AI Enhanced Forecasting of Infectious Disease with Mathematical Modeling as a Fusion of Mechanistic and Data-Driven Approach and Framework

Abstract

Accurate prediction of infectious diseases is critical for timely treatment, resource allocation, and public health interventions. The SIR and SEIR models, along with their extensions, provide mechanistic understanding of disease transmission, but face challenges such as nonstationary dynamics, noisy surveillance data, and external factors including climate, behavior, mobility, and the emergence of new variants. Artificial Intelligence (AI) and Machine Learning (ML) models, such as neural networks and hybrid dynamical-statistical systems, offer the capability to identify nonlinear, multivariate patterns in data. This study proposes a novel hybrid health system that employs AI to enhance understanding of disease spread and reporting dynamics over time, and to explore spatial linkages. The framework integrates neural components into an extended SEIR-type model, preserving the mechanistic foundation while improving short- and medium-term predictive performance.