AI System for Preparing Patient Appointment Request Classifications

The problem

In daily operations, free-text requests may enter the queue without complete department or time information. When appointment forms, call notes, department calendars and contact preferences are spread across different screens, documents or team records, the issue may not be visible in time.

This fragmented data delays preparation of the appointment record draft and forces staff to search again for supporting information. Before deciding, the appointment registration officer must complete missing fields and verify conflicts one by one.

A common exception is that the same expression can refer to different departments in different clinics. If this context is not checked, an incomplete or incorrect workflow could direct a patient to the wrong department, so its output cannot be applied directly.

What we set out to improve

• Number of records returned by the officer because information was missing
• Rate of outputs corrected or rejected by the appointment registration officer
• Time between the source record and the review output

How the system works

1. 01 Define the review scope and the authorised appointment registration officer role
2. 02 Receive the appointment form, call note, department calendar and contact preference
3. 03 Check source identity, date, version and data freshness
4. 04 Extract administrative appointment fields
5. 05 Compare the candidate department and time window with the calendar
6. 06 Check the exception that the same expression can refer to different departments in different clinics
7. 07 Place low-confidence or conflicting 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 appointment registration officer approve, correct, defer or reject the output

Methods we used

• An organisation-specific department glossary and rule-based field validation
• Source, format, version and mandatory-field checks for appointment forms, call notes, department calendars and contact preferences
• A missing-data warning instead of inference when inputs are absent or conflicting
• Separate assessment of exceptions and the main rule
• Joint retention of the source identity, rule result, appointment record draft and human decision

Where people stay involved

Data and security

Appointment forms, call notes, department calendars and contact preferences are accessed with the narrowest permissions required for the role. Identity and sensitive fields are masked where possible, and only the necessary section rather than the entire raw file is sent to the model. Access, output and the appointment registration officer's decision are logged; production use does not begin until the organisation approves data retention and location.

Who this suits

Frequently asked questions