Clinician report
A diabetes appointment is short. Wellovue produces a summary of thirty or ninety days that a clinician can check rather than take on trust — the findings, what each was built from, and what the platform expected before it found out.
−1.1 across four measurements
7.9
Nov
7.4
Feb
7.1
May
6.8
Aug
78%
Above target most often between 21:00 and 23:00.
Walking after the evening meal, six days. −1.3 mmol/L against a predicted −1.3, recorded before the trial began.
What is on it
Each finding appears with the number of observations behind it, a confidence, and the list of things it does not account for. A finding the data could not support is included as exactly that, rather than dropped so the page looks stronger.
Where a finding is a comparison — meals with activity against meals without, late meals against earlier ones — both groups are shown, with their glucose curves drawn against the target range and their post-meal measurements beside them: time to peak, minutes above range, and time back in range.
The part worth the appointment
When an experiment runs, the platform records what it expects before the experiment begins, and that record cannot be revised afterwards. The report shows it next to what was actually observed, and the difference between them.
That is the number a clinician can use. It says how well this software’s model of this particular person has held up, which is a far more useful thing to know than any single finding on the page.
The engine build that produced each result is printed too. Two predictions made under different builds are not answers to the same question, and the report says which was which rather than quietly implying they are comparable.
What it is not
The report is a summary of a person’s own records and what a statistical model found in them. It contains no diagnosis, no treatment recommendation, no medication or insulin guidance, and no instruction to the clinician reading it. Nothing in it should change care on its own.
It is written to be argued with. Every number names what produced it, so a clinician who disagrees can see precisely where the disagreement is — which is the only reason a summary like this is worth carrying into a room.
Next
How this works goes through the loop in order, and diabetes intelligence defines what is being measured.