Looking for an academic partner for your discovery projects?
Looking for an academic partner for your discovery projects?
Ghent University offers a unique proposal: the collaboration between veterinarians, physicians and scientists from different disciplines present at Ghent University takes the research to a higher level and creates many opportunities for innovation. At our Faculty of Veterinary Medicine these innovations can be tested in our own facilities and on the target species.
Check what we can offer in these fields
Ghent University offers a unique proposal: the collaboration between veterinarians, physicians and scientists from different disciplines present at Ghent University takes the research to a higher level and creates many opportunities for innovation. At our Faculty of Veterinary Medicine these innovations can be tested in our own facilities and on the target species.
Check what we can offer in these fields
Diagnostics
Injectable sensor platform for continuous equine health monitoring
Injectable IoT microsensor with onboard machine learning for real-time behavioural monitoring in horses
A minimally invasive injectable sensor that continuously monitors equine behaviour and physiology and automatically detects health events, streaming data for remote, 24/7 supervision. Injected as simply as a standard ID chip.
Early: critical events such as colic are detected before clinical peak, enabling timely intervention. Multi-parameter: continuous monitoring of activity, behaviour and temperature via onboard machine learning. Unobtrusive: fully internal, so it does not disturb the horse and carries none of the wound, chafing or entanglement risks of collars or wearables. Remote: low-power wireless telemetry alerts owner and carer 24/7, anywhere, with no handling. Low-maintenance: wireless recharging gives long autonomy.
Technical proof of concept of an injectable equine health monitor
A technical proof of concept has been built, integrating onboard behavioural sensing, embedded machine-learning inference and wireless data transmission. On horses, the behavioural-classification algorithms detected colic with 91.2% accuracy, approximately 20 minutes before peak pain, and foaling with 100% accuracy. The technology is now being matured, with in-body robustness, miniaturisation and energy autonomy under active investigation. Large-scale data collection in approximately 200 horses is planned to further validate detection performance ahead of in-body deployment.
Partnering
We seek investors and partners in the animal health, veterinary technology and equine insurance sectors to fund and collaborate. We welcome investment and pilot collaborations.