Discordant Relationship Between Evaluation of Facial Expression and Subjective Pain Rating Due to the Low Pain Magnitude

Changes in the equine facial repertoire during different orthopedic pain intensities

A number of facial expressions are associated with pain in horses, however, the entire display of facial activities during orthopedic pain have yet to be described. The aim of the present study was to exhaustively map changes in facial activities in eight resting horses during a progression from sound to mild and moderate degree of orthopedic pain, induced by lipopolysaccharides (LPS) administered in the tarsocrural joint. Lameness progression and regression was measured by objective gait analysis during movement, and facial activities were described by EquiFACS in video sequences (n = 348, total length 892.5 min) of the horses obtained when resting in their box stalls. Predictive modeling identified 16 action units and action descriptors, related to ears, eyes, and lower face. Lower lip depressor (AU16), lips part (AU25), half blink (AU47), single ear forward (SEAD101) and single ear rotator (SEAD104) were selected as co-occurring significantly more in horses with pain than in horses without pain. The major change in co-occurring facial activities occurred in the transition from no pain to mild pain. In conclusion, resting horses with induced orthopedic pain showed a dynamic upper and lower facial repertoire and the relationship between level of pain intensity and facial activity appears complex.

Facial Expressions of Horses Using Weighted Multivariate Statistics for Assessment of Subtle Local Pain Induced by Polylactide-Based Polymers Implanted Subcutaneously

Simple Summary

Facial expression (FE) has been used for pain diagnosis in horses. The current study aimed to identify pain in horses undergoing under-skin polylactide-based polymer implantation. Five statistical methods for analyzing FE were used, including conventional and new approaches. First, we scored the seven FEs separately. Subsequently, the scores of the seven FEs were added (SUM). Subsequently, principal component analysis (PCoA) was performed using the scores of the seven FEs obtained using the first method. Afterwards, weights were created for each FE based on each variable’s contribution variability obtained from the PCoA (SUM.W). Finally, we applied a general score to the animal’s face (GFS). The horses were filmed before and 24 and 48 h after implantation. The tissue sensitivity to mechanical stimulation and skin temperature of the horses were assessed at the same time points. The results show no changes in the FEs analyzed separately or jointly. The horses with incision and suture but no polymer implant displayed a higher pain-related FE 48 h after implantation, while the horses implanted with polymers displayed more apparent alterations in the mechanical skin sensitivity and temperature. Our findings show that the five statistical methods used to analyze the faces of the horses were not able to detect low-grade inflammatory pain.

Abstract

Facial-expression-based analysis has been widely applied as a pain coding system in horses. Herein, we aimed to identify pain in horses undergoing subcutaneously polylactide-based polymer implantation. The sham group was submitted only to surgical incision. The horses were filmed before and 24 and 48 h after implantation. Five statistical methods for evaluating their facial expressions (FEs) were tested. Primarily, three levels of scores (0, 1, and 2) were applied to the seven FEs (ear movements, eyebrow tension, orbicularis tension, dilated nostrils, eye opening, muzzle tension, and masticatory muscles tension). Subsequently, the scores of the seven FEs were added (SUM). Afterwards, principal component analysis (PCoA) was performed using the scores of the seven FEs obtained using the first method. Subsequently, weights were created for each FE, based on each variable’s contribution variability obtained from the PCoA (SUM.W). Lastly, we applied a general score (GFS) to the animal’s face (0 = without pain; 1 = moderate pain; 2 = severe pain). The mechanical nociceptive threshold (MNT) and cutaneous temperature (CT) values were collected at the same moments. The results show no intra- or intergroup differences, when evaluating each FE separately or in the GFS. In the intragroup comparison and 48 h after implantation, the control group showed higher values for SUM, PCoA, and SUM.W, although the horses implanted with polymers displayed more obvious alterations in the CT and MNT. Our findings show that the five statistical strategies used to analyze the faces of the horses were not able to detect low-grade inflammatory pain.

Sharing pain: Using pain domain transfer for video recognition of low grade orthopedic pain in horses

Orthopedic disorders are common among horses, often leading to euthanasia, which often could have been avoided with earlier detection. These conditions often create varying degrees of subtle long-term pain. It is challenging to train a visual pain recognition method with video data depicting such pain, since the resulting pain behavior also is subtle, sparsely appearing, and varying, making it challenging for even an expert human labeller to provide accurate ground-truth for the data. We show that a model trained solely on a dataset of horses with acute experimental pain (where labeling is less ambiguous) can aid recognition of the more subtle displays of orthopedic pain. Moreover, we present a human expert baseline for the problem, as well as an extensive empirical study of various domain transfer methods and of what is detected by the pain recognition method trained on clean experimental pain in the orthopedic dataset. Finally, this is accompanied with a discussion around the challenges posed by real-world animal behavior datasets and how best practices can be established for similar fine-grained action recognition tasks. Our code is available at https://github.com/sofiabroome/painface-recognition.