Designing an Interoperable Intelligent Agent for the Blood Transfusion Chain in Geneva, Switzerland.

INTRODUCTION

Blood supply chain management is a cornerstone of modern medicine, yet it faces persistent structural challenges, including unpredictable supply and demand, perishability, and fragmentation of information systems. These limitations can hinder real-time inventory visibility and complicate extended blood compatibility searches, particularly for poly-transfused patients at risk of alloimmunization.

METHODS

We designed a proof-of-concept combining (1) an interoperable health data exchange pipeline based on HL7 FHIR, SNOMED-CT, and LOINC standards, and (2) an intelligent matching agent implementing multi-criteria, rule-based filtering and ranking logic for donor-recipient compatibility. The prototype was evaluated using a synthetic dataset reflecting representative operational scenarios.

RESULTS

The system aggregates cross-institutional inventory data and generates ranked compatibility suggestions, demonstrating the technical feasibility of combining semantic interoperability and decision-support logic for transfusion workflows.

CONCLUSION

Future work will focus on integration with validated matching algorithms and prospective evaluation in operational environments.