Antevion
Request a leakage audit

Imaging follow-up

Antevion

In development · onboarding its first partner hospitals

Antevion is designed to read each signed imaging report, quote the follow-up recommendation the clinician wrote, and hand it to the department the hospital has configured as responsible, with a named person and a due date. It never writes for the clinician, and a person confirms every closure.

The gap

What it addresses

A recommendation in a report is not a task in anyone's queue.

Hospitals don't lack detection. They lack anyone who holds the state “recommended but not yet done”. The report goes to the doctor who ordered the scan, often for an unrelated reason, and nobody can count what is outstanding.

The loss concentrates between departments: a nodule on an emergency CT pulmonary angiogram, or on an abdominal CT, that belongs to pulmonology. None of this is anyone's fault. It's structural.

Workflow

How it is designed to work

  1. Reads and quotes

    It reads each signed report of the scan types in scope and records the follow-up recommendation, quoting the clinician's own sentence.

  2. Hands it to the owning department

    It hands the recommendation to the department the hospital has configured as responsible, with a named person and a due date taken from the interval the clinician stated.

  3. Asks the author

    When the interval or the action is missing, it asks the report's author to complete the recommendation. It never fills it in.

  4. Proposes; a person confirms

    It proposes the later exam or appointment that may fulfil the recommendation, for a member of staff to confirm; a near-miss is rejected and nothing closes.

  5. Accepts follow-up done elsewhere

    It lets the patient tell the hospital that the follow-up was done at another provider, and staff verify it before anything changes.

  6. Counts, and states its coverage

    It reports, by department pair, how many recommendations were completed, completed elsewhere, closed as not indicated, overdue or never actioned, and always states its coverage.

Example

One follow-up, from the report to confirmation

Illustrative example

Quoted sentence

Nódulo pulmonar no lobo inferior direito. Sugere-se TC de tórax de controlo dentro de 6 meses.

Quoted from the signed report, as written. Translation: “Pulmonary nodule in the right lower lobe. A control chest CT within 6 months is suggested.”

What is recorded

Owning department
Pulmonology
Owner
Pulmonology coordinator
Due
04/09
Report signed 04/03, plus the 6 months the clinician wrote
Proposed later exam
Chest CT

State Confirmed by a person

Illustrative example with fictitious data. It does not represent a real patient, clinician or hospital. The sentence, department and dates are fictional. The due date comes from the interval the clinician wrote; Antevion never sets an interval.

Differentiators

What makes it different

  • The hospital's own number, before anything changes

    A retrospective audit of 12 months of reports, before any workflow changes.

  • It asks the radiologist; it never writes for them

    Incomplete recommendations go back to their author. Nothing is pre-filled or suggested.

  • Closure that crosses providers

    In Portugal, follow-up often happens outside the hospital that recommended it. Antevion is designed to accept follow-up done at another provider, verified by staff, instead of counting it as never done.

Where it starts

The leakage audit

Antevion starts with a retrospective audit of 12 months of signed chest-CT-family reports: CT pulmonary angiography, emergency and abdominal CT with lung bases, chest CT and cardiac CT. Later exams and specialty appointments are included where the hospital can export them.

What the hospital will receive

  • For each recommended follow-up, whether a matching later exam or appointment was found in the hospital's records (unverified) or no follow-up was found, by ordering → owning department. Follow-up done at another provider is usually not observable in an audit, and the report says so.
  • How often in-scope findings were reported with no follow-up statement — counted, and never queried.
  • Transcription accuracy, measured against a clinician-labelled sample of the hospital's own reports.
  • A written statement of coverage and of what could not be observed.

Terms

About 6 weeks of analysis once the data is available. A fixed fee, on request. It requires a data-processing agreement and a DPIA, completed with the hospital's DPO, and a named clinical lead. No change to anyone's workflow, and no patient contact.

Guardrails

Its guardrails

These limits are deliberate.

  • It does not analyse images.
  • It never generates or suggests a recommendation, an interval or a treatment.
  • It does not estimate risk and does not rank patients.
  • A person closes every follow-up, with a reason. Nothing closes automatically.
  • It always states what it covers, and never uses one hospital's data for anyone else.

Designed for

Hospital boards and quality and risk teams, who need to know how many recommendations were never done; and the departments that own each finding, which will receive each recommendation in the clinician's own words.

Same core

Every Antevion product is designed on the same core: it quotes what a clinician wrote, gives it an owner and proves whether it happened. It never generates an interval or a verdict; a person decides.

See the product family

Start with your hospital's own number.

12 months of signed reports, about 6 weeks of analysis once the data is available, and a fixed fee, on request. No change to anyone's workflow, and no patient contact.