Background: The prevalence of subacute ruminal acidosis (SARA) in dairy cows is high with large impact on economy and welfare. Its current field diagnosis is based on point ruminal pH measurements by oral probe or rumenocentesis. These techniques are invasive and inaccurate, and better markers for the diagnosis of SARA are needed. The goal of this study was to evaluate clinical signs of SARA and to investigate the use of blood, faecal and urinary parameters as indicators of SARA. Six lactating, rumen cannulated, Danish Holstein cows were used in a cross-over study with three periods. The first and second periods included two cows on control diet and two cows on nutritional SARA challenge. The third period only included two cows on SARA challenge. Control diet was a conventional total mixed ration [45.5% dry matter (DM), 17.8% crude protein, 43.8% neutral detergent fibre, and 22.5% acid detergent fibre (DM basis)]. SARA challenge was conducted by substituting control diet with grain pellets (50% wheat/barley) over 3 days to reach 40% grain in the diet. Ruminal pH was measured continuously. Blood samples were collected once daily at 7 h after feeding. Samples of faeces and urine were collected at feeding, and at 7 and 12 h after feeding. Blood samples were analysed for pCO2, pO2, pH, electrolytes, lactate, glucose, packed cell volume (PCV), and total plasma protein concentration. Milk composition, ruminal VFA, and pH of faeces and urine were measured. Results: SARA was associated with decreased ( P < 0.05) minimum ruminal, faecal and urinary pH. Daily times and areas of ruminal pH below 5.8, and 5.6 were increased to levels representative for SARA. Significant differences were detected in milk composition and ruminal VFAs. Blood calcium concentration was decreased ( P < 0.05), and pCO ₂ tended to be increased ( P = 0.10). Significant differences were not detected in other parameters. Conclusions: SARA challenge was associated with changes in faecal and urinary pH, blood calcium concentration and pCO ₂ . These may be helpful as indicators of SARA. However changes were small, and diurnal variations were present. None of these parameters are able to stand alone as indicators of SARA.

Advances in animal motion tracking and pose recognition have been a game changer in the study of animal behavior. Recently, an increasing number of works go ‘deeper’ than tracking, and address automated recognition of animals’ internal states such as emotions and pain with the aim of improving animal welfare, making this a timely moment for a systematization of the field. This paper provides a comprehensive survey of computer vision-based research on recognition of pain and emotional states in animals, addressing both facial and bodily behavior analysis. We summarize the efforts that have been presented so far within this topic—classifying them across different dimensions, highlight challenges and research gaps, and provide best practice recommendations for advancing the field, and some future directions for research.

Automated recognition of human facial expressions of pain and emotions is to a certain degree a solved problem, using approaches based on computer vision and machine learning. However, the application of such methods to horses has proven difficult. Major barriers are the lack of sufficiently large, annotated databases for horses and difficulties in obtaining correct classifications of pain because horses are non-verbal. This review describes our work to overcome these barriers, using two different approaches. One involves the use of a manual, but relatively objective, classification system for facial activity (Facial Action Coding System), where data are analyzed for pain expressions after coding using machine learning principles. We have devised tools that can aid manual labeling by identifying the faces and facial keypoints of horses. This approach provides promising results in the automated recognition of facial action units from images. The second approach, recurrent neural network end-to-end learning, requires less extraction of features and representations from the video but instead depends on large volumes of video data with ground truth. Our preliminary results suggest clearly that dynamics are important for pain recognition and show that combinations of recurrent neural networks can classify experimental pain in a small number of horses better than human raters.

Computer vision is a subcategory of artificial intelligence focused on extraction of information from images and video. It provides a compelling new means for objective orthopaedic gait assessment in horses using accessible hardware, such as a smartphone, for markerless motion analysis. This study aimed to explore the lameness assessment capacity of a smartphone single camera (SC) markerless computer vision application by comparing measurements of the vertical motion of the head and pelvis to an optical motion capture multi-camera (MC) system using skin attached reflective markers. Twenty-five horses were recorded with a smartphone (60 Hz) and a 13 camera MC-system (200 Hz) while trotting two times back and forth on a 30 m runway. The smartphone video was processed using artificial neural networks detecting the horse’s direction, action and motion of body segments. After filtering, the vertical displacement curves from the head and pelvis were synchronised between systems using cross-correlation. This rendered 655 and 404 matching stride segmented curves for the head and pelvis respectively. From the stride segmented vertical displacement signals, differences between the two minima (MinDiff) and the two maxima (MaxDiff) respectively per stride were compared between the systems. Trial mean difference between systems was $2.2$ mm (range 0.0–8.7 mm) for head and 2.2 mm (range 0.0–6.5 mm) for pelvis. Within-trial standard deviations ranged between 3.1–28.1 mm for MC and between 3.6–26.2 mm for SC. The ease of use and good agreement with MC indicate that the SC application is a promising tool for detecting clinically relevant levels of asymmetry in horses, enabling frequent and convenient gait monitoring over time.

