Creole goats have adapted to the harsh Andean environment, yet the physiological impacts of high-altitude production systems remain underexplored. This study assessed seasonal and dietary influences on the hematological and biochemical profiles of 45 Creole goats in the Peruvian Andes. The animals were assigned to three diets: D1 (grazing), D2 (grazing + 2000 g hay), and D3 (grazing + 400 g concentrate), across rainy and dry seasons. Biweekly blood sampling measured urea, cholesterol, total protein, albumin, ALP, ALT, WBCL, NeuP, LymP, HGB, and MCV. Season exerted the strongest influence (p < 0.001), with modest dietary effects and a consistent effect of sampling time. Urea, total protein, and albumin increased during the rainy season, though only urea responded significantly to diet. Leukocytosis rose in the dry season and with higher-protein diets, suggesting heightened immune activation under environmental stress. Hemoglobin peaked in the rainy season and early sampling, indicating better oxygenation. MCV and body weight were higher in the dry season, with weight unaffected by diet. These results underscore the complex interplay of environmental and nutritional factors in shaping goat physiology at high altitudes, emphasizing the importance of dynamic modeling in sustainable Andean livestock systems.

Endoparasitosis is a critical health challenge in the management of Creole goats under extensive production systems due to its negative impact on animal health and productivity. This study determined the occurrence of endoparasites and identified associated risk factors in Creole goats from the southern coast of Peru. Fecal samples were collected from 129 goats in two localities of the Pisco province to detect the presence of oocysts from Eimeria spp. and eggs from trichostrongyles, Skrjabinema spp., Trichuris spp., and Fasciola hepatica. Data were analyzed using logistic regression models and adjusted through bootstrapping and stepwise selection methods, with locality, feeding type, age, and body condition as predictive variables. The results revealed a high occurrence of Eimeria spp. (86.0%) and trichostrongyles (65.1%), while Fasciola hepatica (14.0%) and Skrjabinema spp. (7.0%) were exclusively identified in Independencia and San Clemente, respectively. Mixed infestations were predominant (65.9%), occurring more frequently in Independencia (75.9%) than in San Clemente (57.7%) (OR: 2.26, p < 0.05). The likelihood of infestation was significantly higher in Independencia for Eimeria spp. (OR: 5.72, p < 0.01) and Fasciola hepatica (OR: 61.4, p < 0.01). Moreover, goats fed exclusively on alfalfa were more likely to be infested with Fasciola hepatica compared to those fed a mixed diet of alfalfa and crop residues (OR: 0.06, p < 0.05). These findings underscore the necessity of implementing comprehensive health programs tailored to local management and feeding conditions.

Accurate prediction of pregnancy following fixed-time artificial insemination (FTAI) remains challenging under commercial goat production conditions. This study compared multivariable logistic regression and Random Forest models for pregnancy prediction and used SHAP analysis to characterize predictor contributions. Data from 920 goats subjected to FTAI across four regions of Peru were analyzed using reproductive, hormonal, animal-level, and management variables. Logistic regression was developed after univariable screening, whereas Random Forest models used 500 trees with mtry values of 2, 3, and 4. Models were compared using stratified 10-fold cross-validation with identical folds. The mtry = 4 configuration yielded the highest Random Forest AUC. Logistic regression identified semen type, buck and doe breed, insemination site, and cervical mucus score as independent predictors. Chilled semen was associated with higher pregnancy odds, whereas superficial cervical insemination was associated with lower odds. Logistic regression outperformed Random Forest in discrimination (AUC, 0.761 vs. 0.654), accuracy (0.679 vs. 0.644), and specificity (0.882 vs. 0.782), whereas Random Forest showed higher sensitivity (0.369 vs. 0.278). SHAP analysis identified eCG dose, cervical mucus score, semen type, and insemination site as the most influential predictors. Overall, logistic regression provided superior and more consistent predictive performance, whereas Random Forest offered complementary sensitivity and captured nonlinear predictor contributions. These findings support logistic regression as the more effective predictive approach for pregnancy following FTAI under the conditions studied, with explainable machine learning providing complementary insight into prediction patterns.