Integrating Surveillance and Stakeholder Insights to Predict Influenza Epidemics: A Bayesian Network Study in Queensland, Australia

TL;DR

This study uses a Bayesian network model to predict influenza epidemics in Queensland, integrating surveillance data and stakeholder insights to improve public health preparedness.

Contribution

The novel contribution is the development of a Bayesian network model that integrates diverse data sources and stakeholder knowledge to predict influenza epidemic risk.

Findings

Scenario simulations show that factors like Southeast Asian viral origin and low immunization rates increase epidemic likelihood.

Southeast Queensland is identified as particularly vulnerable under high-risk conditions.

The model achieved 70% accuracy and good discriminative performance (AUC = 0.6974).

Abstract

Public health relevance—How does this work relate to a public health issue?
The study addresses the ongoing global public health challenge of seasonal influenza by using a Bayesian Network (BN) model to examine how surveillance data, population characteristics, and contextual risk factors interact to influence epidemic occurrence in Queensland.The BN framework captures the complexity and uncertainty inherent in influenza transmission and epidemic emergence, potentially contributing to the planning and preparedness for infectious disease outbreaks.

The study addresses the ongoing global public health challenge of seasonal influenza by using a Bayesian Network (BN) model to examine how surveillance data, population characteristics, and contextual risk factors interact to influence epidemic occurrence in Queensland.

The BN framework captures the complexity and uncertainty inherent in influenza transmission and epidemic emergence, potentially contributing to the planning and preparedness for infectious disease outbreaks.

Public health significance—Why is this work of significance to public health?
The study demonstrates that a BN-based approach, integrating surveillance data, environmental/climatic indicators with expert and stakeholder knowledge, enhances epidemic risk estimation and response.The findings provide a transparent and interpretable modelling framework that quantifies uncertainty and supports evi-dence-informed decision-making in influenza preparedness.

The study demonstrates that a BN-based approach, integrating surveillance data, environmental/climatic indicators with expert and stakeholder knowledge, enhances epidemic risk estimation and response.

The findings provide a transparent and interpretable modelling framework that quantifies uncertainty and supports evi-dence-informed decision-making in influenza preparedness.

Public health implications—What are the key implications or messages for practitioners, policy makers and/or researchers in public health?
Public health practitioners can apply the BN model to explore “what-if” scenarios, identify high-risk regions and conditions, and guide targeted vaccination, travel risk management, and timely control measures.Policymakers and researchers may use the BN framework to support adaptive preparedness planning, evaluate intervention strategies under uncertainty, and extend the model to other climate-sensitive or emerging infectious diseases.

Public health practitioners can apply the BN model to explore “what-if” scenarios, identify high-risk regions and conditions, and guide targeted vaccination, travel risk management, and timely control measures.

Policymakers and researchers may use the BN framework to support adaptive preparedness planning, evaluate intervention strategies under uncertainty, and extend the model to other climate-sensitive or emerging infectious diseases.

Seasonal influenza continues to pose a substantial and recurrent public health challenge in Queensland, driven by annual variability in transmission and uncertainty in climatic, demographic, and behavioural determinants. Predictive modelling is constrained by data limitations and parameter uncertainty. In response, this study developed a Bayesian network (BN) model to estimate the probability of influenza epidemics in Queensland, Australia. The model integrated diverse inputs, including international and local influenza surveillance data, demographic health statistics, and expert and stakeholder insights to capture the complex multifactorial causal relationships underlying epidemic risk. Scenario-based simulations revealed that Southeast Asian viral origin, severe global influenza seasons, peak season timing, increasing international travel, absence of control measures, and low immunisation rates substantially elevate the likelihood of influenza epidemics. Southeast Queensland was identified as particularly vulnerable under high-risk conditions. Model evaluation demonstrated good discriminative performance (AUC = 0.6974, accuracy = 70%) with appropriate uncertainty quantification through credible intervals and sensitivity analysis. Its modular design and capacity for integrating various data sources make it a practical decision-making support tool for public health preparedness and responding to evolving climatic and epidemiological conditions.

Figures