 were associated with mild pain, and AUs 4, 6, 41, 46, and 11 were associated with moderate pain cases. In severe pain, AUs 4, 6, 7, 9, 11, and 43 were associated. In fake pain feelings, AU43, AU38, and AU12 were the most activated with no difference between boys and girls.

show abstract

“…Studies attempt to classify AUs using the FACS as a basis for Deep Learning methods. These works include [9], which evaluates the visual transformers ViT and SWIN for AU classification using the DISFA+ dataset [10]. Besides normalizing the images, they perform facial alignment, horizontal flips, and rotations for preprocessing.…”

Section: Introductionmentioning

confidence: 99%

Using Diverse ConvNets to Classify Face Action Units in Dataset on Emotions Among Mexicans (DEM)

Moreno-Armendáriz,

Espinosa-Juarez,

Godinez-Montero

2024

IEEE Access

View full text Add to dashboard Cite

To understand how Convolutional Neural Networks (ConvNets) perceive the muscular movements of the human face, known as Action Units (AUs) in this work, we introduce a new dataset named Dataset on Emotions among Mexicans (DEM), consisting of 1557 images of Mexicans labeled with twentysix AUs and seven emotions. As a benchmark, we used the comparison with DISFA+ labeled with 12 AUs. To address the task of detecting AUs in each image, six ConvNets were employed, and we evaluated their performance using the F1 Score. The two ConvNets with the best performance were VGG19 with 0.8180% (DEM), 0.9106 % (DISFA+), and ShuffleNetV2 with 0.7154% (DEM), 0.9440% (DISFA+). Subsequently, these ConvNets were analyzed using Grad-CAM and Grad-CAM++; this algorithms allows us to observe the areas of the face considered for prediction. In most cases, these areas consider the region of the labeled AU. Considering the F1 score and the visual study, we can conclude that using DEM as a dataset to classify AUs is promising since the experiments achieved performances similar to those of the current literature that only use ConvNets.INDEX TERMS Action Units, ConvNets, CAM analysis.

show abstract

Pain Action Unit Detection in Critically Ill Patients

Cited by 7 publications

References 17 publications

Automated facial recognition system using deep learning for pain assessment in adults with cerebral palsy

Automated facial recognition system using deep learning for pain assessment in adults with cerebral palsy

Analyzing the Facial Action Units associated with genuine and fake pain caused by inferior alveolar nerve block in Syrian children: a cross-sectional study

Using Diverse ConvNets to Classify Face Action Units in Dataset on Emotions Among Mexicans (DEM)

Contact Info

Product

Resources

About