Prediction of insemination outcomes in Holstein dairy cattle using alternative machine learning algorithms.

When making the decision about whether or not to breed a given cow, knowledge about the expected outcome would have an economic impact on profitability of the breeding program and net income of the farm. The outcome of each breeding can be affected by many management and physiological features that vary between farms and interact with each other. Hence, the ability of machine learning algorithms to accommodate complex relationships in the data and missing values for explanatory variables makes these algorithms well suited for investigation of reproduction performance in dairy cattle. The objective of this study was to develop a user-friendly and intuitive on-farm tool to help farmers make reproduction management decisions. Several different machine learning algorithms were applied to predict the insemination outcomes of individual cows based on phenotypic and genotypic data. Data from 26 dairy farms in the Alta Genetics (Watertown, WI) Advantage Progeny Testing Program were used, representing a 10-yr period from 2000 to 2010. Health, reproduction, and production data were extracted from on-farm dairy management software, and estimated breeding values were downloaded from the US Department of Agriculture Agricultural Research Service Animal Improvement Programs Laboratory (Beltsville, MD) database. The edited data set consisted of 129,245 breeding records from primiparous Holstein cows and 195,128 breeding records from multiparous Holstein cows. Each data point in the final data set included 23 and 25 explanatory variables and 1 binary outcome for of 0.756 ± 0.005 and 0.736 ± 0.005 for primiparous and multiparous cows, respectively. The naïve Bayes algorithm, Bayesian network, and decision tree algorithms showed somewhat poorer classification performance. An information-based variable selection procedure identified herd average conception rate, incidence of ketosis, number of previous (failed) inseminations, days in milk at breeding, and mastitis as the most effective explanatory variables in predicting pregnancy outcome.

[1]  S. Rensing,et al.  Genetic evaluation of fertility traits of dairy cattle using a multiple-trait animal model. , 2008, Journal of dairy science.

[2]  J. Santos,et al.  Factors affecting conception rate after artificial insemination and pregnancy loss in lactating dairy cows. , 2004, Animal reproduction science.

[3]  K. Weigel,et al.  Management practices associated with conception rate and service rate of lactating Holstein cows in large, commercial dairy herds. , 2010, Journal of dairy science.

[4]  M P L Calus,et al.  Genetic correlations between milk production and health and fertility depending on herd environment. , 2006, Journal of dairy science.

[5]  F. O'Mara,et al.  Relationships among milk production, energy balance, plasma analytes, and reproduction in Holstein-Friesian cows. , 2007, Journal of dairy science.

[6]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[7]  J. F. Hayes,et al.  Prediction of Cow Performance with a Connectionist Model , 1995 .

[8]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[9]  Tom Fawcett,et al.  Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions , 1997, KDD.

[10]  Pedro M. Domingos,et al.  Naive Bayes models for probability estimation , 2005, ICML.

[11]  R. Veerkamp,et al.  Genetic parameters for body condition score, body weight, milk yield, and fertility estimated using random regression models. , 2003, Journal of dairy science.

[12]  Bojan Cestnik,et al.  Estimating Probabilities: A Crucial Task in Machine Learning , 1990, ECAI.

[13]  J. Morton,et al.  Effects of environmental heat on conception rates in lactating dairy cows: critical periods of exposure. , 2007, Journal of dairy science.

[14]  Daniel Zaborski,et al.  Original paper: Detection of cows with insemination problems using selected classification models , 2010 .

[15]  Kent A Weigel,et al.  Comparison of classification methods for detecting associations between SNPs and chick mortality , 2009, Genetics Selection Evolution.

[16]  Lutz Hamel,et al.  Model Assessment with ROC Curves , 2009, Encyclopedia of Data Warehousing and Mining.

[17]  A. M. Suchorski.Tremblay,et al.  Modelling horse hoof cracking with artificial neural networks , 2001 .

[18]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[19]  O. González-Recio,et al.  Genetic parameters for female fertility traits and a fertility index in Spanish dairy cattle. , 2005, Journal of dairy science.

