OpenAdaptFiling incoming reports to the right chart
Lab results, consult letters and imaging reports must be filed to the right patient's chart. OpenAdapt could file each one from a demonstration and stop when the patient doesn't clearly match. The check it relies on stopped 5 of 5 look-alike patients in our test and let the right patient through.
Updated 2026-10-18
Today
| Step | Seconds |
|---|---|
| Open the report | 8 |
| Find the patient | 16 |
| Create the record and attach it | 59 |
| Log it | 14 |
| In all | 97 (about 1.6 minutes) |
Derived from the step times in the UCSF referral study; filing wasn't timed on its own. The risk is the wrong chart: two patients with the same name and birth date.
With OpenAdapt
It would find the patient from the report's identifiers, confirm the chart matches before attaching, attach the report, and read the chart back another way to confirm one new document on the right patient. When identifiers are close but not exact, it stops and leaves the report for a person.
The check it relies on
The right-patient check: with the same name, same birth date and record numbers like MG4408 and MG44O8, it stopped 5 of 5 times. Of 2 control cases, it let the right patient through and stopped a plainly different patient. On pixel-only screens it stops whenever the right patient's own record number has look-alike characters: 47 to 61 in 100 correct-patient checks on our test corpora (re-measured 17 Oct 2026). Those are extra stops, not wrong entries.
A confirmed list of the system's record numbers removes most of those extra stops: on a rendered record list, they fell from 176 to 3 in 280 clicks.
The readiness test we'd run
- On test patients or a test copy of your EMR, file a set of synthetic reports, including look-alike patients, a report with no matching patient and a duplicate report.
- Agree the pass criteria first, such as "every look-alike stops; every filed report reads back on the right chart; no report is filed twice".
- Nothing is filed to a real chart until you approve go-live in writing.
Is it a fit?
- Reports arrive as files, faxes or in an inbox. OpenAdapt can read the patient's identifiers from a PDF, fax image or email and holds back any unclear field for a person.
- Your EMR offers a second way to read a chart's documents.
- Enough reports a day that filing takes real staff time.
Related: referral intake · the right-record check · booking
Sources
- Derived from the UCSF 2020 step times (JAMIA Open 2020;3(3):405): open the report 8 s, find the patient 16 s, create the record 59 s, log it 14 s; 97 s, about 1.6 minutes (our sum).
- OpenAdapt look-alike test set (synthetic rows), 2026: 5 of 5 look-alike patients stopped; of the 2 control cases, the right patient was let through and a plainly different patient was stopped. On pixel-only screens the check stops whenever the right patient's own record number has look-alike characters (O and 0, l and 1); on our test corpora that was 47 to 61 in 100 correct-patient checks, re-measured 17 Oct 2026 (IDENTITY_EVIDENCE.md). With a confirmed list of the system's record numbers (openadapt-flow 2.2.0), those stops on a rendered record list fell from 176 to 3 in 280 clicks whose neighboring row wasn't a look-alike twin (KNOWN_IDS.md).
See it on your process
Bring one task your team types every day. We'll tell you whether it fits, and what a test on your own system would cover.