Mathematical Modeling of Nipah Virus: Sensitivity and Differential Transformation Insights using Deep Learning

Nipah virus (NiV) is a zoonotic virus with a high mortality rate and potential for human-to-human transmission, posing a significant public health threat. This paper presents a mathematical model to analyze the transmission dynamics of Nipah virus, incorporating sensitivity analysis and differential transformation methods. The proposed SEIR-based model includes compartments for susceptible, exposed, infectious, and recovered individuals, enhanced with deep learning techniques to improve predictive accuracy. Sensitivity analysis identifies key parameters influencing the spread of the virus, while the differential transformation method (DTM) provides efficient solutions to the system of differential equations. A deep learning model, based on LSTM networks, is integrated to capture complex patterns in the data. The framework is validated using real-world data, demonstrating superior performance in terms of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²) compared to traditional SEIR models. The results highlight the model's effectiveness in predicting Nipah virus transmission, offering valuable insights for public health planning and intervention strategies. Despite challenges such as data scarcity and model interpretability, the proposed framework represents a significant advancement in infectious disease modeling, with potential applications in combating Nipah virus and other zoonotic diseases.