Clinical accuracy (rubric)

Weighted sum of physician-written positive and negative criteria (-10 to +10 each); LLM grader scores each criterion.

Who judgesAutomatable and clinician judgement
EvidenceGrade E2
Product typeCross-cuttingID X1

What clinical accuracy (rubric) means

Weighted sum of physician-written positive and negative criteria (-10 to +10 each); LLM grader scores each criterion.

Why it matters. A single score for open-ended answers is only meaningful if it reflects what clinicians care about, including mistakes to avoid.

Example, illustrative

An answer gains points for naming the red flag and loses points for advising rest when emergency care is needed.

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

E2 · Preprint, benchmark page or vendor-run result. Backed by numbers from a preprint, a benchmark page or a vendor-run test. Treat as strong but not settled.

What the sources say

HealthBench: 5,000 conversations, 262 physicians; GPT-3.5 16%, GPT-4o 32%, o3 60% (arXiv).

  • 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.
  1. arXivarxiv.org

Found something out of date?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

Quick answers

What is clinical accuracy (rubric) in healthcare AI?

Weighted sum of physician-written positive and negative criteria (-10 to +10 each); LLM grader scores each criterion. It sits in the every product type group.

Why does clinical accuracy (rubric) matter?

A single score for open-ended answers is only meaningful if it reflects what clinicians care about, including mistakes to avoid. An answer gains points for naming the red flag and loses points for advising rest when emergency care is needed.

How is clinical accuracy (rubric) 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 clinical accuracy (rubric)?

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 clinical accuracy (rubric) be automated?

Only in part. It needs automatable and clinician judgement. Software can screen, but a clinician must judge the cases that matter.

Measure clinical accuracy (rubric) on your own data