Equine Facial Action Coding System for determination of pain-related facial responses in videos of horses

Abstract

During the last decade, a number of pain assessment tools based on facial expressions have been developed for horses. While all tools focus on moveable facial muscles related to the ears, eyes, nostrils, lips, and chin, results are difficult to compare due to differences in the research conditions, descriptions and methodologies. We used a Facial Action Coding System (FACS) modified for horses (EquiFACS) to code and analyse video recordings of acute short-term experimental pain (n = 6) and clinical cases expected to be in pain or without pain (n = 21). Statistical methods for analyses were a frequency based method adapted from human FACS approaches, and a novel method based on co-occurrence of facial actions in time slots of varying lengths. We describe for the first time changes in facial expressions using EquiFACS in video of horses with pain. The ear rotator (EAD104), nostril dilation (AD38) and lower face behaviours, particularly chin raiser (AU17), were found to be important pain indicators. The inner brow raiser (AU101) and eye white increase (AD1) had less consistent results across experimental and clinical data. Frequency statistics identified AUs, EADs and ADs that corresponded well to anatomical regions and facial expressions identified by previous horse pain research. The co-occurrence based method additionally identified lower face behaviors that were pain specific, but not frequent, and showed better generalization between experimental and clinical data. In particular, chewing (AD81) was found to be indicative of pain. Lastly, we identified increased frequency of half blink (AU47) as a new indicator of pain in the horses of this study.

Effect of transportation and social isolation on facial expressions of healthy horses

“…Rashid et al . [ 33 ] found that nostril dilator (AD38) and chin raiser (AU17) were indicative of pain when using both the HFI and Co-occurrence methods. The fact that nostril dilator (AD38) is also present during stressful management conditions could indicate that this AD is common during simple management interventions and less significant for determining pain.…”

“…Therefore, the relative temporal distribution of AUs was also considered. In order to do this, the method of Rashid et al [ 33 ], here referred to as the Co-occurrence method, was used to calculate the co-occurrence of AUs. This method selected EquiFACS codes that occurred together with other EquiFACS codes more frequently in stress than in no-stress states.…”

“…Such methods have been proven feasible when analyzing other large and variable datasets in the biological sciences, for example behavioral studies [ 32 ]. In a recent study, EquiFACS data were used for determination of facial expressions of pain [ 33 ]. Using a machine learning method utilizing the temporal overlap of AUs in observation windows of different lengths, co-occurring facial expressions which discriminated between painful and non-painful horses were determined in a very small dataset in that study (N = 6) [ 33 ].…”

“…In a recent study, EquiFACS data were used for determination of facial expressions of pain [ 33 ]. Using a machine learning method utilizing the temporal overlap of AUs in observation windows of different lengths, co-occurring facial expressions which discriminated between painful and non-painful horses were determined in a very small dataset in that study (N = 6) [ 33 ]. The results of this method largely agreed with those of the frequency-based method, but it was also able to identify less frequent, but distinct, AUs of relevance for pain [ 33 ].…”

“…Using a machine learning method utilizing the temporal overlap of AUs in observation windows of different lengths, co-occurring facial expressions which discriminated between painful and non-painful horses were determined in a very small dataset in that study (N = 6) [ 33 ]. The results of this method largely agreed with those of the frequency-based method, but it was also able to identify less frequent, but distinct, AUs of relevance for pain [ 33 ]. To our knowledge, exploration of facial expressions originating from affective states using this or other methods has yet to be explored in horses, and it is not clear whether facial expressions of pain in horses can be affected by other cognitive states.…”