A Surveillance Infrastructure for Malaria Analytics: Provisioning Data Access and Preservation of Interoperability

Area of Science:

• Computer Science
• Public Health Informatics
• Epidemiology

Background:

• Malaria surveillance is significantly hampered in high-burden regions due to fragmented data across multiple silos.
• Limited interoperability between existing malaria data sources hinders the identification of disease trends and effective intervention strategies.

Purpose of the Study:

• To propose the Semantics, Interoperability, and Evolution for Malaria Analytics (SIEMA) platform for enhanced malaria surveillance.
• To leverage semantic data federation for accessing distributed data and maintaining interoperability with dynamic data sources.

Main Methods:

• Utilized Semantic Automated Discovery and Integration (SADI) Semantic Web Services for data access and interoperability.
• Employed the HYDRA semantic query engine for malaria program-specific queries.
• Developed a custom algorithm and dashboard to detect and manage changes in terminologies and data sources, using Valet SADI for service rebuilding.

Main Results:

• Developed a prototype surveillance and change management platform integrating various tools, terminologies, and algorithms.
• Demonstrated interoperable access to distributed data sources via SADI Semantic Web services, enabling complex queries with minimal user technical skill.
• Implemented a dashboard for monitoring changes, preserving interoperability, and minimizing service downtime.

Conclusions:

• Introduced a flexible framework for malaria surveillance, enabling queries across distributed data resources.
• The SIEMA platform offers interoperable, domain-agnostic data access and is transferable to other surveillance activities.
• The integrated dashboard facilitates infrastructure management and system updates, significantly advancing malaria information system capabilities.