article · Discover Applied Sciences
Artificial intelligence and machine learning applications in veterinary and biomedical sciences have expanded considerably, shifting from early diagnostic support to advanced operational uses. A bibliometric review of 1,641 publications from 1994 to 2025 shows an annual growth rate of 8.83 per cent, characterised by minimal activity before 2017 followed by rapid acceleration peaking in 2025. Research focus has evolved over time from traditional machine learning methods toward deep learning, computer vision, and Internet of Things technologies applied to precision livestock farming. Contemporary studies also increasingly address broader issues such as animal welfare, climate change, and food safety. However, global contributions remain uneven, with research outputs and collaborative networks dominated by high-income countries, particularly China, the United States, and European nations, highlighting a persistent geographic divide in veterinary technological research.
Understanding the progression of artificial intelligence in veterinary medicine helps clarify how digital technologies support food safety, animal welfare, and disease diagnosis. The concentration of this research within high-income nations indicates that developing agricultural sectors may face barriers accessing precision livestock solutions, pointing to an urgent need for wider global research partnerships to improve livestock productivity and food security.
The abstract does not indicate a direct commercialisation pathway, as it reports a bibliometric overview rather than a technical prototype or trial. It nevertheless highlights growing technological interest in precision livestock farming, deep learning, computer vision, and Internet of Things tools designed to assist veterinary clinicians, livestock managers, and agricultural producers with disease diagnosis and herd management.
AI-generated from the published abstract. Always read the original work before citing.
Artificial intelligence (AI) and machine learning (ML) are increasingly transforming veterinary medicine and biomedical science through improved disease diagnosis, therapeutics, livestock management, and supporting decision-making. However, the rapid expansion of this field has not been systematically synthesized to clarify its growth, patterns, thematic evolution, adoption, and global research disparities. A bibliometric analysis was conducted using publications indexed in the Scopus database. A total of 1,641 documents (1,472 articles and 169 reviews) published between 1994 and 2025 in 594 journals were retrieved and analyzed. Bibliometric indicators, including publication trends, citation performance, core journals, author productivity, keyword co-occurrence, thematic structures, and international collaboration networks were examined using established bibliometric methods, including the Bradford’s Law and thematic mapping techniques. Our findings indicate that the field exhibited an annual growth rate of 8.83%, with two distinct phases: a prolonged low-activity period (1994–2016) and a rapid expansion from 2017 onward, reaching a peak in 2025. Core journals such as Computers and Electronics in Agriculture , Animals , and the Journal of Dairy Science accounted for a substantial share of publications. Thematic evolution revealed a shift from traditional machine learning approaches to deep learning, computer vision, IoT-enabled precision livestock farming & veterinary medicine, and applications addressing animal welfare, food safety, and climate change. Research output and collaboration were dominated by high-income countries, particularly the United States, China, and Europe. AI and ML research in veterinary medicine is rapidly maturing and diversifying, yet significant geographic and institutional inequalities persist, underscoring the need for more inclusive global research collaborations to enhance livestock productivity and food security.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s42452-026-09228-2
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
