Artificial Intelligence

AI: An Emerging Frontier for Veterinary Medicine

Since 2020, faculty have led a diverse and growing portfolio of artificial intelligence AI/ML research. These publications demonstrate applied, translational AI across clinical medicine, epidemiology, microbiome science, imaging, pharmacology, informatics, and educational research.

Several defining characteristics span this body of work:

  • Strong clinical orientation – AI tools for diagnostics, imaging interpretation, disease classification, and EHR-integrated decision support.
  • Population and One Health modeling – ML applied to disease surveillance, forecasting, and antimicrobial resistance.
  • Production and agricultural systems AI – Machine learning for microbiome analysis, dairy systems, and predictive livestock health.
  • Advanced computational methods – Deep learning, neural networks, radiomics, and spatio-temporal modeling.
  • Infrastructure and evaluation work – Platforms, benchmarking, reproducibility studies, and AI literacy assessment.

Importantly, these publications reflect not just participation in AI research, but intellectual leadership, with SVM faculty serving as first or senior authors in clinically relevant, domain-driven AI innovation.

AI Research Areas

Clinical AI, Diagnostics, and EHR Integration

SVM faculty have applied machine learning and artificial intelligence to improve clinical diagnostics, decision support, and health record integration. This includes both algorithm development and evaluation of AI tools in real-world veterinary settings.

Key Contributions

  • Development and validation of ML-based diagnostic classifiers
  • AI-assisted pathology quantification
  • Clinical decision support for internal medicine
  • Real-time ML integration into veterinary EHRs
  • Evaluation of LLMs for clinical information extraction

Publications & SVM Authors

Epidemiology, One Health, and Disease Forecasting

SVM researchers have applied machine learning to population-level disease modeling, spatio-temporal forecasting, and antimicrobial resistance analysis.

Key Contributions

  • Spatio-temporal epidemic forecasting
  • AI-driven surveillance of infectious diseases
  • Environmental and agricultural pathogen prediction
  • Modeling disease dynamics across animal populations

Publications & SVM Authors

Microbiome, Production Medicine, and Agricultural Systems

AI methods have been applied to high-dimensional microbiome data, dairy systems analytics, and livestock health prediction.

Key Contributions

  • Feature engineering and ensemble ML for microbiome analysis
  • Predictive modeling in dairy production systems
  • Integration of ML and statistical inference for agricultural data

Publications & SVM Authors

Imaging, Radiomics, and Deep Learning

SVM faculty have led the application of deep learning, radiomics, and neural networks to imaging and complex biomedical datasets.

Key Contributions

  • Deep learning (CNNs, neural networks) in imaging
  • Radiomics modeling
  • Advanced segmentation and pattern recognition
  • Application of AI in radiation oncology

Publications & SVM Authors

Pharmacokinetics, Drug Modeling, and Regulatory AI

AI has been applied to drug residue detection, pharmacokinetics, and modeling relevant to regulatory science.

Key Contributions

  • Machine learning for drug residue detection
  • AI-informed pharmacokinetic modeling
  • Data mining for regulatory applications

Publications & SVM Authors

Infrastructure, Methodology, and AI Evaluation

Several publications address AI methodology, implementation challenges, reproducibility, and workforce readiness.

Key Contributions

  • Practical challenges in ML implementation
  • AI tool evaluation and benchmarking
  • AI literacy and adoption assessment
  • Editorial leadership in AI-enabled life sciences

Publications & SVM Authors

 

Opportunities Ahead

SVM is positioned to expand AI impact through:

  • Scaling EHR-to-AI ecosystems for real-time clinical decision support
    Building on existing EHR integration platforms to enable predictive triage, diagnostic assistance, and longitudinal outcome modeling within VMTH and partner hospitals.
  • Standardizing digital pathology datasets for cross-site research
    Developing shared, annotated pathology and imaging repositories to support multi-institutional AI model training and validation.
  • Expanding sensor + microbiome prediction challenges for dairy systems
    Leveraging production-scale data streams (sensor data, microbiome profiles, health outcomes) to create predictive modeling benchmarks and translational dairy AI applications.
  • Building deployable AI surveillance tools for state, federal, and global One Health partners
    Translating epidemiologic and forecasting models into operational decision-support systems for animal health agencies and global health collaborators.
  • Formalizing training pathways (AI micro-credentials, short courses, resident training)
    Establishing structured educational programs that build AI literacy and applied competency among DVM students, residents, and faculty clinicians.