[20]  H. Tyrrell,et al.  Prediction of the energy value of cow's milk. , 1965, Journal of dairy science.

[21]  D Gianola,et al.  Analysis of reproductive performance of lactating cows on large dairy farms using machine learning algorithms. , 2006, Journal of dairy science.

[22]  A. Roli Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[23]  Ian Witten,et al.  Data Mining , 2000 .

[25]  G. Oikonomou,et al.  Genetic relationship of body energy and blood metabolites with reproduction in holstein cows. , 2008, Journal of dairy science.

[26]  M. Lucy,et al.  Reproductive loss in high-producing dairy cattle: where will it end? , 2001, Journal of dairy science.

[27]  K. Weigel Improving the Reproductive Efficiency of Dairy Cattle through Genetic Selection , 2004 .

[28]  K. Weigel,et al.  Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat , 2011, BMC Genetics.

[29]  Krzysztof Adamczyk,et al.  PREDICTION OF BULLS’ SLAUGHTER VALUE FROM GROWTH DATA USING ARTIFICIAL NEURAL NETWORK , 2005 .

[30]  Pedro M. Domingos,et al.  On the Optimality of the Simple Bayesian Classifier under Zero-One Loss , 1997, Machine Learning.

[31]  M. McGilliard,et al.  Effect of sire fertility and timing of artificial insemination in a Presynch + Ovsynch protocol on first-service pregnancy rates. , 2006, Journal of Dairy Science.

[32]  R. Veerkamp,et al.  Energy balance of dairy cattle in relation to milk production variables and fertility. , 2000, Journal of dairy science.

[33]  Brian R. Gaines,et al.  Current Trends in Knowledge Acquisition , 1990 .

[34]  C. Risco,et al.  Effect of lameness on ovarian activity in postpartum holstein cows. , 2004, Journal of dairy science.

[35]  M P L Calus,et al.  Influence of herd environment on health and fertility and their relationship with milk production. , 2005, Journal of dairy science.

[36]  Peter Clark,et al.  The CN2 Induction Algorithm , 1989, Machine Learning.

[37]  Finn Verner Jensen,et al.  Bayesian Networks and Influence Diagrams , 1997 .

[38]  G. Williamson The explorer. , 1980, The Australasian nurses journal.

[39]  H. Dobson,et al.  Influence of uterine bacterial contamination after parturition on ovarian dominant follicle selection and follicle growth and function in cattle. , 2002, Reproduction.

[40]  C. Maltecca,et al.  Genetic analysis of fertility in the Italian Brown Swiss population using different models and trait definitions. , 2011, Journal of dairy science.

[41]  S. Brotherstone,et al.  The relationship between fertility, rump angle, and selected type information in Holstein-Friesian cows. , 2005, Journal of dairy science.

[42]  R. Lacroix,et al.  NEURAL DETECTION OF MASTITIS FROM DAIRY HERD IMPROVEMENT RECORDS , 1999 .

[43]  R. Lacroix,et al.  Methods of predicting milk yield in dairy cows-Predictive capabilities of Wood's lactation curve and artificial neural networks (ANNs) , 2006 .

[44]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[45]  Tomi Silander,et al.  Comparing Predictive Inference Methods for Discrete , 1997 .

[46]  Ahmad Kalhor,et al.  Prediction of Breeding Values for Dairy Cattle Using Artificial Neural Networks and Neuro-Fuzzy Systems , 2012, Comput. Math. Methods Medicine.

[47]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[48]  Laura Uusitalo,et al.  Advantages and challenges of Bayesian networks in environmental modelling , 2007 .

[49]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[50]  Anders L. Madsen,et al.  Bayesian networks and influence diagrams , 2007 .

[51]  R. Nebel,et al.  Effects of sex-sorting and sperm dosage on conception rates of Holstein heifers: is comparable fertility of sex-sorted and conventional semen plausible? , 2011, Journal of dairy science.