Alzheimer’s disease (AD) is a progressive neurological illness that causes neuron cells degeneration, resulting in cognitive impairment. While there is no cure for AD, early diagnosis is critical to improving the quality of life of affected individuals. AD progression involves both temporal and spatial dimensions, yet existing models focus solely on either temporal or spatial aspects. Temporal models cannot process spatial data or AD’s spatiotemporal complexity, while spatial models neglect temporal disease progression patterns. Therefore, to comprehensively address the issue from both temporal and spatial dimensions, we propose a spatiotemporal brain model. For effective parameter estimation, we introduce an Integrated Model Parameter Estimation (IMPE) algorithm, which integrates a sparse Bayesian approach with a Markov Chain Monte Carlo (MCMC) method. In addition, we introduce a Classification Decision Tree algorithm for AD identification. Validation experiments utilizing EEG data from AHEPA University Hospital demonstrate that our integrated model and IMPE algorithm achieve superior performance compared to existing state-of-the-art approaches.