Physiological and behavioral effects of dextroamphetamine on Beagle dogs

New Advances in Attention-Deficit/Hyperactivity Disorder-like Dogs

Similar to humans, dogs could suffer an Attention-Deficit/Hyperactivity Disorder-like syndrome (ADHD-like). In fact, several studies highlight the use of dogs as a model for studying ADHD. This condition entails behavioral problems expressed through impulsivity, attention issues, hyperactivity, and/or aggression, compromising the quality of life for both the caregiver and the dog. The pathophysiology of ADHD-like is complex and is associated with dysregulation of various neurotransmitters such as serotonin and dopamine. The expression of ADHD-like behavior in dogs would appear to depend on a classical gene-environment interaction as is the case with many neurological disorders in humans. In addition to the described symptomatology, ADHD-like dogs can exhibit strong comorbidities with compulsive behaviors, aggressiveness, inappropriate elimination and fearfulness, in addition to epilepsy, foreign body ingestion, and pruritus. In spite of the fact that there is no veterinary consensus about the diagnosis of ADHD-like, some validated questionnaires could be helpful, but these cannot be used as a unique diagnostic tool. The use of drugs, such as fluoxetine, in addition to an adequate environmental enrichment, relaxation protocols, and behavior modification can achieve an adequate quality of life for both the dog and caregivers.

Machine learning based canine posture estimation using inertial data

The aim of this study was to design a new canine posture estimation system specifically for working dogs. The system was composed of Inertial Measurement Units (IMUs) that are commercially available, and a supervised learning algorithm which was developed for different behaviours. Three IMUs, each containing a 3-axis accelerometer, gyroscope, and magnetometer, were attached to the dogs' chest, back, and neck. To build and test the model, data were collected during a video-recorded behaviour test where the trainee assistance dogs performed static postures (standing, sitting, lying down) and dynamic activities (walking, body shake). Advanced feature extraction techniques were employed for the first time in this field, including statistical, temporal, and spectral methods. The most important features for posture prediction were chosen using Select K Best with ANOVA F-value. The individual contributions of each IMU, sensor, and feature type were analysed using Select K Best scores and Random Forest feature importance. Results showed that the back and chest IMUs were more important than the neck IMU, and the accelerometers were more important than the gyroscopes. The addition of IMUs to the chest and back of dog harnesses is recommended to improve performance. Additionally, statistical and temporal feature domains were more important than spectral feature domains. Three novel cascade arrangements of Random Forest and Isolation Forest were fitted to the dataset. The best classifier achieved an f1-macro of 0.83 and an f1-weighted of 0.90 for the prediction of the five postures, demonstrating a better performance than previous studies. These results were attributed to the data collection methodology (number of subjects and observations, multiple IMUs, use of common working dog breeds) and novel machine learning techniques (advanced feature extraction, feature selection and modelling arrangements) employed. The dataset and code used are publicly available on Mendeley Data and GitHub, respectively.

Challenges of machine learning model validation using correlated behaviour data: Evaluation of cross-validation strategies and accuracy measures

Automated monitoring of the movements and behaviour of animals is a valuable research tool. Recently, machine learning tools were applied to many species to classify units of behaviour. For the monitoring of wild species, collecting enough data for training models might be problematic, thus we examine how machine learning models trained on one species can be applied to another closely related species with similar behavioural conformation. We contrast two ways to calculate accuracies, termed here as overall and threshold accuracy, because the field has yet to define solid standards for reporting and measuring classification performances. We measure 21 dogs and 7 wolves, and find that overall accuracies are between 51 and 60% for classifying 8 behaviours (lay, sit, stand, walk, trot, run, eat, drink) when training and testing data are from the same species and between 41 and 51% when training and testing is cross-species. We show that using data from dogs to predict the behaviour of wolves is feasible. We also show that optimising the model for overall accuracy leads to similar overall and threshold accuracies, while optimizing for threshold accuracy leads to threshold accuracies well above 80%, but yielding very low overall accuracies, often below the chance level. Moreover, we show that the most common method for dividing the data between training and testing data (random selection of test data) overestimates the accuracy of models when applied to data of new specimens. Consequently, we argue that for the most common goals of animal behaviour recognition overall accuracy should be the preferred metric. Considering, that often the goal is to collect movement data without other methods of observation, we argue that training data and testing data should be divided by individual and not randomly.

Effect of environmental noise and music on dexmedetomidine-induced sedation in dogs

Background

Previous studies in human patients suggest depth of sedation may be affected by environmental noise or music; however, related data in domestic animals is limited. The objective of the current study was to investigate the effect of noise and music on dexmedetomidine-induced (DM- 10 µg/kg, IM) sedation in 10 dogs.

Methods

In a crossover design, post-DM injection dogs were immediately subjected to recorded human voices at either 55–60 decibel (dB) (Noise 1) or 80–85 dB (Noise 2); classical music at 45–50 dB (Music); or background noise of 40–45 dB (Control+). Control− included IM saline injection and exposure to 40–45 dB background noise. Sedation was assessed via monitoring spontaneous behavior and accelerometry (delta-g) throughout three 20-min evaluation periods: baseline, noise exposure, and post-treatment. Sedation was further assessed during two restraint tests at 30 min (R1) and 40 min (R2) post-injection. A mixed model for crossover design was used to determine the effect of noise exposure and time on either spontaneous behavior scores or delta-g. The restraint scores were analyzed using a two-way repeated measures ANOVA.

