Under-triage (missed emergency) and over-triage
Vignettes against clinician gold.
What under-triage (missed emergency) and over-triage means
Vignettes against clinician gold.
Why it matters. Missing an emergency is the costliest triage mistake, and over-triage wastes resources.
A message describing stroke signs is told to rest and rehydrate.
How to measure it
Write cases
Clinicians define the true condition and the right action.
Vary the wording
Simulate many phrasings, languages and levels of detail.
Check emergencies separately
Show red-flag recall apart from the average.
Confirm with real users
Measure the gap between simulated and real-user results.
Strong exam-style scores often fail when real people use the tool.
Emergency recall reported separately, results from varied wording and a simulator-to-real gap.
Report results from real users or realistic simulated users, with varied wording, and show the red-flag escalation rate separately from the average score.
Reviewed by the Precision research team.
How strong is the evidence
E4 · Recalled, not verified. Recalled from background knowledge and not verified. Treat it as a lead for investigation, not a finding.
What the sources say
Concept recalled; no 2025-26 triage accuracy data found.
- Automatable. Can be scored by software, including an AI grader that is spot-checked against clinicians.
- Clinician judgement. Needs a clinician to judge or label, because the answer depends on clinical meaning.
Found something out of date? Write to hello@precision.example.
Agents that measure this
Quick answers
What is under-triage (missed emergency) and over-triage in healthcare AI?
Vignettes against clinician gold. It sits in the patient-facing chat and triage group.
Why does under-triage (missed emergency) and over-triage matter?
Missing an emergency is the costliest triage mistake, and over-triage wastes resources. A message describing stroke signs is told to rest and rehydrate.
How is under-triage (missed emergency) and over-triage measured?
Write cases, then Vary the wording, then Check emergencies separately, then Confirm with real users. Report results from real users or realistic simulated users, with varied wording, and show the red-flag escalation rate separately from the average score.
What should I watch out for with under-triage (missed emergency) and over-triage?
Strong exam-style scores often fail when real people use the tool. A good report gives: emergency recall reported separately, results from varied wording and a simulator-to-real gap.
Can under-triage (missed emergency) and over-triage be automated?
Only in part. It needs automatable and clinician judgement. Software can screen, but a clinician must judge the cases that matter.