Using Machine Learning and Behavioral Patterns Observed by Automated Feeders and Accelerometers for the Early Indication of Clinical Bovine Respiratory Disease Status in Preweaned Dairy Calves

Abstract

The objective of this retrospective cohort study was to evaluate a K-nearest neighbor (KNN) algorithm to classify and indicate bovine respiratory disease (clinical BRD) status using behavioral patterns in preweaned dairy calves. Calves (N=106) were enrolled in this study, which occurred at one facility for the preweaning period. Precision dairy technologies were used to record feeding behavior with an automated feeder and activity behavior with a pedometer (automated features). Daily, calves were manually health-scored for bovine respiratory disease (clinical BRD; Wisconsin scoring system, WI, USA), and weights were taken twice weekly (manual features). All calves were also scored for ultrasonographic lung consolidation twice weekly. A clinical BRD bout (day 0) was defined as 2 scores classified as abnormal on the Wisconsin scoring system and an area of consolidated lung ≥3.0 cm2. There were 54 calves dignosed with a clinical BRD bout. Two scenarios were considered for KNN inference. In the first scenario (diagnosis scenario), the KNN algorithm classified calves as clinical BRD positive or as negative for respiratory infection. For the second scenario (preclinical BRD bout scenario), the 14 days before a clinical BRD bout was evaluated to determine if behavioral changes were indicative of calves destined for disease. Both scenarios investigated the use of automated features or manual features or both. For the diagnosis scenario, manual features had negligible improvements compared to automated features, with an accuracy of 0.95 ± 0.02 and 0.94 ± 0.02, respectively, for classifying calves as negative for respiratory infection. There was an equal accuracy of 0.98 ± 0.01 for classifying calves as sick using automated and manual features. For the preclinical BRD bout scenario, automated features were highly accurate at -6 days prior to diagnosis (0.90 ± 0.02), while manual features had low accuracy at -6 days (0.52 ± 0.03). Automated features were near perfectly accurate at -1 day before clinical BRD diagnosis compared to the high accuracy of manual features (0.86 ± 0.03). This research indicates that machine-learning algorithms accurately predict clinical BRD status at up to -6 days using a myriad of feeding behaviors and activity levels in calves. Precision dairy technologies hold the potential to indicate the BRD status in preweaned calves.

Early detection of bovine respiratory disease in pre-weaned dairy calves using sensor based feeding, movement, and social behavioural data

“…The accuracy achieved in the present study (0.773) is like that attained by Casella, et al 41 who reported an accuracy of between 0.70 and 0.90 depending on the proposed budget. In contrast our model performance was much lower than that found by Cantor, et al 42 who achieved accuracy, precision, recall and F1-score values of 0.99 each. Although, it should be noted that Casella, et al 41 and Cantor, et al 42 included the individual score for each area (nose, eye, cough etc.)…”

“…In contrast our model performance was much lower than that found by Cantor, et al 42 who achieved accuracy, precision, recall and F1-score values of 0.99 each. Although, it should be noted that Casella, et al 41 and Cantor, et al 42 included the individual score for each area (nose, eye, cough etc.) as features in the model, which is likely to be beneficial in the prediction of sick calves labelled as such based on this scoring system.…”

Strategies for Bovine Respiratory Disease (BRD) Diagnosis and Prognosis: A Comprehensive Overview

“…Marchesini et al found that this model's sensitivity and specificity reached 81% and 95%, respectively, three days prior to the clinical diagnosis of BRD and lameness in cattle [248]. Various studies have utilized pedometers and different types of accelerometers-including tri-axial, ear-tag-based, and electronic-to measure cattle activity levels and identify behaviors indicative of BRD [92,237,[249][250][251][252].…”

Decoding Bovine Behavior: A Machine Learning Analysis of Disease and Event Detection

“…Therefore, it is essential for farmers to closely monitor calving and seek veterinary assistance if any issues arise to ensure the well-being of both the cow and calf. To this aim, researchers have investigated a variety of strategies and tactics which includes animal behavior (Cantor et al, 2022), Acoustic monitoring has been utilized to detect distinct vocal patterns associated with calving (Alexander C. et al, 2020).…”