BIG DATA ANALYTICS AND PRECISION ANIMAL AGRICULTURE SYMPOSIUM: Data to decisions.

Big data are frequently used in many facets of business and agronomy to enhance knowledge needed to improve operational decisions. Livestock operations collect data of sufficient quantity to perform predictive analytics. Predictive analytics can be defined as a methodology and suite of data evaluation techniques to generate a prediction for specific target outcomes. The objective of this manuscript is to describe the process of using big data and the predictive analytic framework to create tools to drive decisions in livestock production, health, and welfare. The predictive analytic process involves selecting a target variable, managing the data, partitioning the data, then creating algorithms, refining algorithms, and finally comparing accuracy of the created classifiers. The partitioning of the datasets allows model building and refining to occur prior to testing the predictive accuracy of the model with naive data to evaluate overall accuracy. Many different classification algorithms are available for predictive use and testing multiple algorithms can lead to optimal results. Application of a systematic process for predictive analytics using data that is currently collected or that could be collected on livestock operations will facilitate precision animal management through enhanced livestock operational decisions.

Determination of value of bovine respiratory disease control using a remote early disease identification system compared with conventional methods of metaphylaxis and visual observations.

Mitigation of the deleterious effects of bovine respiratory disease (BRD) is an important issue in the cattle industry. Conventional management of calves at high risk for BRD often includes mass treatment with antimicrobials at arrival followed by visual observation for individual clinical cases. These methods have proven effective; however, control program efficacy is influenced by the accuracy of visual observation. A remote early disease identification (REDI) system has been described that monitors cattle behavior to identify potential BRD cases. The objective of this research was to compare health and performance outcomes using either traditional BRD control (visual observation and metaphylaxis) or REDI during a 60-d postarrival phase in high-risk beef calves. The randomized controlled clinical trial was performed in 8 replicates at 3 different facilities over a 19-mo period. In each replicate, a single load of calves was randomly allocated to receive either conventional management (CONV; total = 8) or REDI (total = 8) as the method for BRD control. Cattle were monitored with each diagnostic method for the first 30 d on feed and performance variables were collected until approximately 60 d after arrival. Statistical differences ( < 0.10) were not identified in common performance (ADG) or health (morbidity, first treatment success, and mortality risk) among the treatment groups. Calves in the REDI pens had a lower ( < 0.01) average number of days on feed at first treatment (9.1 ± 1.2 d) compared with CONV pens (15.8 ± 1.2 d). There were no statistical differences ( > 0.10) in risk of BRD treatment and REDI calves were not administered antimicrobials at arrival; therefore, REDI calves had a lower ( < 0.01) average number of doses of antimicrobials/calf (0.75 ± 0.1 doses) compared with CONV calves (1.67 ± 0.1 doses). In this trial, the REDI system was comparable to conventional management with the potential advantages of earlier BRD diagnosis and decreased use of antimicrobials. Further research should be performed to evaluate the longer-term impacts of the 2 systems.

Pulmonary lesions and clinical disease response to Mannheimia haemolytica challenge 10 days following administration of tildipirosin or tulathromycin.

This clinical trial evaluated the impact of metaphylactic antimicrobial administration 10 d before experimental inoculation with Mannheimia haemolytica (MH) to mitigate pulmonary lesions. Thirty-three crossbreed heifers were procured as a single group and were randomly allocated to 1 of 3 blocks and to treatment, tildipirosin (ZUP; 4 mg/kg) or tulathromycin (DRX; 2.5 mg/kg) or saline (SAL; 1 mL/45.5 kg), within block on arrival at Kansas State University. All trial procedures were staggered by 7-d intervals for each block, resulting in all animals within a block receiving treatment, challenge, and necropsy on the same dates. Heifers within each block received an endoscopic MH challenge 10 d following treatment administration (d 0) and were housed in individual indoor stalls for 3 d postchallenge. Clinical illness scores (CIS), respiration quality scores, appetite scores, and injection site reactions were recorded on all animals from d 0 through d 13. Rectal temperatures were measured once daily on all animals from d 8 through d 13. Heifers were necropsied, and lung lesions were evaluated on d 13. Lung lesion data were evaluated using nonparametric methods (Kruskall-Wallis), and standard least squares models were used to evaluate the remaining variables. The pulmonary lesion scores (percentage of affected lung) ranged from 3.3% to 39.8% for all heifers with 92% (11/12) of ZUP-treated heifers having <10% lesions. Tildipirosin-treated heifers had lower (P < 0.05) lung lesion scores when compared with DRX- and SAL-treated heifers. Lung weight expressed as a percentage of BW was lower (P < 0.05) in ZUP heifers compared to DRX- and SAL-treated heifers. The probability of receiving abnormal CIS, appetite scores, and respiratory scores was lower (P < 0.05) in ZUP-treated heifers compared to DRX- and SAL-treated animals. This study showed that heifers treated with tildipirosin 10 d before MH challenge have less pulmonary damage and fewer clinical signs of illness compared to heifers treated with DRX or SAL.

Effect of Mannheimia haemolytica pneumonia on behavior and physiologic responses of calves during high ambient environmental temperatures.

The objective of this study was to determine the effect of pneumonia during conditions of high (maximum ≥ 32°C) ambient temperatures on physiological and behavioral responses of calves. Eighteen black beef heifers averaging 240 kg were blocked by BW and randomly assigned to 1 of 2 treatment groups: 1) pneumonia induced by bronchoselective endoscopic inoculation with Mannheimia haemolytica (MH; n = 10) and 2) noninoculated controls (CN; n = 8). Nasal passage and rectal temperatures were measured every 2 h for 24 h after challenge and then twice daily for 9 d. Accelerometers, pedometers, and positioning devices monitored cattle behavior within the pen for 9 d after challenge. Blood samples were collected on trial d 0, 0.5, 1, 2, 3, 7, and 9 and were analyzed to determine the concentration of substance P, cortisol, haptoglobin, and metalloproteinase. All calves in the MH group were euthanized and necropsied on trial d 9. All MH calves became clinically ill postchallenge. A treatment × time interaction (P < 0.05) was evident for nasal and rectal temperatures, behavior, weight, and blood analysis. Rectal temperatures in MH were higher (P < 0.01) than CN during the period from 6 to 24 h after challenge. Conversely, nasal passage temperatures were less in MH calves compared with CN at 12 to 22 h after challenge. Calves in MH spent less time at the grain bunk, less time at the hay feeder, and more time lying down during the early pneumonia period compared with CN calves. Also, MH calves had significantly greater concentrations of blood biomarkers of pain (substance P) on d 0.5 (P < 0.01); stress (cortisol) on d 0.5 and 1 (P < 0.01); haptoglobin on d 0.5, 1, 2, 3, 7 (P < 0.01); and metalloproteinase on d 1, 2, and 3 (P < 0.01) compared with CN calves. At necropsy, all MH calves had right cranioventral bronchopneumonia (median lung lesions = 6.8%). Mannheimia haemolytica pneumonia caused significantly more changes in behavior and increased biomarkers during high (maximum ≥32°C) ambient temperatures compared with control calves. The results of this study may guide research in the development of objective assessment tools for management of cattle affected with bovine respiratory disease during extreme summer conditions.