This research investigates applying artificial intelligence-based digital health technologies to predict Forex market volatility between different hourly intervals, and enhance their ability to support global health economic risk management. To better enable model robustness, a heterogeneous dataset was added that combined historical Forex with global health indicators (e.g., death rates, disease prevalence, and healthcare expenditures). Additional macroeconomic and geopolitical events were also included. The models incorporate recurrent neural networks (RNNs), linear regression, and other designs such as CNN-LSTM and Transformer-based networks for benchmarking performance. The paper highlights how AI-driven health-economic fusion enhances predictive capability and offers insights valuable for the economic management of risks following health crises. Experimental results show significant correlations between health information and market volatility, confirming the pragmatic value of this interdisciplinary strategy. Subsequent research will explore real-time application and extended applications in financial markets (e.g., stocks and cryptocurrencies) in the direction of strong financial forecasting systems.