Asian Journal of Research in Zoology

Gastrointestinal helminths remain a persistent constraint to cattle health and productivity in Nigeria, shaped by diverse agro-ecological zones, seasonal grazing dynamics, and variable access to diagnostics and veterinary services. Conventional surveillance methods, while essential, are often limited by cost, labor, and delayed feedback, reducing their utility for proactive control and rational anthelmintic use. Machine learning (ML) and artificial intelligence (AI) offer practical opportunities to shift helminth management from reactive treatment to prediction-oriented decision support. This review synthesizes advances in AI-enabled prediction of gastrointestinal helminths in cattle, emphasizing how Nigerian production realities influence data availability, model design, and deployment. We examine the Nigerian epidemiological context, core predictors at animal, herd, and environment levels, and the evolving landscape of diagnostic data streams, including copromicroscopy workflows, digital egg counting, and molecular identification. We further discuss model development choices relevant to helminth prediction, including label quality, class imbalance, temporal validation, external generalizability, and explainability. Finally, we propose implementation pathways suitable for Nigeria, including mobile-enabled risk scoring, low-resource image-based diagnostics, climate-informed forecasting, and integration with targeted selective treatment strategies to slow anthelmintic resistance. The review concludes by outlining research and capacity priorities required to move from proof-of-concept modeling toward scalable, trustworthy, and field-ready helminth prediction systems.