Predictive models of lameness in dairy cows achieve high sensitivity and specificity with force measurements in three dimensions

Abstract

Lameness remains a significant cause of production losses, a growing welfare concern and may be a greater economic burden than clinical mastitis . A growing need for accurate, continuous automated detection systems continues because US prevalence of lameness is 12.5% while individual herds may experience prevalence's of 27.8-50.8%. To that end the first force-plate system restricted to the vertical dimension identified lame cows with 85% specificity and 52% sensitivity. These results lead to the hypothesis that addition of transverse and longitudinal dimensions could improve sensitivity of lameness detection. To address the hypothesis we upgraded the original force plate system to measure ground reaction forces (GRFs) across three directions. GRFs and locomotion scores were generated from randomly selected cows and logistic regression was used to develop a model that characterised relationships of locomotion scores to the GRFs. This preliminary study showed 76 variables across 3 dimensions produced a model with greater than 90% sensitivity, specificity, and area under the receiver operating curve (AUC). The result was a marked improvement on the 52% sensitivity, and 85% specificity previously observed with the 1 dimensional model or the 45% sensitivities reported with visual observations. Validation of model accuracy continues with the goal to finalise accurate automated methods of lameness detection.

The cow pedogram—Analysis of gait cycle variables allows the detection of lameness and foot pathologies

“…However, changes of kinetic variables in the vertical axis of cows with similar foot lesions and locomotion score were heterogeneous among cows (Liu et al, 2011). One explanation for this was that cows with painful lateral claws may shift load-bearing to the sound medial claw of the same limb (Dunthorn et al, 2015). Pastell et al (2009) reported a significant difference in the symmetry of forward acceleration of hind limbs between the gait of lame and sound cows using a wireless 3-dimensional accelerometer system.…”

Performance of human observers and an automatic 3-dimensional computer-vision-based locomotion scoring method to detect lameness and hoof lesions in dairy cows

“…To our knowledge, no study reports a direct association between presence of specific hoof lesions and pain. However, several studies report that cows classified as lame required less pressure to produce limb retraction (i.e., painful hoof) than cows classified as nonlame (Whay et al, 1997;Dyer et al, 2007;Dunthorn et al, 2015). Thus, because horn lesions are more associated with lameness than skin lesions and interdigital hyperplasias, it is possible to infer that horn lesions are more painful than skin lesions and hyperplasias.…”

“…Most automatic locomotion scoring systems attempt to mimic human observers by measuring and analyzing parameters of cows' locomotion and behavior through sensors and mathematical algorithms. Some examples include measuring forces exerted on the floor by the limbs using force plates (Rajkondawar et al, 2002) or 3-dimensional (3D) force plates (Dunthorn et al, 2015), weight distribution of limbs using 4 independent weighing units (Chapinal et al, 2009a), parameters associated with distances between hoof prints using pressure-sensitive mats (Maertens et al, 2011), or parameters associated with activity and behavior using accelerometers attached to the neck or limbs of cows (Alsaaod et al, 2012;Thorup et al, 2015). Recently a promising approach for an automatic locomotion scoring used 3D camera technology to measure different angles associated with back curvature (Viazzi et al, 2013;Van Hertem et al, 2014).…”

Estimating economic and production losses in relation to locomotion score in primiparous Polish Holstein-Friesian cows

“…If the lameness is not severe, cows are kept as productive animals, but the reduction in the milk production and reproductive problems imply the reduction in income and also cause not measurable economic losses. An increase of lameness degree may affect a shorter productive life, which in turn generate an increase of measurable economic losses (Dunthorn et al 2015).…”

“…According to the literature, lameness is ranged between 6 and 42% of the total dairy cow herds (Dembele et al 2006;Barker et al 2010;Ito et al 2010;Tadich et al 2010;Sogstad et al 2012;Von Keyserlingk et al 2012;Van Nuffel et al 2015). Amory et al (2006) and also Cooke and Bennett (2005) reported that of the whole (21.5 million) EU dairy cow population, about five million had problems with locomotion, which in terms of costs amounts to more than a billion EUR per year.…”