Ontology-Based Knowledge Graphs for Personalized Public Health

This Research Topic focuses on the convergence of human-in-the-loop (HITL) techniques, ontology-driven knowledge graphs (KGs), and their applications in digital public health. "Human in the loop" (HITL) is a system or process where humans and automated systems, especially AI, collaborate to achieve a task, with humans providing oversight and input at critical stages to enhance accuracy, accountability, and ethical decision-making. By advancing this field, we aim to improve health outcomes through tailored, data-driven strategies, resulting in more effective and responsive public health systems.

Digital public health utilizes data and computational techniques to monitor, prevent, and manage population health issues. With the surge in digital data sources—ranging from electronic health records to social media—public health agencies face new challenges in data integration and insight extraction. Ontology-based KGs provide a unifying framework to connect and reason over these diverse sources, while semantic search further enhances accessibility by enabling context-aware retrieval of relevant health information across heterogeneous datasets. However, automated processes alone may miss nuances or context-specific insights vital for public health action. Human-in-the-loop approaches bridge this gap, embedding domain expertise into each stage of KG development and application. This emerging paradigm ensures that public health knowledge systems remain dynamic, accurate, and aligned with practitioners' needs.

The goal of this Research Topic is to address the critical challenge of integrating vast, heterogeneous health data sources and translating them into actionable knowledge for personalized public health interventions. Ontology-based KGs have emerged as transformative tools, structuring and linking disparate datasets for rich, holistic analyses. When coupled with HITL methodologies, these graphs enable a powerful synergy: expert knowledge can be infused directly into the data curation, validation, and analysis pipeline, ensuring outputs are both robust and contextually relevant. This collection invites research that pushes the boundaries of HITL-KG integration, exploring advances in methods, platforms, and real-world deployments, with the vision of enabling adaptive, trustworthy, and impactful public health initiatives.

We welcome original research articles, reviews, and case studies that contribute to advancing knowledge and best practices in this area. We invite submissions on, but not limited to, the following themes:

· Ontology development and refinement for public health KGs
· HITL methods for KG construction and curation
· Collaborative platforms for managing and updating public health KGs
· Applications of KGs in designing and personalizing public health interventions
· Real-time data integration and analytics
· AI/ML integration with HITL KGs
· Ethical and privacy considerations
· Visualization and user interface design for KGs
· Evaluation of KGs’ impact on health outcomes
· Interoperability standards for public health informatics