Comparison of linear and non-linear decision boundaries to detect feedlot bloat using intensive data collection systems on Angus × Hereford steers.

Ruminal tympany (bloat) has long been an issue for large and small livestock operations. Though improvements in feedlot management practices have reduced its occurrence, it is still highly prevalent and is known to detrimentally affect animal performance, welfare, and in many instances, lead to animal death. Current decision support systems and diet formulation software omit the inclusion of bloat prediction based on animal performance. Here, we aim to predict bloat incidence in implanted and non-implanted feedlot steers from performance data comparing linear (LDB) and non-linear decision boundaries. Eighteen crossbred Angus × Hereford steers: BW (491.13 ± 25.78 kg) and age (12 ± 1 mo) were randomly distributed into implanted and non-implanted treatments. All animals were randomly assigned to one of two pens fit with automated monitoring systems for BW, freshwater intake, and water intake behavior: water intake event visit, no water intake event visit (NWIE), and time spent drinking. DM intake (DMI) was individually recorded from all animals through the Calan Gate system for 135 d (30 d adaptation, 105 d experimental diet). Incidences of bloat were recorded as bloat instances regardless of severity to ensure that early onset detection of bloat was recorded and properly identified in predictive models. Logistic regression with a binomial distribution and a logit link function was utilized to predict the incidences of bloat through LDB. Feature selection and penalization of coefficients were explored through L1 (sum of absolute values) and L2 (sum of squares) penalization to avoid overfitting of models. Additional NLDB and a non-parametric LDB are examined for prediction. Accuracy, specificity, and sensitivity were high for the models reported. No significant differences were observed between LDB and NLDB, with the highest specificity (predicting bloat) value of 0.820 for stepwise feature selection algorithms, and a value of 0.832 for the artificial neural network. Highest accuracy was 0.829 for ridge regression, and 0.847 for the random forest with hyperparameter tuning. DM intake, BW, and NWIE were the three most important variables for the prediction of feedlot bloat showing clear drops in DMI and BW and increases in NWIE when animals bloated. The lack of difference in predictive performance between LDB and NLDB highlights the often-overlooked concept that machine learning algorithms are not always the only/best modeling technique. Additionally, the models reported herein carry acceptable predictive performance for inclusion into management decisions that reduce bloat incidences in feedlot cattle.

Effects of lipid and starch supplementation as water intake mitigation techniques on performance and efficiency of nursing Holstein calves.

Exploring alternative supplementation sources capable of maximizing feed and water efficiency in nursing Holstein calves is often ignored. The goals herein involve investigating the effects of two isoenergetic supplements on a nonmedicated milk replacer diet on total water intake, milk water intake, fresh water intake, feed intake parameters, and performance of Holstein nursing bull calves. Twenty-three animals (body weight [BW] = 94.67 ± 12.07 kg, age = 67 days old) were randomly assigned to one of three treatments for 68 days: control (CON; ad libitum milk replacer, n = 7), carbohydrate supplement (CHO; corn starch on top of ad libitum milk replacer-based diet, n = 8), or lipid supplement (FAT; menhaden fish oil on top of ad libitum milk replacer-based diet, n = 8). The isoenergetic supplementation consisted of 3% menhaden fish oil addition on DM basis for FAT. This was matched energetically with corn starch for the CHO group resulting in a 7% composition in DM basis. All animals were provided free access to mineral mix and 120 g daily dried microbrewer's spent grains (BG). Data were analyzed with the GLMMIX procedure of SAS in a completely randomized design with the diets as a fixed effect. Dry matter intake (DMI) adjusted by average daily gain (ADG; DMI/ADG) resulted in significantly lower values for supplemented groups with CON = 2.48, CHO = 2.38, and FAT = 2.27 kg/kg (ADG) (P = 0.033). Energy intake values were lower for CON when analyzing metabolizable energy intake (P < 0.0001), net energy intake for maintenance (P < 0.0001), and net energy intake for gain (P < 0.0001), followed by CHO, and then FAT. Total water intake (P < 0.0001), milk water intake (P < 0.0001), and fresh water intake (P < 0.0001) all resulted in CHO consuming 0.5 L or less water than the other two treatments. Energy requirements as digestible energy (P < 0.0001), metabolizable energy (P < 0.0001), net energy for maintenance (P < 0.0001), and net energy for gain (P < 0.0001) were lower for CHO, followed by CON, and then FAT having the highest requirements. Similar results were observed for residual feed (RFI; P = 0.006) and residual water intakes (RTWI; P = 0.902). Ultimately, no performance differences were detected with regards to BW (CON = 146.71, CHO = 146.25, and FAT = 150.48 kg; P > 0.1). These results indicate that lipid-based and starch-based supplementation can potentially increase feed efficiency and decrease voluntary water intake without adversely affecting performance.

Effect of ultraviolet light, organic acids, and bacteriophage on Salmonella populations in ground beef.

This study investigated individual and combined effects of organic acids, bacteriophages, and ultraviolet light interventions on Salmonella populations in ground beef. Beef trim was inoculated with four Salmonella strains to result in a contamination level of 3.5 log CFU/g after grinding. Lactic (LA) and peroxyacetic (PAA) acids, bacteriophages (S16 and FO1a) (BA), and ultraviolet light (UV) were applied on fresh trim prior to grinding. Applications of individual or combined organic acids did not significantly decrease Salmonella populations in ground beef. Individual applications of BA and UV light decreased approximately 1 log CFU/g (P<0.05). Combined applications of BA and UV provided an optimal decrease of 2 log CFU/g (P<0.05). Organic acid applications do not reduce Salmonella populations in ground beef when applied on trim prior to grinding. Combined applications of UV and BA may be used in industry settings to improve Salmonella control in ground beef.