Equine behaviour analysis in a bilateral lameness model as a
precursor to automated detection.
Egan, S.1, Brama, P.A.J.2, Kearney C.M.2, McKeown, D.J.3, McGrath, D.1
1: UCD School of Physiotherapy Public Health and Sports Science, 2: UCD School of Veterinary Medicine
3: UCD School of Mechanical & Materials Engineering, University College Dublin, Dublin, Ireland
•Exploratory animal behaviour has been
associated with health status. Currently it is
unclear how this is expressed in equines.
•Pawing has been linked to orthopaedic pain.
What equine behaviours are pertinent
during the acute 12 hours post bilateral
•Duration of non-exploratory behaviour
(DNEB) calculated from:
•Preliminary analysis focuses on the 0 –12 hour period, 15 behaviours were classified as exploratory/non-
exploratory. Visual inspection indicated moderate to serve lameness, pawing was analysed independently.
•5 out of 7 animals demonstrated a consistent trend of increasing DNEB in the 4-8hr period compared to the
0-4hrs, despite differing baseline magnitudes. Pawing indicated a similar pattern in 4 out of 7 horses.
•The manual coding process is the initial step to training sensor data using a machine learning approach. The
ultimate objective is to develop a behaviour classification system enabling real-time relevant behaviour
The authors wish to thank the Irish Research Council, Government of Ireland Postgraduate Programme for supporting this research.
Further analysis is underway to determine the behaviour-relationship with food availability and the recovery
trajectory over 7 days.
This will determine if DNEB & pawing are a useful and sensitive indicator of bilateral lameness for future ‘training’
(0.25ng) @ 0 hours
Half Recumbency Total Recumbency
Quiet standing Agitated standing
Raised Forelimb (L) Raised Forelimb (R)
from 0 -12 hours
0-4hr 4-8hr 8-12hr
0-4hr 4-8hr 8-12hr
Recommendations & Future Directions
@ 2hrs (2ml saline)