VLGA: A Chaos-Enhanced Genetic Algorithm for Optimizing Transformer-Based Prediction of Infectious Diseases

Accurate and generalizable prediction of infectious disease incidence is essential for proactive public health response. This study proposes a novel hybrid VLGA-Transformer model to address this challenge, validated through tuberculosis (TB) and hepatitis B case studies. Utilizing monthly TB data from Zhejiang Province (2013–2023), raw sequences were first decomposed via Variational Mode Decomposition (VMD) to extract intrinsic temporal patterns. To overcome Transformer parameter optimization difficulties, we innovatively integrated the Lorenz attractor into a Genetic Algorithm (GA), creating a Lorenz-attractor-enhanced GA (LGA) that dynamically balances exploration and exploitation. The resulting VLGA-Transformer framework demonstrated superior performance, achieving R2 values of 0.96 for TB and 0.93 for hepatitis B prediction, significantly outperforming benchmark models in both accuracy and stability. When tested on hepatitis B data, the model confirmed its robust cross-disease generalizability. These findings highlight the framework’s dual strengths—high-precision forecasting and robust generalization—providing actionable insights for public health authorities to optimize resource allocation and intervention strategies, thereby advancing data-driven infectious disease control systems.