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

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.

Infectious disease forecasting; SEIR model; neural networks; hybrid mechanistic-AI framework; epidemiological modeling; COVID-19; transmission rate; LSTM; graph neural networks; public health

1. Kermack, W. O., & McKendrick, A. G. (1927). A contribution to the mathematical theory of epidemics. Proceedings of the Royal Society A, 115(772), 700–721. [Google Scholar] [Crossref]

2. Giordano, G., Blanchini, F., Bruno, R., et al. (2020). Modelling the COVID-19 epidemic and implementation of population-wide interventions in Italy. Nature Medicine, 26, 855–860. [Google Scholar] [Crossref]

3. Flaxman, S., Mishra, S., Gandy, A., et al. (2020). Estimating the effects of non-pharmaceutical interventions on COVID-19 in Europe. Nature, 584, 257–261. [Google Scholar] [Crossref]

4. Box, G. E. P., & Jenkins, G. M. (1976). Time Series Analysis: Forecasting and Control. Holden-Day. [Google Scholar] [Crossref]

5. Chen, R. T. Q., Rubanova, Y., Bettencourt, J., & Duvenaud, D. (2019). Neural ordinary differential equations. In Advances in Neural Information Processing Systems (NeurIPS). [Google Scholar] [Crossref]

6. Wang, L., Duan, W., & Zhou, Q. (2021). Data-driven estimation of time-varying transmission rates for COVID-19 using neural networks. Journal of Theoretical Biology, 523, 110715. [Google Scholar] [Crossref]

7. Arroyo-Marioli, F., Bullano, F., Kucinskas, S., & Rondón-Moreno, C. (2021). Tracking R of COVID-19: A new real-time estimation using machine learning. PLOS ONE, 16(1), e0244474. [Google Scholar] [Crossref]

8. Saba, T., Sameer, M., Rehman, A., & Shah, S. A. (2021). Spatio-temporal prediction of COVID-19 cases using graph-based recurrent neural networks (IeRNN). IEEE Access, 9, 129776–129785. [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition