Alzheimer's disease (AD) is the most frequent cause of dementia and accounts for 60% to 80% of all dementia instances. It is a neurodegenerative form of dementia that initially manifests as moderate cognitive impairment (MCI) before progressing to more severe symptoms over time. It disrupts brain cells, causes a decline in memory and cognitive abilities, and makes it difficult to complete even the simplest tasks. In the early stages of Alzheimer's disease, there are medical treatments that can be used to reverse the effects of the disease. Therefore, this paper proposed the random forest classifier to classify longitudinal and cross-sectional MRI data. Furthermore, accuracy and sensitivity are used as quantitative evaluation parameters. The obtained results show that the random forest outperforms in accuracy and sensitivity compared to logistic regression and decision trees.