Wording invariance

Near-identical inputs get consistent, safe outputs.

Who judgesAutomatable
EvidenceGrade E1
Product typeCross-cuttingID X16

What wording invariance means

Near-identical inputs get consistent, safe outputs.

Why it matters. Near-identical inputs should get consistent, safe outputs. Wording sensitivity is a warning sign.

Example, illustrative

Changing 'tummy ache' to 'abdominal pain' flips a triage result.

How to measure it

01

Define the unit

Decide whether you count per sentence, per note, per patient or per call.

02

Sample on purpose

Pick cases that cover specialties, languages and rare events, not only easy ones.

03

Judge with clinicians

Clinicians label a sample. Graders are then checked against those labels.

04

Report the margin

Show an interval, and the grader's own error rate beside the score.

Watch out for

A single average hides rare, serious errors and weaker subgroups.

What a good report shows

A number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.

Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.

Reviewed by the Precision research team.

How strong is the evidence

E1 · Peer-reviewed, regulator, audit or court source. Backed by a peer-reviewed paper, a regulator, an audit or a court record. Usually read through a summary, not the full text.

What the sources say

Oxford: near-identical subarachnoid-haemorrhage messages produced opposite advice (Oxford).

  • Automatable. Can be scored by software, including an AI grader that is spot-checked against clinicians.
  1. Oxfordox.ac.uk

Found something out of date? Write to hello@precision.example.

Quick answers

What is wording invariance in healthcare AI?

Near-identical inputs get consistent, safe outputs. It sits in the every product type group.

Why does wording invariance matter?

Near-identical inputs should get consistent, safe outputs. Wording sensitivity is a warning sign. Changing 'tummy ache' to 'abdominal pain' flips a triage result.

How is wording invariance measured?

Define the unit, then Sample on purpose, then Judge with clinicians, then Report the margin. Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.

What should I watch out for with wording invariance?

A single average hides rare, serious errors and weaker subgroups. A good report gives: a number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.

Can wording invariance be automated?

Largely yes, including AI graders that are spot-checked against clinicians. Report the grader's error rate beside every score.

Measure wording invariance on your own data