Results

Spontaneous behavior scores indicated less sedation during Noise 2 compared to Control+ (P = 0.05). R2 restraint scores for all DM treatments except Noise 2 indicated significantly higher sedation than Control− [C+ (P = 0.003), M (P = 0.014) and N1 (P = 0.044)].

Discussion

Results suggest that the quality of sedation is negatively impacted by high-intensity noise conditions (80–85 dB), but exposure to music did not improve sedation in this population of research dogs.

Use of accelerometers to measure stress levels in shelter dogs

Stress can compromise welfare in any confined group of nonhuman animals, including those in shelters. However, an objective and practical method for assessing the stress levels of individual dogs housed in a shelter does not exist. Such a method would be useful for monitoring animal welfare and would allow shelters to measure the effectiveness of specific interventions for stress reduction. In this pilot study, activity levels were studied in 13 dogs using accelerometers attached to their collars. Behavioral stress scores as well as urinary and salivary cortisol levels were measured to determine if the dogs' activity levels while confined in the kennel correlated with behavioral and physiological indicators of stress in this population. The results indicated that the accelerometer could be a useful tool to study stress-related activity levels in dogs. Specific findings included a correlation between the salivary cortisol and maximum activity level (r = .62, p = .025) and a correlation between the urine cortisol-to-creatinine ratio and average activity level (r = .61, p = .028) among the study dogs. Further research is needed to better understand the complex relationship between stress and activity level among dogs in a kennel environment.

Identification of behaviour in freely moving dogs (Canis familiaris) using inertial sensors

Monitoring and describing the physical movements and body postures of animals is one of the most fundamental tasks of ethology. The more precise the observations are the more sophisticated the interpretations can be about the biology of a certain individual or species. Animal-borne data loggers have recently contributed much to the collection of motion-data from individuals, however, the problem of translating these measurements to distinct behavioural categories to create an ethogram is not overcome yet. The objective of the present study was to develop a “behaviour tracker”: a system composed of a multiple sensor data-logger device (with a tri-axial accelerometer and a tri-axial gyroscope) and a supervised learning algorithm as means of automated identification of the behaviour of freely moving dogs. We collected parallel sensor measurements and video recordings of each of our subjects (Belgian Malinois, N=12; Labrador Retrievers, N=12) that were guided through a predetermined series of standard activities. Seven behavioural categories (lay, sit, stand, walk, trot, gallop, canter) were pre-defined and each video recording was tagged accordingly. Evaluation of the measurements was performed by support vector machine (SVM) classification. During the analysis we used different combinations of independent measurements for training and validation (belonging to the same or different individuals or using different training data size) to determine the robustness of the application. We reached an overall accuracy of above 90% perfect identification of all the defined seven categories of behaviour when both training and validation data belonged to the same individual, and over 80% perfect recognition rate using a generalized training data set of multiple subjects. Our results indicate that the present method provides a good model for an easily applicable, fast, automatic behaviour classification system that can be trained with arbitrary motion patterns and potentially be applied to a wide range of species and situations.

Validity and reliability of Polar® RS800CX heart rate monitor, measuring heart rate in dogs during standing position and at trot on a treadmill

The aim of the present study was to assess criterion validity, and relative and absolute reliability of Polar® RS800CX heart rate monitor, compared to simultaneously recorded electrocardiogram (ECG) data, in measuring heart rate of dogs during standing position and at trot on a treadmill.

METHODS

Heart beats from Polar® RS800CX and Cardiostore ECG were recorded simultaneously during seven continuous minutes in standing position and at trot, in 10 adult healthy dogs. Polar® data was statistically compared to ECG data for a variety of mean beats per minute (BPM), standard deviation and confidence interval. Criterion validity was calculated by Pearson product moment correlation method and intraclass correlation coefficient (ICC2.1). Relative and absolute reliability were calculated by ICC2.1, the Bland and Altman analysis and standard error of measurement (SEM and SEM%).

RESULTS

The correlation, criterion validity, between Polar® and ECG data in standing position was r=0.99 (p<0.0005) and at trot r=0.97 (p<0.0005). Polar® data was not significantly different from ECG data. Mean difference between ECG and uncorrected Polar® data was -0.6 BPM in standing position and -0.6 BPM at trot. Polar® was over- and underestimating ECG data. SEM and SEM% in standing were ±2.6 BPM and 3.0%, at trot ±3.8 BPM and 3.1%, indicating that measurement errors were low.

CONCLUSION

This study showed that the criterion validity and the instrument reliability were excellent in Polar® RS800CX heart rate measuring system. The equipment seemed to be valid and reliable in measuring BPM in the dogs studied during submaximal cardiovascular conditions such as in standing position and at trot on a treadmill.