Artificial Intelligence Applications in Small Animal Medicine: The Current Status, Key Challenges, and Future Prospects with Special Emphasis on Blockchain Innovation

Shiri, Fatemeh and Amin, Shahinzadeh and Arya, Heidari (2026) Artificial Intelligence Applications in Small Animal Medicine: The Current Status, Key Challenges, and Future Prospects with Special Emphasis on Blockchain Innovation. World’s Veterinary Journal. pp. 750-764. ISSN 2322-4568

Text WVJ16(2)750-765,2026.pdf - Published Version Download (1MB)

Abstract

Artificial intelligence (AI) and machine learning are rapidly transforming companion animal veterinary medicine. The present narrative review examined current applications, challenges, and future directions for AI in the care of dogs, cats, and other companion animals. The current study is based on a structured literature search across PubMed/MEDLINE, Scopus, and IEEE Xplore from January 2015 to April 2026, with clearly defined inclusion and exclusion criteria to ensure transparency and reproducibility. In diagnostic imaging, computer vision algorithms improve the speed and accuracy of interpreting radiographs, ultrasound, and dermatoscopic images, helping detect conditions such as hip dislocation, osteoarthritis, foreign bodies, skin lesions, and parasites. In digital pathology, AI aids in identifying abnormal cells from blood and histology slides, supporting diagnoses such as lymphoma and anemia. Wearable devices with AI algorithms continuously monitor physiological data, including activity, sleep, and early signs of pain. Natural language processing (NLP) extracts information from electronic health records to facilitate epidemiological studies. Despite this promise, several challenges remain. Technical hurdles include the need for large, high-quality annotated datasets, which are harder and more costly to obtain than in human medicine, and the high genetic diversity among dog and cat breeds, which makes it difficult to develop generalizable algorithms. Ethical and legal issues involve liability for diagnostic errors, data privacy, and algorithmic bias, requiring new regulatory frameworks. Practical barriers include high costs, integration into clinical workflows, and the need to train veterinarians to effectively use and critically evaluate AI outputs. Future progress depends on close collaboration among AI specialists, veterinarians, biologists, and industry. Priorities include developing cost-effective, user-friendly tools; creating internationally shared, standardized databases; and establishing ethical and professional guidelines. Blockchain may serve as a trust layer for recording and verifying data access events, rather than as a primary repository for large-scale medical data. Ultimately, AI is expected to act as a powerful assistant, not a replacement for veterinary expertise, enabling earlier diagnoses, personalized treatments, improved preventive care, and a better quality of life for companion animals and their owners.

Item Type:	Article
Keywords:	Artificial intelligence, Companion animal, Diagnostic imaging, Machine learning, Veterinary medicine
Subjects:	Q Science > Q Science (General) S Agriculture > SF Animal culture
Divisions:	World's Veterinary Journal (WVJ)
Page Range:	pp. 750-764
Journal or Publication Title:	World’s Veterinary Journal
Journal Index:	Scopus
Volume:	16
Number:	2
Publisher:	science-line
Identification Number:	https://doi.org/10.54203/scil.2026.wvj70
ISSN:	2322-4568
Depositing User:	Dr. Alireza Sadeghi
URI:	https://eprints.science-line.com/id/eprint/1775

Actions (login required)

View Item