Why Analysis Health Exists.
Health data is only as valuable as what gets done with it.
Facts about lab testing.
13.3 billion clinical lab tests are run in the US every year, and roughly 75% of clinical decisions depend on what those tests show.¹ The volume keeps growing — direct-to-consumer genetic testing has more than doubled in the last five years,² and comprehensive panels are now within reach for anyone willing to pay.
What hasn’t kept pace is interpretation:
Patients can’t read what they get. A study of patients with lower numeracy found only 38% could correctly identify whether a lab result was inside or outside the normal range.³
Doctors don’t have time. Primary care physicians would need 26.7 hours a day to deliver every recommended check on a typical patient panel.⁴
The system doesn’t follow up. Up to 62% of abnormal lab results lack timely follow-up, depending on test type.⁵
The gap isn’t in the data — it’s in the work that turns the data you already have into an actionable plan.
Analysis Health exists to close that gap. More data isn’t the answer. More interpretation is.
Our Founders’ Story.
We’re Alaina and Mike, a married couple who each ran businesses of our own before starting Analysis Health. Mike is a data engineer; he heads the technical architecture behind every analysis. Alaina shapes the brand and customer experience — how the product reads, what people understand, where our message meets them.
What we saw was specific. The cost of running 100+ markers has dropped from thousands to hundreds in a decade. New companies — Function Health, Superpower, Life Force and more — have all made comprehensive panels accessible. People are finally able to run these tests in volume. But what hasn’t yet expanded is the work that comes after: turning long lab reports into a plan that names what to do first.
We knew the gap up close. For years we’d been ordering our own panels and ending each round with more numbers and not much more clarity. Alaina became our first client. While her health struggles weren’t a complete mystery, her analysis explained them more clearly than anything before — and the changes she’d been trying to make finally stuck.
But we didn’t just build Analysis Health because we couldn’t find an answer for ourselves. We built it because we could see exactly where the gap was, knew the work to close it, and had the technical and business chops to do it.
What we built is the tool we wanted. An interpretation that takes the data already in hand and produces a plan, in hours. Not another panel. Not another subscription. But the missing layer that turns data into action.
What We Believe.
Our company beliefs shows up in our work — what gets included, what gets cut, what our products are willing to claim.
Five ethos shape Analysis Health.
Each one is load-bearing. Each one changes what our customers experience.
Health data should be usable.
A panel that no one can act on is a panel with less value. Numbers exist to help make decisions
AI is part of our methodology, not our headline.
It’s the craft behind each analysis, not the product itself. Customers come for personalized interpretation; the technology that delivers it stays in the background.
More data doesn’t replace interpretation, and good interpretation reads markers in relationship rather than in isolation.
A single value out of range is a poor witness. The same value sitting inside a pattern across markers, against the customer’s symptoms and history, says something different.
Analysis Health works alongside medical care, never as a substitute.
Our job is to bring organized data to the user’s conversations with their doctor — with named patterns, prioritized concerns, and the right questions to raise.
Health science and technology both evolve.
Our products evolve with them. What’s certain today gets revisited as the field changes; iteration is built into the design, not retrofitted.
How we use technology.
AI is the backbone of how Analysis Health interprets data. The work we do — reading patterns across many markers, comparing how different analytical frames score the same evidence, ranking what matters most for next steps — is the kind of pattern-recognition AI does at scale.
For us, AI is what makes our products possible. We use it to run analyses at a depth and speed no small team could match. We use it to maintain consistency across every report — the same architecture, every time. And we use it to iterate on our approach as the science changes, without rebuilding the whole system from scratch.
How we shape AI is what makes our analysis specifically ours: our frameworks define its depth, what gets weighted, what gets flagged with less certainty, and what gets delivered. The interpretation is AI’s. The structure is ours.
Our Role Alongside Care.
Analysis Health was built to work alongside medical care.
Our position is intentional — we’ve thought about it carefully and couldn’t build the product any other way.
A doctor’s role is irreplaceable. Clinical examination, diagnosis, prescription of treatment, and the ongoing relationship of a care provider are the work of medicine. None of that is what we do.
What we do sits in a different layer. People are now accumulating lab data faster than a short clinical visit can engage with thoughtfully. The cost of testing has come down; the time available to interpret each test hasn’t expanded with it. A real gap has opened between data and conversations had about it.
Analysis Health works directly in that gap. We turn data into something organized — what’s connected to what, what to address first, what’s worth raising in your next visit. You end up with data you can act on, in your own time, on your own terms.
What real users are saying.
“AI is the backbone of how Analysis Health interprets data. The work — reading patterns across many markers, comparing how different analytical frames score the same evidence, ranking what matters most for next steps — is the kind of pattern-recognition AI does at scale.”
- C. Byrant
“For us, AI is what makes our products possible. We use it to run analyses at a depth and speed no small team could match. We use it to maintain consistency across every report — the same architecture, every time. And we use it to iterate on our approach as the science changes, without rebuilding the whole system from scratch.”
- A. Gurwitz
“How we shape AI is what makes our analysis specifically ours: our frameworks define its depth, what gets weighted, what gets flagged with less certainty, and what gets delivered. The interpretation is AI’s. The structure is ours.”
- P. Rosa