The non-linear relationship between population health and economic prosperity represents a new frontier in modelling and optimization. This paper presents a novel hybrid computational framework which was designed for crafting optimal health policies through empirically validated simulations, integrating a top-down macroeconomic framework with a bottom-up agent-based simulation (ABM) for a dynamic, heterogeneous population. The proposed framework employs a robust, four-step pipeline. First, an agent-based model generates a large dataset, which will train a high-speed surrogate model. Further on, an AI-based optimization engine leverages this surrogate model in order to efficiently discover the optimal policy strategies, which are subsequently validated with regard to their statistical robustness. This framework was validated against a post-menopausal osteoporosis case study, identifying a policy that significantly outperforms the benchmark strategy across a ten-run validation process. To sum up, this paper provides a new, empirically grounded blueprint for a “Digital Twin” for public health, combining complex systems modelling with AI-driven optimization to help engineer longevity at a national level.
Agent-based simulation, AI-driven, Optimization.
Daniel Ioan CHIS, Ioan DUMITRACHE, "Engineering Longevity: A Hybrid AI-driven Simulation Framework for Optimizing National Health and Economic Prosperity", Studies in Informatics and Control, ISSN 1220-1766, vol. 34(4), pp. 79-86, 2025. https://doi.org/10.24846/v34i4y202507
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).