Descripción

Key Features

Contents

Preface: Artificial Intelligence in Small Animal Veterinary Medicine ix
Casey Cazer

An Introduction to Artificial Intelligence and Machine Learning for Veterinary
Professionals 1023
Christopher Pinard

Artificial intelligence (AI) and machine learning (ML) are increasingly being explored and adopted in veterinary medicine. This article provides veterinary professionals with a foundational understanding of AI and ML concepts,
including the distinction among AI, ML, and deep learning; the major learning paradigms (supervised, unsupervised, and reinforcement learning); and common algorithms and architectures such as decision trees, random forests, support vector machines, and neural networks. Key terminology, model evaluation metrics, and practical considerations
for clinical implementation are discussed. Understanding these fundamental concepts will prepare veterinary professionals to evaluate, adopt, and contribute to the development of AI-based tools in their practice.

Ethical Considerations for Artificial Intelligence Tools in Small Animal Veterinary
Medicine 1039
Simon Coghlan and Thomas Quinn

As veterinary artificial intelligence (AI) tools become more available, it is vitalto ensure that they genuinely promote patient well-being and avoid harm. This article examines the ethics of AI in small animal veterinary medicine, considering both “machine” and “human” aspects. The article then outlines appropriate accountability responsibilities for veterinary practitioners, as well as for AI developers and purveyors, hospital and clinic managers, and professional veterinary bodies. Understanding these ethical
issues and accountability measures should help steer the creation, maintenance, and use of AI tools toward meeting the core veterinary medical obligation of improving animal health and welfare.

Regulation of Artificial Intelligence in Veterinary Medicine 1053
Matthew D. Winter

Artificial intelligence (AI) tools are rapidly being adopted in veterinary medicine.Unlike human medicine, where the Food and Drug Administration has established comprehensive pre-market approval pathways for AI-enabled medical devices, veterinary AI tools are marketed and deployed without regulatory oversight, independent validation, or post-market surveillance.
This article examines the current regulatory landscape for veterinary AI across the United States, European Union, and United Kingdom, and explores the roles of professional organizations in establishing standards through position statements and task forces. Liability and data privacy considerations are discussed, along with practical guidance for practitioners evaluating and adopting AI tools.

Clinical Artificial Intelligence and Machine Learning Metrics 101: How to Evaluate
Artificial Intelligence Tools for Veterinary Clinical Practices 1069

Brian Hur, Aparna Elangovan, and Laura Hardefeldt

Artificial intelligence (AI) tools are rapidly entering veterinary medicine, yet clinicians often lack frameworks to evaluate their performance. This article provides a practical guide to understanding AI evaluation metrics, including sensitivity, specificity, precision, recall, and area under the receiver operating characteristic curve, and explains why accuracy alone is insufficient. We address the critical role of interannotator agreement in establishing performance ceilings, the importance of external validation, and modality-specific evaluation considerations for AI scribes, digital imaging, and pathology applications. In the absence of regulatory oversight, veterinary professionals must develop evaluation literacy to make informed decisions about AI adoption.

Language Models in Veterinary Clinical Practice: Applications, Risks, and Practical
Guidance 1087
Nathan Bollig, Jonathan L. Lustgarten, and Elizabeth Venit

This article reviews computer systems that support veterinary clinical practice using artificial intelligence language models for language interpretation and generation, such as systems for client communication, medical records, clinical decision support, and clinical practice assessment. It provides guidance on incorporating tools based on large language models into clinical workflows to improve efficiency, clinical accuracy, and provider performance. Key inherent risks and recommendations for the responsible
use of this technology by veterinary professionals are provided.

Artificial Intelligence–Assisted Interpretation of Veterinary Radiographs:
Opportunities, Risks, and Best Practices for Clinicians 1105

Parminder S. Basran, Ryan Appleby, and Ian Porter

Artificial intelligence (AI) serves as a decision support tool, not a replacement for clinical judgment, when used to interpret radiological images. Veterinarians retain full professional accountability for all diagnoses and treatment decisions, regardless of AI involvement. Transparency is essential: if you cannot explain to clients in understandable terms how an AI system works and its limitations, it should not be used in practice. Successful implementation requires following established best practices, including
comprehensive team training, maintaining traditional diagnostic skills, and establishing quality assurance protocols.

Computer Vision and Deep Learning in Small Animal Cytology and Slide Review 1117
Candice P. Chu

Computer vision (CV) is an emerging application of artificial intelligence (AI) with growing relevance to veterinary cytology. This review provides a foundational overview of CV concepts and model architectures and summarizes current research progress in small animal cytology, including blood smear examination. The author discusses trends in scientific validation, industrial
implementation, and regulatory oversight, highlighting gaps in transparency and standardization. Educational  guidelines, and concerns regarding deskilling and workforce impact are also discussed. Together, this review aims to support informed adoption
of CV tools while emphasizing the importance of validation, professional oversight, and AI literacy in veterinary practice.
Using Evidence-Based Veterinary Medicine and Artificial Intelligence

Clinical Decision Making in Veterinary Practice 1135
Sally Everitt and Caroline Scobie

Clinical decision-making, including decisions about diagnosis and treatment options, are an important part of veterinary practice. While it is now recognised that the human brain has access to two main pathways to decision making these are subject to bias and limitations of working memory. This article will look at how the principles of evidence-based veterinary medicine and tools using artificial intelligence can be used to support clinical decision making.

Disease and Health Surveillance in Companion Animals Using Artificial Intelligence
and Machine Learning 1151
Peter-John Mäntylä Noble and Sean Oliver Farrell

Companion animal disease surveillance now benefits from collated databases of electronic health records and artificial intelligence. This review examines computational approaches for analyzing unstructured veterinary clinical text, from rule-based systems through traditional neural networks to modern transformer models. Domain-adapted encoders like PetBERT enable efficient disease coding and syndromic surveillance, while generative models offer new capabilities. Topic modeling provides unsupervised pattern discovery. Key challenges include model generalization across clinical settings, privacy protection through deidentification, standardized evaluation frameworks, and environmental sustainability. Strategic deployment of appropriately sized models can advance One Health surveillance while respecting environmental responsibility.

Disease Prediction and Precision Veterinary Medicine: Applications, Opportunities,
and Limitations of Artificial Intelligence in Small Animal Practice 1165
Audrey Ruple and Stuart W.J. Reid

Artificial intelligence and machine learning are increasingly shaping the future of small animal veterinary medicine, particularly through predictive modeling that estimates disease risk. This article introduces key concepts underlying disease prediction and precision veterinary medicine and explains how diverse data sources including electronic medical records, insurance
claims, wearable devices, and environmental datasets support predictive analytics. The article reviews common modeling approaches, emerging clinical applications, and the role of companion animals as sentinels in a One Health framework. It also examines practical limitations, potential biases, and ethical considerations, emphasizing that predictive tools should complement, not replace, clinical expertise in veterinary practice.

Author Information