Sensor-based detection of a Haemonchus contortus (Barber's pole worm) infection in sheep

Haemonchus contortus, or Barber's Pole worm, is considered one of the most pathogenic parasites of sheep due to the production, profitability and animal welfare implications associated with infections. However, detection of H. contortus infections by routine observation of sheep flocks is difficult, and producers are usually unaware of a problem until animals are severely infected. The aim of the current study was to explore the potential for accelerometer-based activity monitoring to detect H. contortus infections in sheep. A three-month clinical study was conducted in Central Queensland, Australia, whereby 45, 12-month-old merino wethers were randomly allocated to one of three treatment groups: control (n = 9), low H. contortus infection (n = 18) or high H. contortus infection (n = 18). Infection occurred on Day 0, and accelerometer sensors were attached to a halter and deployed on all animals from Day 21 to Day 70. Animals were sampled weekly (faecal and blood) and treated with an anthelmintic on Day 56. Following the clinical period, five study animals were observed for a total of five hours to compare direct behavioral observations against accelerometer data. This was then used to develop a machine learning (ML) model to classify the accelerometer data into active or inactive behavior, which was further summarized to determine the proportion of time spent active per day. The most valuable features in the selected ML model were movement variation (MV), maximum X-axis value (MaxX), standard deviation of the X-axis (SDX), maximum Y-axis value (MaxY) and standard deviation of the Z-axis (SDZ). Linear mixed-effects models identified a significant difference in all sheep activity pre- and post-anthelmintic drench on Day 56 (P < 0.001). Conversely, there was no significant difference between activity levels of infected animals compared to controls (P = 0.14). To further explore how the activity of sheep changed with clinical presentations of H. contortus infections, weekly faecal egg count (FEC) and blood packed cell volume (PCV) were compared to sheep activity using a Spearman's rank correlation test. There was a weak but significant negative correlation between FEC and sheep activity (P < 0.001) and a weak but significant positive correlation between PCV and sheep activity (P < 0.001). In conclusion, this study has shown that accelerometer-based activity monitoring may be able to identify changes in sheep activity associated with clinical presentations of H. contortus infections and between periods prior to and following anthelmintic treatment. However, the ability to detect activity differences between infected and control animals was less clear. Further research is needed to determine the impact of individual behavior variability and flock dynamics when using on-animal sensors for the detection of behavioral changes associated with disease.