Pilot AI support for triage in the emergency department

Emergency departments prioritise patients at initial assessment with AI support

Future prospectStrictly regulatedSupporting specialist findingsHospitals & medical practices

Fits: Health & care

Software is meant to support nurses with the initial assessment, e.g. by recording information in a structured way and suggesting an urgency level. The aim is for fewer people to be triaged too low, even when the waiting area is full. So far, this is mainly being tested in studies and pilot projects. The triage decision stays with the professional.

Is this for you?

  • Your emergency department wants to be an early pilot partner, and medical and nursing management can set aside time for it.
  • You already work with an established triage system and document digitally.
  • You can carry out a silent comparison in which the suggestion does not yet influence the triage decision.
First step today

Without patient data: use the template below to draft a pilot plan in which the software initially only runs silently and its suggestion is compared with your initial assessment. Medical and nursing management set the target values and stopping criteria.

How to go about it

  1. Define the pilot question and responsibility for triage
  2. Choose a system whose legal status is clear
  3. Run it silently, then integrate it carefully
  4. Compare with your own triage decisions and patient courses
  5. Train triage nurses and doctors
  6. Document deviations and the pilot result

Templates to copy

Try it now
in the training
Analyse
in the training
Plan the rollout
in the training
Included in the training

The complete guide

  • 6 steps explaining exactly what to do
  • 3 proven templates to copy into your own AI
  • Safe use: data, checking, deciding, informing
  • Pitfalls, effort and how to recognise success

With the training you get all 430 guides for as long as your access runs.

See the trainingOne-off per person, no subscription

Same approach, other use cases

7 more use cases follow the pattern “Supporting specialist findings”.

Check medication for interactions with approved softwareFollow up atrial fibrillation alerts from wearables in an orderly wayDocument wounds and healing with photosHave skin photos pre-assessed by medical device softwareSupport X-ray, CT and MRI reporting with AI markingsPilot AI analysis of digital tissue sectionsPilot early warning of sepsis from vital signs
‹ PreviousSee all use casesNext ›

KP-05 · Legal status 08.10.2026 · Public services, emergency calls, triage (Annex III No. 5a/5d)