The efficacy of predicting dystocia in yearling beef heifers: II. Using discriminant analysis

Association between dam and calf measurements with overall and fetopelvic dystocia in Holstein heifers

We investigated the relationship between dam's pelvic and calf's dimensions with dystocia due to fetopelvic disproportion in the Holstein breed and estimated risk factors and dystocia probability. For this purpose, external pelvic measurements were performed in 402 heifers 15 ± 11 (1-38) days ante-partum and specific conformation measurements were obtained from their calves 1.7 ± 1.2 post-partum. Dystocia was defined as the inability of the heifer to complete parturition spontaneously within 120 min after the appearance of the amnion with normal presentation, position and posture or as having definite obstetrical obstacles within 60 min. Overall and fetopelvic disproportion dystocia incidence was 10.4% and 5.2%, respectively. Heifer measurements mainly influenced overall dystocia, whereas calf conformation was related solely with fetopelvic dystocia. Specifically, heifers with a small pelvis (hip width <49.95 cm, pelvic inlet area <333.2 cm2, pelvic volume <7799.2 cm3) had 2.8 to 3.5 times greater incidence of overall dystocia (19.0-20.8%) compared to heifers with a larger pelvis (incidence of 7.0-7.6%). Regarding calf factors, sex (male calves), body weight, chest circumference and fetlock joint circumference significantly increased the odds of experiencing dystocia due to fetopelvic disproportion compared with female, lighter or smaller calves. In a backward elimination model with independent variables treated as continuous, an area under the ROC curve of 0.66 regarding the prediction of overall dystocia based on heifer pelvic length, and of 0.64 for the prediction of fetopelvic dystocia based on fetlock joint circumference was found. The combination of the two variables in one model improved the ROC area to 0.71 regarding dystocia due to fetopelvic disproportion, reaching acceptable level of discrimination. Our findings indicate that dystocia due to fetopelvic disproportion in heifers is mainly influenced by the fetal side. Additionally, the estimation of pelvic dimensions of the dam before parturition and specific conformation characteristics of the calf during parturition, especially fetlock joint circumference, could aid obstetricians and herdsmen regarding dystocia probability and parturition surveillance.

Classification of Daily Body Weight Gains in Beef Calves Using Decision Trees, Artificial Neural Networks, and Logistic Regression

The aim of the present study was to compare the predictive performance of decision trees, artificial neural networks, and logistic regression used for the classification of daily body weight gains in beef calves. A total of 680 pure-breed Simmental and 373 Limousin cows from the largest farm in the West Pomeranian Province, whose calves were fattened between 2014 and 2016, were included in the study. Pre-weaning daily body weight gains were divided into two categories: A-equal to or lower than the weighted mean for each breed and sex and B-higher than the mean. Models were developed separately for each breed. Sensitivity, specificity, accuracy, and area under the curve on a test set for the best model (random forest) were 0.83, 0.67, 0.76, and 0.82 and 0.68, 0.86, 0.78, and 0.81 for the Limousin and Simmental breeds, respectively. The most important predictors were daily weight gains of the dam when she was a calf, daily weight gains of the first calf, sex of the third calf, milk yield at first lactation, birth weight of the third calf, dam birth weight, dam hip height, and second calving season. The selected machine learning models can be used quite effectively for the classification of calves based on their daily weight gains.

The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle

OBJECTIVE

The aim of this study was to verify the usefulness of artificial neural networks (ANN), multivariate adaptive regression splines (MARS), naïve Bayes classifier (NBC), general discriminant analysis (GDA), and logistic regression (LR) for dystocia detection in Polish Holstein-Friesian Black-and-White heifers and cows and to indicate the most influential predictors of calving difficulty.

METHODS

A total of 1,342 and 1,699 calving records including six categorical and four continuous predictors were used. Calving category (difficult vs easy or difficult, moderate and easy) was the dependent variable.

RESULTS

The maximum sensitivity, specificity and accuracy achieved for heifers on the independent test set were 0.855 (for ANN), 0.969 (for NBC), and 0.813 (for GDA), respectively, whereas the values for cows were 0.600 (for ANN), 1.000 and 0.965 (for NBC, GDA, and LR), respectively. With the three categories of calving difficulty, the maximum overall accuracy for heifers and cows was 0.589 (for MARS) and 0.649 (for ANN), respectively. The most influential predictors for heifers were an average calving difficulty score for the dam's sire, calving age and the mean yield of the farm, where the heifer was kept, whereas for cows, these additionally included: calf sex, the difficulty of the preceding calving, and the mean daily milk yield for the preceding lactation.

