The biology graph
Much of biology remains unexplained. What medicine understands in one species often leaves unanswered questions in another. Veterinarians work across those gaps every day, treating animals whose diseases and responses to treatment can differ profoundly.
Those differences also give medicine something to learn from. Comparing species helps researchers investigate why disease develops, why a treatment works, and why one animal can recover in ways another cannot.
OpenVet is a comparative medicine AI company building a medical intelligence around that opportunity. We begin where care happens, connecting veterinary knowledge with the history of the patient and what happens after treatment. Over time, we are building toward a system that learns from those connections and helps advance medicine across the animal kingdom.
The asymmetry
Veterinary medicine spans an extraordinary range of biology. Yet the evidence available for a clinical question varies by species, and a finding in one animal does not answer every question about another.
Clinical practice adds another kind of knowledge. A veterinarian considers the patient’s history, interprets the findings, weighs treatment options, and works with the owner to decide what care is possible. The outcome only makes sense when those circumstances remain connected.
We are building a system that preserves that medical reasoning alongside the record of care. This gives comparative medicine more to work with than an isolated diagnosis or a final result. It connects what was known, what was decided, and what happened next.
| Stage of care | What happened | What gives it meaning |
|---|---|---|
| Patient | The diagnosis | Species, history, and findings |
| Decision | The chosen plan | Clinical reasoning and alternatives |
| Treatment | The recommendation | Care that was carried out |
| Outcome | The result | Follow-up and changes at home |
| Comparison | A shared pattern | Similarities, differences, and unanswered questions |
The four anchors
The intelligence we are building depends on understanding care as it unfolds. OpenVet supports the veterinarian in the clinic; OpenAnimal connects with the owner who sees the animal between appointments. Bringing those perspectives together creates a fuller medical history.
Clinical reasoning
Veterinary evidence considered alongside the patient’s history, findings, and treatment options.
Patient history
A medical record that follows the animal over time, connecting decisions with treatment and recovery.
Veterinary expertise
The experience and judgment of clinicians shaping how the system understands and supports care.
Care at home
The owner’s observations and experience carrying out the care plan, connected with the animal’s medical history.
These are the foundations of a system designed to improve through experience. Learning requires understanding how an outcome came about, including the complications, constraints, and unanswered questions.
What medicine can learn across species
Published research already shows why this matters.
Cancer
Researchers studying osteosarcoma in pet dogs identified three patterns in the environment surrounding the tumors. A machine-learning model developed from the canine data found corresponding patterns in human osteosarcoma datasets, with relevance to disease progression. Studying a naturally occurring cancer in dogs helped researchers understand features of the human disease.
Comparative osteosarcoma study
Diabetes
SGLT2 inhibitors act on glucose handling in the kidneys. The drug class is used in human type 2 diabetes and in selected cats with diabetes. A shared biological mechanism has applications across species, while patient selection, monitoring, and treatment risks remain species specific. Feline treatment requires particular attention to the risk of ketoacidosis.
Regeneration
Spiny mice can regenerate tissues that typically heal with scarring in other mammals. Researchers comparing their healing process with laboratory mice found that sustained ERK signaling helps explain the difference. Studying how one mammal regenerates gives researchers a mechanism to investigate in others.
These findings come from independent research. They illustrate the scientific work we want OpenVet to support: recognizing connections across species, understanding their limits, and identifying questions worth testing.
Why now
AI gives us new ways to work with complex medical information. Connecting those capabilities with clinical practice creates an opportunity to study disease through the course of an animal’s life, including the decisions and follow-up that isolated records leave out.
We are building toward a self-learning medical intelligence that becomes stronger as validated knowledge and clinical experience inform it. Reliable records, appropriate permissions, and scientific evaluation are part of that system’s foundations.
Our goal is to put more of medicine’s knowledge into the hands of veterinarians today and help expand that knowledge over time. The measure of success is what this work makes possible for animals: better treatment, less suffering, and more years of healthy life.