Advanced ANN‐LMB Modeling of Malaria Transmission with Vaccination and Neurological Disability Dynamics

Malaria remains a persistent public health challenge in endemic regions, where high transmission rates and limited intervention coverage contribute to significant morbidity and mortality. Among its severe forms, cerebral malaria caused by Plasmodium falciparum is a leading cause of long‐term neurological disability, especially in children. In this study, a modified SITRM‐based compartmental model is developed that integrates vaccination dynamics and a disability progression parameter (), along with treatment failure, reinfection, and awareness‐driven behavioral changes. A comprehensive mathematical analysis establishes the local stability of the disease‐free equilibrium (DFE) under suitable conditions. To simulate the nonlinear dynamics of the model efficiently and accurately, an Artificial Neural Network (ANN) trained via the Levenberg‐Marquardt Backpropagation (LMB) algorithm is employed. The ANN is trained on numerical solutions generated by the classical RK4 method, using a data split of 85% for training, 10% for validation, and 5% for testing. Across multiple case scenarios, including DFE, endemic equilibrium, and sensitivity to key epidemiological parameters, the ANN achieves consistently low mean squared errors (MSEs) ranging from to , with regression coefficients approaching unity (). The ANN predictions demonstrate excellent agreement with reference solutions and maintain low absolute errors across all compartments. These findings underscore the effectiveness of the ANN‐LMB framework in modeling malaria dynamics and predicting severe outcomes, including neurological disability, thereby offering valuable insights for optimizing vaccination strategies and disability‐focused public health interventions.