Background Accurate prediction of breeding values (BVs) is fundamental to genetic improvement in racehorses. Although single-trait mixed models (STM), typically implemented using BLUP-based procedures, remain the standard framework for genetic evaluation, machine learning (ML) methods offer a flexible, data-driven approach for learning complex relationships among phenotypic, environmental, and pedigree-derived information. These capabilities have encouraged researchers to explore the application of ML methods for predicting breeding values. Objectives This study compared the performance of 13 ML algorithms for predicting estimated breeding values (EBVs) of Race Completion Time (RCT), Rank at the End of Competition (REC), and Average Speed (AS) in Iranian crossbred racehorses. Methods A total of 55,070 race records from 5,296 horses were analyzed. Reference EBVs were estimated using single-trait mixed models (STM) fitted by maximum likelihood in Wombat. Thirteen ML algorithms, including linear regression models, tree-based ensembles, boosting methods, and artificial neural networks (ANNs), were trained using 75% of the data and evaluated on the remaining 25%. Predictive performance was assessed using accuracy, correlation, mean absolute error (MAE), mean squared error (MSE), bias, and dispersion. Results All ML models outperformed the conventional STM across the three traits. ANN consistently achieved the highest predictive performance, with accuracies of 0.63, 0.72, and 0.56 and correlations of 75%, 86%, and 71% for RCT, REC, and AS, respectively. XGBoost, LightGBM, Gradient Boosting and Random Forest also showed strong predictive ability, whereas linear models and distance-based methods exhibited comparatively lower performance. Prediction bias remained close to zero, and dispersion coefficients were generally close to unity across ML models. Conclusions Machine learning, particularly ANN and boosting-based algorithms, substantially improved EBV prediction compared with the conventional STM. These findings demonstrate the potential of ML as a complementary tool for accelerating routine genetic evaluation and supporting more reliable selection decisions in horse breeding programs.
Background Left ventricular (LV) volume assessment evaluates cardiac size and remodelling in horses. Single-plane Simpson method of discs (SMOD) provides volumetric measurements requiring body size normalization. Aims/objectives We described LV volumes using SMOD in healthy Brazilian Sport Horses (BH) and evaluated thoracic-girth–estimated body weight (BWe) versus scale-measured weight (BWs) for indexing. Methods Thirty BH horses (15 males, 15 females; 4–16 years) underwent echocardiography. LV end-diastolic (LVEDV), end-systolic volumes (LVESV), and ejection fraction (EF%) were obtained using SMOD. Body weight was scale-measured and estimated via thoracic girth formula. Volumes were indexed to BWs, BWe, and a 500- kg reference. Results Mean LVEDV was 1060 ± 154 mL (95% CI: 1003–1118), LVESV 318 ± 77 mL (95% CI: 290–347), and EF 70.0 ± 5.4%. Overall, BWe was associated with BWs (R² = 0.61; P < 0.0001) with mean bias of +33.25 kg (limits of agreement:37.59 to +104.09 kg), mean absolute error of 39 ± 28.83 kg, and percentage error of 8.92 ± 7.27%. LVEDV/BWs averaged 2.30 ± 0.29 mL/kg and LVEDV/BWe 2.15 ± 0.26 mL/kg. Normalization to 500 kg yielded LVEDV[500] of 1151 ± 146 and 1069 ± 131 mL, and LVESV[500] of 346 ± 83 and 321 ± 70 mL (BWs; BWe). Indexed variables showed moderate to strong linear association between methods. In this sample, no sex or age differences were detected. Conclusion Body weight normalization improved interindividual comparability. While BWe offers a practical field alternative, estimation errors warrant caution in individual evaluations, making BWs preferred.
