Unsafe-advice rate
Dangerous instructions (ECRI: wrong diagnoses, invented body parts, unsafe electrosurgical electrode placement advice).
What unsafe-advice rate means
Dangerous instructions (ECRI: wrong diagnoses, invented body parts, unsafe electrosurgical electrode placement advice).
Why it matters. Dangerous instructions can cause direct harm.
An answer suggests an unsafe home treatment for a serious symptom.
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
E3 · Secondary or single-source report. Reported by trade press or a single source. Directional only until checked against the primary document.
What the sources say
(ECRI).
- Clinician judgement. Needs a clinician to judge or label, because the answer depends on clinical meaning.
- ECRIhome.ecri.org
Found something out of date? Write to hello@precision.example.
Agents that measure this
Quick answers
What is unsafe-advice rate in healthcare AI?
Dangerous instructions (ECRI: wrong diagnoses, invented body parts, unsafe electrosurgical electrode placement advice). It sits in the patient-facing chat and triage group.
Why does unsafe-advice rate matter?
Dangerous instructions can cause direct harm. An answer suggests an unsafe home treatment for a serious symptom.
How is unsafe-advice rate 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 unsafe-advice rate?
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 unsafe-advice rate be automated?
Only in part. It needs clinician judgement. Software can screen, but a clinician must judge the cases that matter.