As the incidence of senile dementia continues to increase, researches on Alzheimer's disease (AD) have become more and more important. Several studies have reported that there is a close relationship between AD and aging. Some researchers even pointed out that if we wanted to understand AD in depth, mechanisms of AD based on accelerated aging must be studied. Nowadays, machine learning techniques have been utilized to deal with large and complex profiles, thus playing an important role in disease researches (i.e., modelling biological systems, identifying key modules based on biological networks, and so on). Here, we developed an aging predictor and an AD predictor using machine learning techniques, respectively. Both aging and AD biomarkers were identified to provide insights into genes associated with AD. Besides, aging scores were calculated to reflect the aging process of brain tissues. As a result, the aging acceleration network and the aging-AD bipartite graph were constructed to delve into the relationship between AD and aging. Finally, a series of network and enrichment analyses were also conducted to gain further insights into the mechanisms of AD based on accelerated aging. In a word, our results indicated that aging may contribute to the development of AD by affecting the function of the immune system and the energy metabolism process, where the immune system may play a more prominent role in AD.