AI System for Administrative Checks of Patient Referral Documents

The problem

In day-to-day operations, missing attachments can delay admission. When the referral form, identity fields, organisation details and attachment list are scattered across different screens, documents or team records, problems do not become visible in time.

Fragmented data delays preparation of the missing-field report and forces staff to search manually for supporting evidence again. Before making a decision, the patient admissions officer and authorised healthcare professional have to complete missing fields and verify inconsistencies one by one.

A common exception is that attachments may be completed later in an emergency process. Incomplete or incorrect automation that overlooks this context could lead to a valid referral being rejected or an incomplete file being accepted, so the output cannot be applied directly.

What we set out to improve

• Number of confirmed missing administrative fields
• Rate of outputs corrected or rejected by the patient admissions officer and authorised healthcare professional
• Time between the source record and the review output

How the system works

1. 01 Define the scope of the review and the authorised patient admissions officer and healthcare professional roles
2. 02 Collect the inputs: referral form, identity fields, organisation details and attachment list
3. 03 Check source identity, date, version and data freshness
4. 04 Check the document version and identity
5. 05 Compare the listed attachments with the files
6. 06 Check the exception: attachments may be completed later in an emergency process
7. 07 Place low-confidence or inconsistent records in a separate human review queue
8. 08 Write the source identity, rule, output and time to the audit trail
9. 09 Have the patient admissions officer and authorised healthcare professional approve, correct, defer or reject the output

Methods we used

• Validation of the template and attachment list
• Source, format, version and required-field checks for the referral form, identity fields, organisation details and attachment list
• A missing-data warning instead of an estimate when inputs are missing or inconsistent
• Checking exceptions separately from the main rule
• Storing the source identity, rule result, referral missing-field report and human decision together

Where people stay involved

Data and security

Access to the referral form, identity fields, organisation details and attachment list is limited to the minimum permissions required for each role. Identifiers and sensitive fields are masked where possible, and only the necessary section is sent to the model rather than the entire raw file. Access, outputs and decisions by the patient admissions officer and authorised healthcare professional are recorded; the system does not enter production until the organisation has approved the retention period and data location.

Who this suits

Frequently asked questions