External validation of a collar-mounted triaxial accelerometer for second-by-second monitoring of eight behavioural states in dogs

Abstract

Early detection of disease by an animal owner may motivate them to seek early veterinary advice. Presentation before a more advanced clinical manifestation is evident could lead to more effective treatment and thus benefit the animal’s health and welfare. Accelerometers are able to detect changes in specific activities or behaviours, thus indicating early signs of possible adverse health events. The objective of this validation study was to determine whether the detection of eight behavioural states: walk, trot, canter/gallop, sleep, static/inactive, eat, drink, and headshake, by an accelerometer device was sufficiently accurate to be useful in a clinical setting. This fully independent external validation estimated the accuracy of a specific triaxial, collar-mounted accelerometer on a second-by second basis in 51 healthy dogs of different breeds, aged between 6 months and 13 years, weighing >10 kg. The overall diagnostic effectiveness was estimated as: % record correctly classified of > 95% in walk, trot, canter/gallop, eat, drink and headshake and >90% in sleep and static/inactive. The positive predictive values ranged from 93–100%, while the negative predictive values ranged from 96–100%, with exception of static/inactive (86%).This was probably because dogs were placed in unfamiliar kennels where they did not exhibit their typical resting behaviour. The device is worn on a collar, making its use feasible for anyone wanting to monitor their dog’s behaviour. The high accuracy in detecting various kinds of behaviour appears promising in assessing canine health and welfare states.

Feeding Cannabidiol (CBD)-Containing Treats Did Not Affect Canine Daily Voluntary Activity

“…The use of accelerometers, kinesiology, and gait analysis are becoming popular methods by which to evaluate the health status of an animal as well as response to treatment. Several triaxial accelerometers have been validated for the measurement of canine activity and can be easily attached to a collar or harness for home use ( 7 – 10 ). They have been used to evaluate the effectiveness of treatments for osteoarthritis and pruritic behaviors ( 11 – 14 ), the effects of exercise and rest on the voluntary activity of active sled dogs ( 15 , 16 ), and to predict rest in dogs and sleep in humans ( 17 – 19 ).…”

Combining Actigraph Link and PetPace Collar Data to Measure Activity, Proximity, and Physiological Responses in Freely Moving Dogs in a Natural Environment

“…The Actigraph accelerometer (ActiGraph, Pensecola, FL, USA) was shown to be a valid, practical and reliable device for the measurement of habitual physical activity in dogs in 2011 [1]. The Actigraph monitor and other accelerometers have been used to assess activity in ideal weight, overweight and obese dogs [2], during weight loss in dogs [3], in dogs receiving chemotherapy [4], in shelter dogs [5], and to monitor the behavioral states in dogs [6]. ActiLife software (ActiGraph, Pensecola, FL, USA) allows researchers to process and score collected data via validated algorithms that include sedentary bout and activity bout analysis and physical activity intensity (cut-points).…”

Use of a Collar-Mounted Triaxial Accelerometer to Predict Speed and Gait in Dogs

“…Given the model fit, we have a high degree of confidence in identifying periods when a dog is moving at speeds faster than walk. Other methods that can reliably differentiate more gaits have used a more complex method of categorisation, with algorithms to identify patterns in the accelerometry beyond simple delta-G analysis or activity count [ 6 , 7 , 8 ]. This indicates a more complex method than delta-G analysis may be required for a more detailed categorisation of gait.…”

“…Several studies have used accelerometry to determine whether a dog was walking, sleeping, cantering, or in a period of “inactivity” [ 6 , 7 , 8 ]. For activity categorisation, algorithms have been created to identify patterns in the acceleration vectors consistent with each activity in question, such as the symmetrical gait of a trot [ 6 , 7 , 8 ]. This method has been shown to accurately identify certain activities in dogs.…”