Radattest.
For radiologists For hospitals Quality Implementation Contact
Quality

We don't grade the report.
We finish it — accurately,
and efficiently.

Extra quality with improved radiologist efficiency — not one traded for the other. Quality assurance happens before the error rather than after it, automatically, on every report. Nothing is asked of you unless something is actually detected, and when it is, resolving it is usually one click. Most of the time you will never see it work at all. It is not a chore, and it costs the radiologist nothing.

Exception flag detail: a CT head study flagged for late-arriving images, with a timestamped evidence trail of when images arrived and when the study was first opened.
Live product A flag says this number needs a footnote — raw and adjusted are both always computed, and the evidence travels with the number, timestamp by timestamp. Synthetic patient data.
Before the error

Before the error, not after it

The mental model everyone brings to the word “QA” is retrospective. Ours isn't.

Retrospective peer review

  • Finds the error after the report left the building
  • A sample. Most reports are never looked at
  • Produces a discrepancy: a date, a signer, a patient
  • Costs the radiologist time and standing

What we do

  • Catches it while it is still free to fix
  • Every report, every time
  • Produces a non-event: the report was simply correct
  • Costs the radiologist nothing and no clicks
The hardest question

Answered directly

If it shows the last three impressions, it can show that somebody missed something.

Nothing previously noted gets missed again — by anyone, in either direction. The ledger counts saves, not blame: it records that a discrepancy was resolved, never who authored the earlier report.

The single strongest sentence we have on this

The prior report is in the chart either way. The only question is whether a radiologist sees it before signing — or an attorney sees it after.

Read the argument
Watch it catch one

The prior said tear. The draft says normal.

A real one, on synthetic data: the prior MRI carried a lateral meniscal tear; today's draft dictated the medial side and left the lateral field on its template default. At signing:

Continuity check modal comparing against the prior MRI impression: CONTRADICTED? Prior described peripheral tear of the posterior horn of the lateral meniscus — your draft says the lateral meniscus is normal without tear. Resolved, or missed? — with dismiss, ignore, return-to-report and sign-anyway actions.
Live product Reconciled against the right prior — same modality first — and side-aware: a medial tear does not satisfy a lateral one. It even catches the contradiction coming from an untouched template default. Nothing blocks signing; every row is dismissible. Synthetic patient data.
Governed the same way

Who sees what, and who holds the switch

Configurability, applied a second time.

You are always the first person to see your own numbers. Every metric is configurable — what's measured, what's shown, and to whom — and the switch is in the group's hands. Not the hospital's, and not ours. Your group's performance data has always existed. You've just never been given a copy.

The inventory

Every check, on one screen.

Short on purpose. Sorted by who it's for.

For the radiologist protection that costs no time
Did you answer what was asked?Indication checked against expected coverage.
One click adds the negativeA pertinent negative, straight off a flag.
Eight checks, zero clicksThey run before you sign.
Laterality and contradictionsCaught before signature.
Urgent findings escalate themselves
Guideline follow-up, written for youFleischner, TI-RADS — verified against published guidance.
Invisible until it isn'tRuns on every report; asks you for something only when something is actually detected.
Stop double-checking yourselfThe promise all of this adds up to.
For the facility quality you can show, not assert
An audit trail on every reportBy default, not retrofitted.
Peer review, readyThe OPPE packet — not retrofitted.
Turnaround vs real difficultyNot just the clock.
MIPS, evaluated liveMet and unmet against the report text; one click inserts what's missing.
Critical results, suggestedA critical finding in the impression is offered for communication automatically.
Critical results, timedAnd evidenced.
The reader can flag a numberOutage, late images, an interruption — evidence attached. It annotates, never deletes.
Leading-edge securityVerified with your facility.
For the patient the loop that usually breaks
Follow-up doesn't get lostThe follow-up registry.
Closes itself on evidenceAuto-close when the study arrives.
Hand the list to whoever chases itNavigator export.
Findings tracked across timeLesion and thyroid nodule tracking.

See it on your own cases.

Configured per radiologist. Verified by your IT.

Talk to us For radiologists For hospitals
Ask for it

Want it to work some other way?

Configurability is the whole design, and it does not stop at the settings that happen to exist today. If your group or your facility wants a behaviour changed, a metric defined differently, a template shaped another way or something added outright — ask. It is very often possible, and you will be talking to the radiologist who builds it rather than to a roadmap.

Ask for a change