The development and validation of a milk feeding behavior alert from automated feeder data to classify calves at risk for a diarrhea bout: A diagnostic accuracy study.

The objective of this diagnostic accuracy study was to develop and validate an alert to identify calves at risk for a diarrhea bout using milk feeding behavior data (behavior) from automated milk feeders (AMF). We enrolled Holstein calves (n = 259) as a convenience sample size from 2 facilities that were health scored daily preweaning and offered either 10 or 15 L/d of milk replacer. For alert development, 132 calves were enrolled and the ability of milk intake, drinking speed, and rewarded visits collected from AMF to identify calves at risk for diarrhea was tested. Alerts that had high diagnostic accuracy in the alert development phase were validated using a holdout validation strategy of 127 different calves from the same facilities (all offered 15 L/d) for -3 to 1 d relative to diarrhea diagnosis. We enrolled calves that were either healthy or had a first diarrheal bout (loose feces ≥2 d or watery feces ≥1 d). Relative change and rolling dividends for each milk feeding behavior were calculated for each calf from the previous 2 d. Logistic regression models and receiver operator curves (ROC) were used to assess the diagnostic ability for relative change and rolling dividends behavior relative to alert d) to classify calves at risk for a diarrhea bout from -2 to 0 d relative to diagnosis. To maximize sensitivity (Se), alert thresholds were based on ROC optimal classification cutoff. Diagnostic accuracy was met when the alert had a moderate area under the ROC curve (≥0.70), high accuracy (Acc; ≥0.80), high Se (≥0.80), and very high precision (Pre; ≥0.85). For alert development, deviations in rolling dividend milk intake with drinking speed had the best performance (10 L/d: ROC area under the curve [AUC] = 0.79, threshold ≤0.70; 15 L/d: ROC AUC = 0.82, threshold ≤0.60). Our diagnostic criteria were only met in calves offered 15 L/d (10 L/d: Se 75%, Acc 72%, Pre 92%, specificity [Sp] 55% vs. 15 L/d: Se 91%, Acc 91%, Pre 89%, Sp 73%). For holdout validation, rolling dividend milk intake with drinking speed met diagnostic criteria for one facility (threshold ≤0.60, Se 86%, Acc 82%, Pre 94%, Sp 50%). However, no milk feeding behavior alerts met diagnostic criteria for the second facility due to poor Se (relative change milk intake -0.36 threshold, Se 71%, Acc 70%, and Pre 97%). We suggest that changes in milk feeding behavior may indicate diarrhea bouts in dairy calves. Future research should validate this alert in commercial settings; furthermore, software updates, support, and new analytics might be required for on-farm application to implement these types of alerts.

Individuality of calves: Linking personality traits to feeding and activity daily patterns measured by precision livestock technology.

Animal personality has established connections with animal performance, resilience, and welfare which are related to stable behavioral patterns. Precision livestock technologies introduce the opportunity to measure these behavior patterns automatically and noninvasively. Thus, the primary aim of this study was to determine if personality traits in dairy calves measured via standardized personality assessments were associated with activity measured via a commercially available accelerometer. Secondary aims of this study were to investigate if personality traits were associated with feeding behaviors measured via an automatic feeding system (AFS) and with average daily gain (ADG). We characterized personality traits of Holstein calves (n = 49) utilizing standardized personality (novel environment, novel person, novel object, and startle) tests. Behaviors from these tests were summarized and 3 factors were extracted from a principal component analysis to represent calf personality traits: fearful, active, and explorative. Factor scores were regressed against behaviors from the accelerometer and AFS and with ADG. We found that calves that were more active were associated with taking more steps in the home environment, consuming more calf starter, and with reaching the benchmark of 1 kg of starter consumed in a day at a younger age. The trait active was also associated with greater ADG throughout the study. In addition, calves that were more explorative in the personality tests were associated with less starter consumed and lower ADG specifically during the weaning period. The findings of this research contribute to the existing literature by further establishing the links between personality traits and the daily behavioral patterns and performance of young calves. This study suggests the potential for using precision technology to assess and characterize personality traits, thereby enhancing their practical applicability on farms. Future research should focus on evaluating how personality traits, as measured through standardized assessments and precision technologies, correlate with deviations in behavior observed in dairy calves during stressors.

A comprehensive evaluation of microchips to measure temperature in dairy calves.

Elevated temperature is often an indicator of an immune response and used in the diagnosis of illness in dairy calves; however, measuring rectal temperature is labor intensive and often not measured daily on the farm. The objective of this study was to measure body temperature using a microchip and determine an appropriate implant site that would passively read body temperature in dairy calves. First, the precision of the temperature microchips and the rectal thermometer were tested ex vivo. Then, Holstein bull calves (n = 12) at 14 ± 12 d (mean ± SD) of age were implanted with microchips subcutaneously by the scutulum of the ear, subcutaneously in the upper scapula (SCAP), and intramuscularly in the trapezius muscle of the neck. One week after implantation, a temperature reading was taken for every microchip implant site using a radiofrequency ID (RFID) reader, as well as rectally and in the tympanic membrane using a digital thermometer every 60 min for 24 h in each calf (hereafter, the hourly study). Additionally, microchip readings and rectal temperatures were taken daily at 0800 h from 8 wk of age (n = 9; 57 ± 12 d of age) until 2 wk postweaning for a subset of the bull calves used in the hourly study (hereafter, the daily study). In the ex vivo trial, the microchip readings were very highly correlated with the rectal thermometer (r = 0.96), and the average coefficient of variation between microchip readings was very low (0.12 ± 0.03%). The relationships between the microchip readings within ear, SCAP, and neck and rectal and tympanic temperatures were analyzed using Pearson correlations and Bland-Altman plots. The ear and neck readings were strongly correlated for the hourly study [individual animal correlation; median (Q1, Q3), r = 0.78 (0.73, 0.84)] and for the daily study [r = 0.79 (0.73, 0.89)] across calves. However, rectal temperature was not significantly correlated with ear, SCAP, neck, or tympanic temperature for the daily and hourly studies. Results suggest that temperature microchips measure temperature appropriately, but temperature is dependent upon the implant site in calves, and temperature measured at ear, SCAP, and neck implant sites cannot be used to estimate rectal temperature. Future research should determine thresholds for fever that are specific to implant sites in calves.