Moving Forward Using Automated Measures for Lameness Detection Núria Chapinal, PhD Animal Welfare Program, UBC April 14, 2010
Outline Introduction Visual/subjective methods of detection Automated methods of detection Examples Do they work? Experimental results Conclusions and practical applications
Introduction Lameness is a major welfare and productivity problem in dairy cattle Traditional assessment method: visual observation Herds are getting larger Producers have difficulties detecting lame cows Simple (fast), accurate and repeatable
Introduction Automated methods of detection available Automated gait assessment Automated monitoring of other behaviors Automated gait assessment Video motion analysis (Flower et al. 2005) Ground reaction force (Rajkondawar et al. 2006)
Introduction Lame cows: Lie down for longer (e.g. Chapinal et al., 2009) Change weight distribution among legs when standing (e.g. Rushen et al. 2007; Pastell and Kujala 2007) Have reduced mobility (e.g. visit a milking robot less frequently, Borderas et al. 2008)
Visual methods for gait assessment Subjective Vague description of lameness degrees Inter and intra observer reliability Not properly validated Training Time consuming
Subjective methods for gait assessment (Flower & Weary 2006 J. Dairy Sci. 89:139-146) Back arch 1 = not lame 5 = severely lame Head bob Joint flexion Asymmetric steps Reluctance to bear weight Swinging in/out Tracking up More than 90% of cases correctly classified as having a sole ulcer or not.
Gait score can predict sole ulcers 4 4 ** ** * * * * 3.5 3.5 Overall gait Overall gait † † Overall gait Overall gait 3 3 2.5 2.5 2 2 1.5 1.5 1 1 -8 -8 -4 -4 0 0 4 4 Week relative to diagnosis Sole ulcer Hemorrhage No lesions (Chapinal et al. 2009 J. Dairy Sci. 92: 4365-4374)
Subjective methods for gait assessment (Flower & Weary 2006 J. Dairy Sci. 89:139-146) Back arch Head bob Joint flexion Asymmetric steps Reluctance to bear weight Swinging in/out Tracking up (Chapinal et al. 2009 J. Dairy Sci. 92: 4365-4374)
Automated methods for lameness detection Objective = Repeatable Reduced labor Continuous monitoring (changes within cows) = Increased accuracy Some haven’t been properly validated yet Becoming affordable
Automated methods for lameness detection Visits to a milking robot Activity Lying behavior (time, bouts) Steps Walking acceleration patterns Weight distribution while standing Ground reaction force while walking
Activity IceTag accelerometer (IceRobotics) AfiMilk Pedometer Plus Tag (SAE Afikim) Hobo G pendant acceleration logger (Onset Computer Corporation) H-tag motion sensor (SCR)
Activity
Activity measures Lying bouts/day Lying bout duration Lying time/day Steps/day Acceleration patterns
Acceleration patterns 3.5 Acceleration (g) 2.5 1.5 0.5 -0.5 -1.5 -2.5 -3.5 0 1 2 3 4 5 Seconds A 3.5 2.5 Acceleration (g) 1.5 0.5 -0.5 -1.5 -2.5 -3.5 0 1 2 3 4 5 Seconds De Passillé et al. J. Dairy Sci. in press
Weight distribution: weighing platform
Weight distribution and shifting among legs 700 600 500 400 Kg 300 200 100 0 10:52:37 10:53:26 10:54:14 10:55:03 10:55:52 Time FRONT LEFT FRONT RIGHT BACK LEFT BACK RIGHT Total WEIGHT
Ground reaction forces: Stepmetrix (BouMatic) Lameness scored based on 5 limb movement variables (measures of stride and weight bearing) Rajkondawar et al. 2006 J. Dairy Sci. 89:4267-4275 Bicalho et al. 2007 J. Dairy Sci. 90:3294-3300
Do they work?
Not lame Lame Automated milking systems collect 120 data on cow 100 behaviour: Lame 80 % cows cows go to robotic 60 milkers less often 40 20 0 Frequent Infrequent visitors visitors Borderas et al. 2008 Can. J. Anim. Sci. 88:1-8
Weight distribution
Lame cows do not distribute weight evenly between contralateral legs 700 600 500 400 Kg 300 200 100 0 10:52:37 10:53:26 10:54:14 10:55:03 10:55:52 Time BACK LEFT BACK RIGHT TOTAL
Lame cows shift weight more often between contralateral legs 700 600 500 400 Kg 300 200 100 0 10:52:37 10:53:26 10:54:14 10:55:03 10:55:52 Time BACK LEFT BACK RIGHT TOTAL
Weight distribution measures For each pair of legs (front and back) WEIGHT ASSYMETRY Leg weight ratio = weight on lighter/weight on heavier leg E.g. 50% on left leg, 50% on right leg LWR = 50/50 = 1 60% on left leg, 40% on right leg LWR = 40/60 = 0.67 WEIGHT SHIFTING: Variability (SD) over time of weight applied to each pair of legs Number of kicks
Weight distribution Pastell & Kujala 2007 J. Dairy Sci. 90:2283-2292
Not lame Mild lameness Moderate lameness Severe lameness Pastell & Kujala 2007 J. Dairy Sci. 90:2283-2292
Measures of weight distribution can detect lameness promptly Pastell & Kujala 2007 J. Dairy Sci. 90:2283-2292
Combination of methods: Does accuracy increase?
