Skip to content

Veterinarian · AI builder

Brian Hur

Brian Hur

§ 01 · Microsoft

§ 02 · Vet school

§ 03 · VetPronto

§ 04 · Love That Pet

§ 05 · PhD

§ 06 · Now

I'm a veterinarian and an NLP researcher who also builds software, so I've usually seen both the clinical side and the data side of whatever isn't working. The AI projects I like most are the ones that change what clinicians can do.

The consulting side of that work goes through my firm, Datatroph, with a bench of people I've worked with before: fractional Chief AI Officer roles, technical due diligence on AI companies, and research projects where the results have to hold up in review. I also take board advisory roles in my own name. If any of that sounds useful, or you'd rather just talk, email me.

Email Google Scholar LinkedIn GitHub

§ · What I'm working on

What I'm working on

AI Mode at VIN

A clinical assistant that uses decades of VIN's clinical knowledge and cites the source of every answer. I built the first version, an engineering team runs it now, and practicing vets use it every day through VIN, which reaches more than half the vets in the US. Knowing when it is wrong is harder than building it.

Dogs and genomes

With the canine genetics group at NC State, applying NLP and machine learning to paired clinical and genomic data. It is early work.

The evaluation gap

Clinical AI is being scored against a ground truth that’s less solid than it looks, and I coauthored a paper on why that is and what to do instead (arXiv, 2026).

Read the paper →

Tendrel

A research graph for Claude Code that keeps track of what’s been tried and what held up. I wrote it for my own work and it is public in case it is useful.

On GitHub →

§ · Research

Selected papers

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

Veterinary Clinics of North America: Small Animal Practice 56(5), 2026

Invited article in the special issue on artificial intelligence in small animal veterinary medicine.

A practical guide for veterinarians: what sensitivity, specificity, precision, recall and AUC actually tell you, why accuracy alone misleads, why expert disagreement sets a ceiling on any AI's measured performance, and the four questions to ask before adopting a tool.

Published version (Elsevier) · Accepted manuscript (PDF, free)

The free PDF is the authors' accepted manuscript, shared under CC BY-NC-ND 4.0. Please cite the published version.

All publications →