Unit and aggregation correctness

Example: 7015 ml vs 7515 ml fluid-output sum (anecdote, vendor blog).

Who judgesAutomatable
EvidenceGrade E3
Product typeEHR agentsID A5

What unit and aggregation correctness means

Example: 7015 ml vs 7515 ml fluid-output sum (anecdote, vendor blog).

Why it matters. Arithmetic and unit slips are easy to miss.

Example, illustrative

A fluid-output sum is off by 500 ml.

How to measure it

01

Set tasks

Define tasks with a clear correct end state in the record.

02

Run in a sandbox

Use a FHIR test record, never a live chart.

03

Check the end state

Programmatically compare resulting records.

04

Review actions

Log every write and which needed approval.

Watch out for

Judging only the final answer misses harmful actions along the way.

What a good report shows

Task completion with resources touched, actions taken, and approval coverage.

Report task completion with the FHIR resources touched, the actions taken, and which actions needed human approval.

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

(medblocks).

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

Found something out of date?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

Quick answers

What is unit and aggregation correctness in healthcare AI?

Example: 7015 ml vs 7515 ml fluid-output sum (anecdote, vendor blog). It sits in the agentic ehr workflows group.

Why does unit and aggregation correctness matter?

Arithmetic and unit slips are easy to miss. A fluid-output sum is off by 500 ml.

How is unit and aggregation correctness measured?

Set tasks, then Run in a sandbox, then Check the end state, then Review actions. Report task completion with the FHIR resources touched, the actions taken, and which actions needed human approval.

What should I watch out for with unit and aggregation correctness?

Judging only the final answer misses harmful actions along the way. A good report gives: task completion with resources touched, actions taken, and approval coverage.

Can unit and aggregation correctness be automated?

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

Measure unit and aggregation correctness on your own data