REAL-TIME PREDICTIVE ANALYTICS FOR EARLY DETECTION OF EMERGING GLOBAL HEALTH THREATS

We examine how predictive health data analytics strengthens early detection of emerging global health threats by developing and testing the Global Early Health Threat Prediction Model using the Real Time Emerging Disease Monitoring Dataset covering Ghana between 2020 and 2025. The empirical design combines integrated surveillance records, algorithm based detection outputs, and institutional preparedness indicators collected from national disease monitoring systems and analyzed across a sample of forty four surveillance professionals. Results show that stronger real time data integration, improved machine learning risk detection accuracy, and faster surveillance data processing substantially enhance outbreak identification, increase alert accuracy, and shorten detection time. Evidence also shows that institutional response capacity strengthens the link between predictive analytics and early detection outcomes by accelerating response activation and improving preparedness across surveillance networks. The model reveals that predictive epidemiology operates through an interaction between digital analytics infrastructure and institutional readiness rather than through technology alone. These findings offer a scalable framework for strengthening global epidemic intelligence systems and provide policy guidance for building integrated surveillance architectures capable of generating timely public health alerts and improving global health security outcomes.