Implementation of compact calving at the farm level: A qualitative analysis of farmers operating pasture-based dairy systems in Ireland

Pasture-based dairy systems aim to maximize the proportion of grazed pasture in the cow's diet by having a compact calving season that coincides with the onset of the grass growing season. In Ireland, where pasture-based systems are dominant, a key performance indicator that reflects the degree of compact calving is referred to as 6-wk calving rate (6-wk CR). Although the industry target is 90%, the national average 6-wk CR in Ireland is currently 67%. The aim of this study was to use qualitative research to understand in depth farmers' experiences in implementing a high 6-wk CR. Ten case-study dairy farmers were interviewed using the biographical narrative interpretive method. We identified 5 broad and often interrelated themes evoked by farmers regarding 6-wk CR: the "good" farmer; support networks; free time and family time; simplicity of a structured system; and profitability and monetary gain. The findings of this study identify complexities and challenges at farm level when it comes to increasing 6-wk CR, such as increased workload and challenges associated with large numbers of male calves born during a condensed calving season. Benefits experienced by farmers as a result of increasing 6-wk CR included increased days in milk and consequently improved cash flow as well as increased grass utilization. Our findings are of interest to researchers and extension agents involved in programs concerned with reproductive management in pasture-based dairy systems.

The effect of growth rate on reproductive outcomes in replacement dairy heifers in seasonally calving, pasture-based systems

The effect of average daily gain (ADG) on reproductive outcomes in replacement dairy heifers was investigated. All heifers were managed in the typical Irish spring calving, pasture-based system, where the herd calves in 1 block between January and April and the majority of the diet comprises grazed grass. Heifer calves (n = 399) from 7 herds were weighed at birth and at the beginning of the breeding season, and ADG was calculated. Service dates and pregnancy diagnosis results were recorded, and conception dates were calculated. Days open (DO) was defined as the number of days between the beginning of the breeding season and conception. Genetic data were retrieved from the Irish Cattle Breeding Federation database. A Cox proportional hazard model was constructed to identify variables with a significant effect on DO. An accelerated failure time model was used to predict survival curves and median survival times for different combinations of the significant variables. The ADG ranged from 0.41 to 0.91 kg/d, with a median of 0.70 kg/d. Frailty effect of farm within year, maintenance subindex of the economic breeding index, and ADG had a significant effect on DO. Derived from the final accelerated failure time model, the predicted median DO for a heifer with an ADG of 0.40, 0.70, or 0.90 kg/d aged 443 d at the beginning of the breeding season and with a maintenance subindex in the second tercile were 27, 16, and 11 d, respectively.

A discussion of calibration techniques for evaluating binary and categorical predictive models

Modelling of binary and categorical events is a commonly used tool to simulate epidemiological processes in veterinary research. Logistic and multinomial regression, naïve Bayes, decision trees and support vector machines are popular data mining techniques used to predict the probabilities of events with two or more outcomes. Thorough evaluation of a predictive model is important to validate its ability for use in decision-support or broader simulation modelling. Measures of discrimination, such as sensitivity, specificity and receiver operating characteristics, are commonly used to evaluate how well the model can distinguish between the possible outcomes. However, these discrimination tests cannot confirm that the predicted probabilities are accurate and without bias. This paper describes a range of calibration tests, which typically measure the accuracy of predicted probabilities by comparing them to mean event occurrence rates within groups of similar test records. These include overall goodness-of-fit statistics in the form of the Hosmer-Lemeshow and Brier tests. Visual assessment of prediction accuracy is carried out using plots of calibration and deviance (the difference between the outcome and its predicted probability). The slope and intercept of the calibration plot are compared to the perfect diagonal using the unreliability test. Mean absolute calibration error provides an estimate of the level of predictive error. This paper uses sample predictions from a binary logistic regression model to illustrate the use of calibration techniques. Code is provided to perform the tests in the R statistical programming language. The benefits and disadvantages of each test are described. Discrimination tests are useful for establishing a model's diagnostic abilities, but may not suitably assess the model's usefulness for other predictive applications, such as stochastic simulation. Calibration tests may be more informative than discrimination tests for evaluating models with a narrow range of predicted probabilities or overall prevalence close to 50%, which are common in epidemiological applications. Using a suite of calibration tests alongside discrimination tests allows model builders to thoroughly measure their model's predictive capabilities.

