Answers are grounded in this paper and cite their sources.
Reproductive efficiency is a central determinant of productivity, profitability, and sustainability in modern pig production, particularly in highly prolific maternal breeds. Increasing economic pressures, climate stress, and genetic intensification have heightened the importance of optimizing reproductive performance to maintain competitiveness. Although numerous studies have examined individual determinants of sow reproductive performance or specific predictive modeling approaches, there remains limited synthesis integrating these biological factors with recent predictive tools for litter size prediction. This review synthesizes current literature on key reproductive performance metrics, their determinants, and the predictive models used for litter size. Collectively, the evidence indicates that reproductive performance cannot be adequately assessed using a single metric but requires an integrated evaluation of genetic, physiological, environmental, and management factors. Genetic selection has improved prolificacy in maternal pig breeds, but these improvements come with trade-offs, including less consistent piglet survival and higher sensitivity to environmental stressors. A wide range of predictive modeling approaches, including classical statistical models, genomic prediction, machine learning, and biological simulation models, are critically evaluated. The review demonstrates that while conventional statistical models remain valuable because of their interpretability, genomic and machine learning approaches provide improved predictive performance for complex reproductive traits, although challenges related to data integration, model generalizability, and biological interpretability remain. By integrating biological determinants with predictive modeling approaches within a single framework, this review provides a comprehensive perspective that supports precision breeding, evidence-based reproductive management, and improved decision-making in commercial pig production. Future research should focus on integrating multi-omics data, precision livestock technologies, climate-resilient modeling approaches, and explainable artificial intelligence to improve predictive accuracy and practical implementation.
No takes yet. Share an insight, caveat, or question.
Ntshehi et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: