AI Alert System for Monitoring Clinical Supply Stocks

The problem

In day-to-day operations, a critical reduction in supplies may be noticed too late. When warehouse movements, consumption, open orders, lead times and stocktake adjustments are scattered across different screens, documents or team records, problems do not become visible in time.

Fragmented data delays preparation of the stock risk list and forces staff to search manually for supporting evidence again. Before making a decision, the warehouse manager and clinical unit manager have to complete missing fields and verify inconsistencies one by one.

A common exception is that stocktake adjustments, substitutions or planned peaks in activity may change consumption. Incomplete or incorrect automation that overlooks this context could lead to an unnecessary order or a stock shortage, so the output cannot be applied directly.

What we set out to improve

• Rate of confirmed stock risk alerts
• Rate of outputs corrected or rejected by the warehouse manager and clinical unit manager
• Time between the source record and the review output

How the system works

1. 01 Define the scope of the review and the authorised warehouse manager and clinical unit manager roles
2. 02 Collect the inputs: warehouse movements, consumption, open orders, lead times and stocktake adjustments
3. 03 Check source identity, date, version and data freshness
4. 04 Combine quantities on hand, reserved and in transit
5. 05 Compare consumption with lead times
6. 06 Check the exception: stocktake adjustments, substitutions or planned peaks in activity may change consumption
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 warehouse manager and clinical unit manager approve, correct, defer or reject the output

Methods we used

• Item-level stock and lead-time rules
• Source, format, version and required-field checks for warehouse movements, consumption, open orders, lead times and stocktake adjustments
• 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, stock risk list and human decision together

Where people stay involved

Data and security

Access to warehouse movements, consumption, open orders, lead times and stocktake adjustments 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 warehouse manager and clinical unit manager 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