Wearable Sensors for Monitoring Neurological Conditions in Dogs

Itzik Klein - Department of Marine Technologies
Anna Zamansky and Tsvika Palkovitch# - Department of Information Systems

Artificial Intelligence
Machine Learning
Deep learning
Neural Networks

Veterinary Medicine

Seed Grant 2023

dogs phone Anna Zamansky

Inertial sensors are intensively used in human neurology, e.g., for assessing risks of falls in elderly patients. In canine neurology they can allow for the detection of subtle changes, e.g. in behavior or gait patterns, which are not easily recognizable by pet owners or even experienced veterinarians, yet may indicate a gradual progression of a neurological disorder. Such detection can promote discovery of new biomarkers and enable effective medical countermeasures that could fundamentally change the course of the disease.

Here is an example of mobile product for humans.

In an exploratory study we demonstrated that inertial sensors in a smartphone can be used to detect a neurological disorder of ataxia in dogs. 

The setting involved inertial sensor data collected by smartphone placed on the dog’s back while walking in a straight line. A total of 770 walking sessions were evaluated comparing the gait of 55 healthy dogs to the one of 23 dogs with ataxia. Different machine learning techniques were used with the K-nearest neighbors technique reaching 95% accuracy in discriminating between a healthy control group and ataxic dogs, indicating potential use for smartphone apps for canine ataxia diagnosis and monitoring of treatment effect.