The creation and evaluation of a model to simulate the probability of conception in seasonal-calving pasture-based dairy heifers

Background

Herd fertility in pasture-based dairy farms is a key driver of farm economics. Models for predicting nulliparous reproductive outcomes are rare, but age, genetics, weight, and BCS have been identified as factors influencing heifer conception. The aim of this study was to create a simulation model of heifer conception to service with thorough evaluation.

Methods

Artificial Insemination service records from two research herds and ten commercial herds were provided to build and evaluate the models. All were managed as spring-calving pasture-based systems. The factors studied were related to age, genetics, and time of service. The data were split into training and testing sets and bootstrapping was used to train the models. Logistic regression (with and without random effects) and generalised additive modelling were selected as the model-building techniques. Two types of evaluation were used to test the predictive ability of the models: discrimination and calibration. Discrimination, which includes sensitivity, specificity, accuracy and ROC analysis, measures a model’s ability to distinguish between positive and negative outcomes. Calibration measures the accuracy of the predicted probabilities with the Hosmer-Lemeshow goodness-of-fit, calibration plot and calibration error.

Results

After data cleaning and the removal of services with missing values, 1396 services remained to train the models and 597 were left for testing. Age, breed, genetic predicted transmitting ability for calving interval, month and year were significant in the multivariate models. The regression models also included an interaction between age and month. Year within herd was a random effect in the mixed regression model. Overall prediction accuracy was between 77.1% and 78.9%. All three models had very high sensitivity, but low specificity. The two regression models were very well-calibrated. The mean absolute calibration errors were all below 4%.

Conclusion

Because the models were not adept at identifying unsuccessful services, they are not suggested for use in predicting the outcome of individual heifer services. Instead, they are useful for the comparison of services with different covariate values or as sub-models in whole-farm simulations. The mixed regression model was identified as the best model for prediction, as the random effects can be ignored and the other variables can be easily obtained or simulated.

A comparison of 4 predictive models of calving assistance and difficulty in dairy heifers and cows

The aim of this study was to build and compare predictive models of calving difficulty in dairy heifers and cows for the purpose of decision support and simulation modeling. Models to predict 3 levels of calving difficulty (unassisted, slight assistance, and considerable or veterinary assistance) were created using 4 machine learning techniques: multinomial regression, decision trees, random forests, and neural networks. The data used were sourced from 2,076 calving records in 10 Irish dairy herds. In total, 19.9 and 5.9% of calving events required slight assistance and considerable or veterinary assistance, respectively. Variables related to parity, genetics, BCS, breed, previous calving, and reproductive events and the calf were included in the analysis. Based on a stepwise regression modeling process, the variables included in the models were the dam's direct and maternal calving difficulty predicted transmitting abilities (PTA), BCS at calving, parity; calving assistance or difficulty at the previous calving; proportion of Holstein breed; sire breed; sire direct calving difficulty PTA; twinning; and 2-way interactions between calving BCS and previous calving difficulty and the direct calving difficulty PTA of dam and sire. The models were built using bootstrapping procedures on 70% of the data set. The held-back 30% of the data was used to evaluate the predictive performance of the models in terms of discrimination and calibration. The decision tree and random forest models omitted the effect of twinning and included only subsets of sire breeds. Only multinomial regression and neural networks explicitly included the modeled interactions. Calving BCS, calving difficulty PTA, and previous calving assistance ranked as highly important variables for all 4 models. The area under the receiver operating characteristic curve (ranging from 0.64 to 0.79) indicates that all of the models had good overall discriminatory power. The neural network and multinomial regression models performed best, correctly classifying 75% of calving cases and showing superior calibration, with an average error in predicted probability of 3.7 and 4.5%, respectively. The neural network and multinomial regression models developed are both suitable for use in decision-support and simulation modeling.