This research domain focuses on investigating diagnostic approaches and AI-driven innovations to enhance outbreak detection and surveillance. It explores the development, application, and optimisation of machine learning, automation, and data validation processes to ensure data quality, optimise analytics, and support real-time decision-making.

Potential Research Questions on AI for knowledge synthesis

• How can AI efficiently identify, synthesize, and merge disparate data sources to improve the quality and variety of data?
• How can AI support the design of models to reduce development time while maintaining accuracy?
• How can AI support efforts of identifying epidemiological parameters?

Potential Research Questions on technology and analytics

• What is the role of AI in mis- and dis-information and how can it be leveraged to assist in the validation and verification of information for public health intelligence?
• How can AI and machine learning be leveraged for rapid threat detection across diverse, multidisciplinary data streams?
• How can AI and machine learning be leveraged to optimize intervention planning and implementation before, during and after health emergencies?
• What are the challenges and opportunities for implementing AI and machine learning approaches for public health intelligence in low-resource settings? What frameworks and solutions can we put in place to address these challenges and empower / enable equitable contributions and use?
• How could uncertainty in modelling be represented more clearly?

This research domain addresses the study of data governance and data sharing practices to improve access, quality, and interoperability of epidemic intelligence data. It includes investigating federated systems, open data, and social science approaches to assess factors influencing efficient data integration across multiple sectors.

Potential Research Questions on data exchange and interoperability

• What frameworks enable seamless data exchange between systems within the health sector as well as across diverse sectors (e.g. public health agencies, private sector and academia) and domains (human health, animal health, environment, etc)
• How can federated data-sharing architectures be optimized to balance data accessibility with privacy, confidentiality and security concerns? Is this practical for public health intelligence and, if so, what are the opportunities and challenges for its implementation?

Potential Research Questions on data sources for public health intelligence

• What is the role of citizen science and community-sourced data in public health intelligence, and how can this be effectively verified and incorporated?
• What and how can behavioural elements be incorporated into public health intelligence, including modeling, to better inform decisions and policies?

Potential Research Questions on data integration

• What are the most effective frameworks for integrating real-time data from human health, animal health, environmental and socio-economic sectors?
• What barriers are there to implementing data integration frameworks in low-resource settings and how do we ensure representation of underserved or marginalized populations?
• What are the technical and methodological challenges in merging structured and unstructured data into unified systems with use case examples (where they exist) from other sectors?
• How can a particular type of data (genomic/behavioral/economic/climactic) be collected and utilized to its full extent, and in a timely fashion, when tackling outbreaks?
• How can different types of modelling methods be combined or utilized to achieve more comparable results or to integrate different data types?
• In what scenarios and under which conditions would containment modeling be helpful?

This research domain investigates advanced modelling and forecasting techniques to improve understanding of pathogen (re-)emergence and disease transmission. It aims to improve real-time infectious disease predictions, enhance data integration, and develop robust analytical frameworks to support early warning systems.

Potential Research Questions on analytical tools for outbreaks

• What are the key challenges faced by field epidemiologists in using data analytics tools during epidemic response, and how can these tools be improved to address these challenges?
• How can open-source epidemiological software tools be adapted to better meet the real-time needs of epidemic responders in low- and middle-income countries?
• How can we strengthen local analytic capacity in outbreak response?

Potential Research Questions on genomics data analytics

• How can population level genomic variation inform risk assessment?
• How can data federation support sharing and analysis of pathogen genomes?

This research domain encompasses scientific inquiry into cross-disciplinary collaboration and the effectiveness of data integration across health, environmental, and social sectors. It explores methods to enhance detection, verification, and notification processes by leveraging diverse data sources and evaluating coordination mechanisms for improved pandemic preparedness.

Potential Research Questions on regional pandemic preparedness

• How can regional capacities diagnostics be effectively identified, analyzed, and evaluated to uncover strengths and gaps?
• What are the key capacity variations in clinical trial set-up across regions, and what strategies can enhance infrastructure to enable rapid?

• Quality Standards: This research domain focuses on exploring and assessing evaluation methods, data standardisation, and oversight mechanisms to ensure the reliability and effectiveness of surveillance and response efforts. It seeks to develop best practices for monitoring the quality and impact of public health interventions during and beyond pandemics.
• Community-Centered Approaches: This research domain investigates ways to incorporate societal perspectives, public sentiment, and community-specific concerns into decision-making for pandemic preparedness and response. It includes research on the integration of community-sourced data into surveillance systems and the role of health equity indicators for targeted interventions.
• Governance: This research domain includes the analysis of ethical, legal, and regulatory frameworks to facilitate secure and equitable data governance and sharing for epidemic intelligence. It further examines governance models, decision-making structures, and mechanisms that enable evidence-based policymaking.
• Evidence to Policy: This research domain investigates approaches for effectively translating research insights into policy decisions. It focuses on enhancing communication of health risk information to policymakers and identifying enablers and barriers to evidence-based decision-making.