Experimental set-up for gait scoring and measuring weight distribution WEIGHING PLATFORM GAIT 9 m SCORE
Weight distribution and activity (Exp 1) Overall gait score correlated with: • Weight shifting in the rear legs (SD): r = 0.23 ; P = 0.01 • Symmetry of rear legs (leg weight ratio): r = - 0.52; P = 0.002 • Frequency of steps: r = - 0.43; P < 0.001 Chapinal et al. J. Dairy Sci. in press
Weight distribution and activity (Exp 1) Cows with severe hoof infections were more asymmetric in the rear legs • Mean leg weight ratio ± SE = 0.75 ± 0.05 vs. 0.80 ± 0.03; P = 0.006 • OR = 1.2 ; P = 0.03 for each 5% decrease in leg weight ratio Chapinal et al. J. Dairy Sci. in press
Weight distribution and activity (Exp 2) Ketoprofen (3mg/kg BW) / Saline (im) Day 1 Day 2 Day 3 Day 4 Lameness Detection (objective 1) Effect of analgesia (objective 2) * Lame cows: overall gait score > 3 (Flower & Weary 2006)
Lameness Detection: Weight distribution among legs Variable Non-lame Lame OR 95%CI Rear legs weight 1.4 1 24.1 ± 2.0 32.6 ± 2.2 * 1.1– 1.8 variability (SD, kg) Front legs weight 1.6 1 16.5 ± 1.5 22.6 ± 1.7 ** 1.1 – 2.3 variability (SD, kg) Rear leg 0.7 2 0.9 ± 0.02 0.8 ± 0.02 ** 0.5 – 0.9 weight ratio 1 OR adjusted to a 5-kg increase; 2 OR adjusted to a 5% increase Chapinal et al. J. Dairy Sci. in press
Lameness Detection: Activity and walking speed Variable Non-lame Lame OR 95%CI Lying time 787.6 ± 27.1 † 1.1 1 720.1 ± 23.2 1.0 – 1.3 (min/day) Lying bout 1.5 1 73.9 ± 3.9 89.7 ± 4.6 * 1.1 – 2.1 duration (min) Walking speed 0.7 2 1.5 ± 0.4 1.3 ± 0.4 ** 0.5 – 0.9 (m/s) 1 OR adjusted to a 30-min increase; 2 OR adjusted to a 0.1 m/s increase Chapinal et al. J. Dairy Sci. in press
Combining measures of weight distribution, activity and walking speed improved lameness detection 1 0.9 0.8 0.7 Sensitivity 0.6 0.5 0.4 0.3 SD + bout duration + speed (AUC= 0.83) 0.2 SD + lying bout duration (AUC = 0.76) 0.1 SD of the weight of the rear legs (AUC = 0.71) 0 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 1 - Specificity Chapinal et al. J. Dairy Sci. in press
The SD of the weight applied to the rear legs significantly decreased after the ketoprofen injections 40 SD of the weight (kg) 35 30 25 Saline 20 Injections Ketoprofen 15 1 2 3 4 Day Chapinal et al. J. Dairy Sci. in press
Lameness Detection Lame cows show: Asymmetry in weight distribution Frequent weight transfer Lame cows usually have Longer lying bouts Longer daily lying times Decreased activity (steps) although differences not always significant!
Variability in activity measures Lying time (h/day) Lying time (h/d) Farm ID Ito et al. 2009 J. Dairy Sci. 92:4412-4420
Variability in activity measures Non-lame 200 2 milkings / day Lame 180 160 140 Steps/h 120 Steps/h 100 80 60 40 20 0 0 2 4 6 8 10 12 14 16 18 20 22 Hour of day Hour of day Chapinal et al. J. Dairy Sci. in press
Variability in activity measures Non-lame 200 3 milkings / day Lame 180 160 140 Steps/h 120 Steps/h 100 80 60 40 20 0 0 2 4 6 8 10 12 14 16 18 20 22 Hour of day Hour of day Chapinal et al. J. Dairy Sci. in press
Acceleration patterns Chapinal et al. 2010. First North American Conference on Precision Dairy Management
Acceleration patterns Symmetry of acceleration (%) Overall gait score Chapinal et al. 2010. First North American Conference on Precision Dairy Management
Conclusions Automated methods of weight distribution and activity show promise for on-farm lameness detection, particularly when combined These methods may provide a tool for future evaluation of lameness therapies
Practical applications Continuous monitoring of activity (heat detection, lameness, other diseases) Milking robots (+ weighing platform?)
Recommend
More recommend
