Early Detection of Epidemics Using Generalized Additive Models and Hidden Markov Models: A Neutrosophic Statistical Approach with Real-Time Health Data

Detection of epidemics during their early stages allows both the reduction of public health emergencies and the enhancement of resource management. The proposed research methodology combines GAMs and HMMs as a neutrosophic statistical framework which detects epidemics in real-time. GAMs analyze nonlinear epidemic patterns which result from environmental along with mobility conditions while HMMs use probabilistic state transitions to perform classification tasks. Bayesian hierarchical models along with spatio-temporal neutrosophic statistical techniques increase the framework's capability to respond regionally and deliver geospatial forecasts. Real world health surveillance data goes through our framework assessment where findings from GAMs and HMMs are compared to results obtained from RNNs and Transformer-based AI models. The combination of neutrosophic statistical methods with AI techniques leads to better outbreak prediction accuracy and generates results which can help interpret and take action in disease surveillance.