The pathogenesis of postpartum dysgalactia syndrome (PDS) in sows is not fully elucidated and affected sows often present vague clinical signs. Accurate and timely diagnosis is difficult, and PDS is often recognized with a delay once piglets begin to starve. Increased rectal temperature of the sow is an important diagnostic parameter, but it may also be influenced by a number of other parameters and is thus difficult to interpret. Inflammatory markers may be important adjuncts to the clinical assessment of sows with PDS, but such markers have only been studied to a limited extent. The objective was to characterize the inflammatory response in healthy sows and in sows suffering from PDS, and to identify biomarkers that may assist in early identification of PDS-affected sows. Thirty-eight PDS-affected (PDS+) and 38 healthy (PDS-) sows underwent clinical examination and blood sampling every 24 h, from 60 h before the first piglet was born to 36 h after parturition. In both groups, inflammatory markers changed in relation to parturition. Most inflammatory markers changed 12-36 h after parturition [white blood cell counts (WBC), neutrophil counts, lymphocyte counts, tumor necrosis factor alpha (TNF-α), interleukin 6 (IL-6), serum amyloid A (SAA), C-reactive protein (CRP), haptoglobin (Hp), iron (Fe) and albumin (ALB)]. Changes in neutrophil counts, lymphocyte counts, CRP, Fe and ALB were observed -12 to 0 h before parturition. WBC, neutrophil and lymphocyte counts, serum concentrations of TNF-α, IL-6, Hp and Fe differed between PDS+ and PDS- sows. These differences were mainly apparent 12 to 36 h after parturition, but already at 12 h before parturition, PDS+ sows had lower lymphocyte counts than PDS- sows. Parturition itself caused significant inflammatory changes, but PDS+ sows showed a more severe response than PDS- sows. WBC, neutrophil and lymphocyte counts, and concentrations of TNF-α, IL-6, Hp and Fe can be potential biomarkers for PDS. Lymphocyte counts may be used to detect PDS at pre-partum. To assess their diagnostic potential, these markers must be investigated further and most likely combined with assessment of clinical parameters and other biomarkers for improved identification of sows at risk of developing PDS.

Postpartum dysgalactia syndrome (PDS) in sows is difficult to diagnose and the pathogenesis is obscure. Hormonal changes related to the disease are often difficult to distinguish from those found in the normal transition period from gestation to lactation. The study aimed to investigate metabolic and hormonal changes related to PDS with the goal of identifying potential biomarkers in sows suffering from PDS (PDS+). Selected biomarkers were examined by comparing 38 PDS+ sows with 38 PDS negative (PDS-) sows. The sows were sampled every 24 h from 60 h ante partum (a.p.) to 36 h post partum (p.p.). Compared to the baseline (60 to 36 h a.p.), cortisol in serum and saliva and fasting blood glucose concentrations increased in PDS+ as well as PDS- sows. C-peptide decreased relative to the baseline in PDS+ sows, and prolactin and 8-epi prostaglandin F2 alpha (8-epi-PGF2α) decreased in PDS- sows. Concentrations of cortisol in serum and saliva, salivary chromogranin A (CgA), fasting blood glucose, C-peptide, and 8-epi-PGF2α differed significantly between PDS+ and PDS- sows, with levels of cortisol in serum and saliva, salivary CgA, and 8-epi-PGF2α in serum being different in the two groups already before parturition. Concentrations of salivary CgA were significantly lower in PDS- sows than in PDS+ sows during the entire study period. The results suggest that salivary CgA, cortisol and serum 8-epi-PGF2α may potentially serve as early diagnostic indicators for PDS. The consistently higher salivary CgA concentration in PDS+ sows compared to PDS- sows may indicate that homeostatic disturbances are present between 36 to 60 h before parturition in sows developing PDS. The higher serum and saliva cortisol concentration in PDS+ sows compared to PDS- sows could reflect an early sign of inflammation or stress. The significantly lower C-peptide in PDS+ sows compared to PDS- sows may reflect a lower food intake. Our results contribute to the understanding of the pathogenesis of PDS, and the homeostatic disturbances detected before parturition warrants further investigation. The diagnostic potential of the markers identified in this study should be investigated further in a larger population of sows.