CONCLUSION

The potential application of the investigated models in dairy cattle farming requires, however, their further improvement in order to reduce the rate of dystocia misdiagnosis and to increase detection reliability.

Genome-wide association for heifer reproduction and calf performance traits in beef cattle

The aim of this study was to identify SNP markers that associate with variation in beef heifer reproduction and performance of their calves. A genome-wide association study was performed by means of the generalized quasi-likelihood score (GQLS) method using heifer genotypes from the BovineSNP50 BeadChip and estimated breeding values for pre-breeding body weight (PBW), pregnancy rate (PR), calving difficulty (CD), age at first calving (AFC), calf birth weight (BWT), calf weaning weight (WWT), and calf pre-weaning average daily gain (ADG). Data consisted of 785 replacement heifers from three Canadian research herds, namely Brandon Research Centre, Brandon, Manitoba, University of Alberta Roy Berg Kinsella Ranch, Kinsella, Alberta, and Lacombe Research Centre, Lacombe, Alberta. After applying a false discovery rate correction at a 5% significance level, a total of 4, 3, 3, 9, 6, 2, and 1 SNPs were significantly associated with PBW, PR, CD, AFC, BWT, WWT, and ADG, respectively. These SNPs were located on chromosomes 1, 5-7, 9, 13-16, 19-21, 24, 25, and 27-29. Chromosomes 1, 5, and 24 had SNPs with pleiotropic effects. New significant SNPs that impact functional traits were detected, many of which have not been previously reported. The results of this study support quantitative genetic studies related to the inheritance of these traits, and provides new knowledge regarding beef cattle quantitative trait loci effects. The identification of these SNPs provides a starting point to identify genes affecting heifer reproduction traits and performance of their calves (BWT, WWT, and ADG). They also contribute to a better understanding of the biology underlying these traits and will be potentially useful in marker- and genome-assisted selection and management.

Bioeconomic factors of beef heifer maturity to consider when establishing criteria to optimally select and/or retain herd replacements

Understanding the biology of heifer maturity and its relationship to calving difficulty and subsequent breeding success is a vital step in building a bioeconomic model to identify optimal production and profitability. A limited dependent variable probit model is used to quantify the responses among heifer maturities, measured by a maturity index (MI), on dystocia and second pregnancy. The MI account for heifer age, birth BW, prebreeding BW, nutrition level, and dam size and age and is found to be inversely related to dystocia occurrence. On average there is a 2.2% increase in the probability of dystocia with every 1 point drop in the MI between the MI scores of 50 and 70. Statistically, MI does not directly alter second pregnancy rate; however, dystocia does. The presence of dystocia reduced second pregnancy rates by 10.67%. Using the probability of dystocia predicted from the MI in the sample, it is found that on average, every 1 point increase in MI added 0.62% to the probability of the occurrence of second pregnancy over the range represented by the data. Relationships among MI, dystocia, and second pregnancy are nonlinear and exhibit diminishing marginal effects. These relationships indicate optimal production and profitability occur at varying maturities, which are altered by animal type, economic environment, production system, and management regime. With these captured relationships, any single group of heifers may be ranked by profitability given their physical characteristics and the applicable production, management, and economic conditions.

A retrospective analysis of factors contributing to calf mortality and dystocia in beef cattle

Records of 2191 calvings from the Clemson University Beef Physiology Unit between 1981 and 1993 were analyzed to determine factors affecting malpresentation, mortality and dystocia. Only 20 (0.91%) parturitions involved malpresentation: posterior presentation (n = 14), leg deviations (n = 3), head deviations (n = 2) and breech birth (n = 1). Dystocia affected calf mortality within 24 h of birth (P < 0.05), with mortality increasing as the severity of dystocia increased. There was an overall 4.5% death loss within 24 h of birth, with 4 and 7% mortality rates for calves from multiparous and primiparous dams, respectively (P < 0.05). Mortality was higher for bull vs heifer calves (P < 0.05). Ninety-four percent of calvings were unassisted, while 6% were assisted births. Dystocia was greater (P < 0.01) in primiparous (17%) than in multiparous dams (4%). In births involving dystocia, 28.1% required mild traction, 69.3% required heavy traction and 2.6% required Cesarean section. Birth weights associated with normal births and mild traction (36 and 36 kg) were lighter than those associated with heavy traction and Cesarean section (40 and 42 kg, respectively; P < 0.05). In conclusion, malpresentations were too few to be of significance, and dystocia influenced mortality within 24 h of birth. Calf birth weight and parity of dam explained most of the observed variations in dystocia.