Supervised Machine Learning Techniques for Breeding Value Prediction in Horses: An Example Using Gait Visual Scores

Simple Summary In the artificial intelligence era, much is speculated about the use of machine learning techniques for the most diverse scientific purposes. Machine learning methods are acknowledged to better handle non-linearity and subjectivity than traditional statistical methods. In the horse industry, visual scores are widely used to evaluate gaited horses. This phenotyping strategy is an effective low-cost alternative to more accurate methods. However, since it heavily depends on the person assessing the gait, subjectivity is introduced in the phenotype. Our study evaluated the application of machine learning techniques in the breeding value prediction for visual scores in Brazilian gaited horses. We used a dataset with horses that were measured for at least one of the following gait scores: dissociation, comfort, style, regularity, and development. Traditional methods, such as ordinary least-squares and multiple-trait models, were combined with artificial neural networks and other machine learning regression methods, and each model was evaluated according to its accuracy, bias, and dispersion. Machine learning techniques had accuracy comparable to traditional methods; however, they presented slightly more bias and were over-dispersed. For selection purposes, more studies are needed; however, machine learning techniques are a feasible alternative for unofficial evaluation runs.Abstract Gait scores are widely used in the genetic evaluation of horses. However, the nature of such measurement may limit genetic progress since there is subjectivity in phenotypic information. This study aimed to assess the application of machine learning techniques in the prediction of breeding values for five visual gait scores in Campolina horses: dissociation, comfort, style, regularity, and development. The dataset contained over 5000 phenotypic records with 107,951 horses (14 generations) in the pedigree. A fixed model was used to estimate least-square solutions for fixed effects and adjusted phenotypes. Variance components and breeding values (EBV) were obtained via a multiple-trait model (MTM). Adjusted phenotypes and fixed effects solutions were used to train machine learning models (using the EBV from MTM as target variable): artificial neural network (ANN), random forest regression (RFR) and support vector regression (SVR). To validate the models, the linear regression method was used. Accuracy was comparable across all models (but it was slightly higher for ANN). The highest bias was observed for ANN, followed by MTM. Dispersion varied according to the trait; it was higher for ANN and the lowest for MTM. Machine learning is a feasible alternative to EBV prediction; however, this method will be slightly biased and over-dispersed for young animals.