An infectious disease prevention and control framework integrating situational awareness and strategy optimization

To propose a new approach to characterizing the evolution of intervention strategies in order to address the inability of current methods to capture the dynamic, adaptive, and multi-objective nature of public health decision-making during the prediction of long-term changes in epidemics.

Epidemic control was conceptualized as a continuous and iterative process involving environmental conditions and pathogen transmission. Situational awareness was integrated with strategy optimization to predict the transmission and dynamic interventions of infectious diseases. This approach comprised a closed loop of environmental simulation, strategy generation, and utility-based evaluation. At each time point, sequential steps including situational awareness, strategy generation, evaluation and selection, and implementation were taken to simulate the adjustments in intervention strategies and their effects on transmission dynamics.

The proposed approach accurately predicted epidemic trajectories amid dynamic adjustment of intervention strategies and improved the characterization of long-term evolution of epidemics. It also enabled systematic simulation and comparative analysis of intervention pathways and their long-term consequences under different policy preferences, such as prioritizing economic activity or maintaining a Zero-COVID (Zero-Coronavirus Disease) policy.

The proposed approach provides a new dimension for understanding dynamic human-machine collaborative decision-making in case of complicated public health emergencies and offers a scalable platform for computational experiments to support the development of forward-looking and adaptive strategies for epidemic control.