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

Abstract

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.

Comparing regression, naive Bayes, and random forest methods in the prediction of individual survival to second lactation in Holstein cattle

“…Another possibility would be to investigate more advanced machine-learning methods such as neural networks. Indeed, neural networks outperformed regression and random forest for the individual prediction of pregnancy status (Fenlon et al, 2017). Neural networks are powerful but complex methods that often require a large number of records to be trained.…”

Automated prediction of mastitis infection patterns in dairy herds using machine learning

“…ML has been used within the field of cattle medicine, for example in attempting to predict fertility outcomes 23 , high somatic cell counts 24 , and the onset of calving 25 . With the advent of increased "big data" within farm animal medicine, the potential to translate this into "smart data" is increasing 26 ; making full use of data already being collected.…”

Review: Application and Prospective Discussion of Machine Learning for the Management of Dairy Farms

“…Although this indicates good predictive values, the sample size included only n = 53 calving instances, thus, it would make sense to test the trained model on a larger dataset. Furthermore, Fenlon et al [ 76 ] correctly predicted 75% of calving instances using a neural network and multinomial regression models, with 3.7% and 4.5% errors of the predicted probability, respectively. To date, some sensors that promise early warnings for calving detection are available on the market; however, little research defining the reliability of such alarms is available.…”