Integrated approaches for lameness control in free-stall dairy systems under heat stress and water scarcity.

Lameness remains a critical welfare and productivity issue in dairy cattle, now intensified by climate-driven stressors such as heat stress and water scarcity. While each stressor has been widely studied individually, their combined and synergistic impacts on lameness risk are insufficiently characterized. This review synthesizes current evidence on the physiological, behavioral, and environmental pathways connecting these stressors to hoof health deterioration. It further inspects advances in sensor technologies and machine learning models. These models are capable of detecting and predicting lameness, heat stress, and water scarcity within integrated, multi-stressor monitoring frameworks. A comparative analysis was conducted for algorithms, including Random Forest, Gradient Boosted Decision Trees, Support Vector Machines, and deep learning-based pose assessment. The analysis revealed notable methodological and sensor overlap, allowing cross-application of validated models between domains. Such integration offers gains in cost-efficiency, data infrastructure use, and scalability, supporting the development of adaptable early-warning systems for precision livestock farming. However, regional climatic variability and infrastructure barriers still pose obstacles to adoption. There is a need for locally adapted thresholds, farmer training, and sustainable implementation strategies. By integrating climate-resilient housing, nutritional optimization, and AI-driven monitoring, dairy systems can transition toward anticipatory, resource-efficient management. This transition enhances welfare, alleviates lameness risk, and improves robustness under escalating environmental variability.