Bovine respiratory disease (BRD) represents one of the major disease challenges affecting preweaning dairy-bred calves. Previous studies have shown that differences in feeding and activity behaviors exist between healthy and diseased calves affected by BRD. The aim of this study was to develop and assess the accuracy of models designed to predict BRD from feeding and activity behaviors. Feeding and activity behaviors were recorded for 100 male preweaning calves between ~8 to 42 d of age. Calves were group housed with ad libitum access to milk via automatic milk feeders, water, starter diet, and straw. Activity was monitored via a leg-mounted accelerometer. Health status of individual calves was monitored daily using an adapted version of the Wisconsin Scoring System to identify BRD. Three models were created to predict disease: (1) deviation from normal lying time based on moving averages (MA); (2) random forest (RF), a machine learning technique based on feeding and activity variables; and (3) a combination of RF and MA output. For the MA model, lying time was predicted based on behavior over previous days (3- and 7-d MA) and the expected value for the current day (based on calf age; measured using accelerometers). Data were not split into training and test data sets. Occasions when the actual lying time increased >9% of predicted lying time were classified as a deviation from normal and a disease alert was provided. Both feeding and activity behaviors were included within the RF model. Data were split into training (70%) and test (30%) data sets based on disease events. Events were classified as 2 d before, the day(s) of the disease event, and 2 d after the event. Accuracy of models was assessed using sensitivity, specificity, balanced accuracy, and Matthews correlation coefficient (MCC). If a positive disease prediction agreed with an actual disease event within a 3-d rolling window, it was classified as a true positive. Stand-alone models (RF; MA) showed high specificity (0.95; 0.97), moderate sensitivity (0.35; 0.43), balanced accuracy (0.65; 0.64), and MCC (0.25; 0.29). Combining outputs increased accuracy (specificity = 0.95, sensitivity = 0.54, balanced accuracy = 0.75, MCC = 0.36). The work presented is the first to demonstrate the use of modeling data derived from precision livestock farming techniques that monitor feeding and activity behaviors for early detection of BRD in preweaning calves, offering a significant advance in health management of youngstock.

Calf housing is naturally thermodynamic, with interactions between various elements such as wind speed, air temperature, and humidity. This study investigated the effect of the proportion of time for which calves were exposed to effective environmental temperatures below their lower critical temperature (LCT) on their daily liveweight gain (DLWG) within their first month of life. This study used the naturally occurring climatic environment, whereas other such studies have been conducted under climatically controlled conditions. Air temperature (°C), relative humidity (%), and wind speed (m/s) were recorded within the calf housing from birth until approximately 28 days of age, with calves being health-scored and weighed at regular intervals. Calves were housed from birth until 6–14 days old in individual hutches, and then moved into group housing igloo pens. Whilst individually housed, calves that spent less than 32% of their time below their LCT had a DLWG of 0.06 ± 0.34 kg/d (mean ± SE) compared to calves that spent more than 97% of their time below their LCT, which had a DLWG of −0.19 ± 0.045 kg/d. When group housed, calves that spent less than 1% of their time below their LCT had a DLWG of 0.59 ± 0.18 kg/d, whereas calves that spent more than 28% of their time below their LCT had a DLWG of 0.53 ± 0.23 kg/d. The proportion of time for which calves were exposed to effective environmental temperatures below their LCT had a significant effect on DLWG when calves were individually housed. Therefore, exposure to effective environmental temperatures below the LCT can be detrimental to the growth of the calf in the early stages of its life.

Bovine respiratory disease (BRD) is a major welfare and productivity issue for calves. Despite the extensive negative impacts on calf welfare and performance, BRD remains challenging to detect and treat effectively. However, the clinical signs of disease are only one aspect of the disease that is experienced by the individual. The assessment of emotional experience in animals is not straightforward, but it is increasingly recognised that the quality of behaviour and demeanour of an individual is a reflection of their internal emotional state. The aim of the present study was to complete the content validation stage of the development process for a health-related quality of life (HRQOL) tool. This was based around indicators from an existing conceptual framework containing twenty-three indicators in two domains (clinical signs and behavioural expression). The content validation stage involves engaging with key stakeholders. For this study, this took the form of a survey and discussions with focus groups, which are standard methods in this field. A survey and stakeholder focus groups were conducted to assess the usefulness of each indicator and its relevance for inclusion within a HRQOL tool. In the survey, participants were asked to rate the usefulness of each of the indicators using a 4-point scale which were then dichotomised into 'useful' and 'less useful'. Based on the 'useful' result, each indicator within the domains was ranked. A similar approach was taken with the responses from the focus groups. Focus group participants were asked to select indicators that they felt were of use and the result of this was used to rank each of the indicators. The ranks of the indicators from both the survey and the focus groups along with the transcripts from the focus groups were used to determine the indicators from each domain to include within the HRQOL tool. Indicators within the clinical signs domain that were included were nasal discharge, cough, respiratory effort, ocular appearance (discharge and vibrancy), body and head posture and ear carriage. For the domain of behavioural expression, the indicators included were movement to feed, responsiveness, spatial proximity, volume of feed intake, motivation at feed and vigour. The next stage will be to validate the construction of the HRQOL tool through its use in practice. The inclusion of indicators that allow the experiential aspects of disease to be recorded in health assessments will likely increase the ability of farmers and others to detect respiratory disease in calves.