Code-level exact-match accuracy
Assigned codes against certified-coder gold.
What code-level exact-match accuracy means
Assigned codes against certified-coder gold.
Why it matters. Each code carries money and compliance risk, so exact matches matter.
The model picks a code close to the right one but not the right one.
How to measure it
Create ground truth
Certified coders code a sample of notes.
Compare at two levels
Report accuracy per code and per claim.
Separate over and under
Overcoding and undercoding carry different risks.
Apply payer rules
Run deterministic checks on code validity and policy.
Vendors often quote one accuracy figure without saying how it was measured.
Accuracy against certified-coder audit, by code set, with over and under coding shown apart.
Report accuracy against certified-coder audit, by code set, with overcoding and undercoding shown separately and the payer rules applied.
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
GPT-4 45.9% ICD-9-CM, 33.9% ICD-10-CM, 49.8% CPT (April 2024) (Healthcare IT News) (dated).
- Clinician judgement. Needs a clinician to judge or label, because the answer depends on clinical meaning.
- Healthcare IT Newshealthcareitnews.com
Found something out of date? Write to hello@precision.example.
Agents that measure this
Quick answers
What is code-level exact-match accuracy in healthcare AI?
Assigned codes against certified-coder gold. It sits in the coding, prior authorisation and revenue cycle group.
Why does code-level exact-match accuracy matter?
Each code carries money and compliance risk, so exact matches matter. The model picks a code close to the right one but not the right one.
How is code-level exact-match accuracy measured?
Create ground truth, then Compare at two levels, then Separate over and under, then Apply payer rules. Report accuracy against certified-coder audit, by code set, with overcoding and undercoding shown separately and the payer rules applied.
What should I watch out for with code-level exact-match accuracy?
Vendors often quote one accuracy figure without saying how it was measured. A good report gives: accuracy against certified-coder audit, by code set, with over and under coding shown apart.
Can code-level exact-match accuracy be automated?
Only in part. It needs clinician judgement. Software can screen, but a clinician must judge the cases that matter.