ABSTRACT
Alzheimer’s disease (AD) is a severe brain disease, and it adversely impacts thinking and memory. As a result, the collective brain size shrinks and prompts death. Therefore, early diagnosis of AD is a crucial factor to decide on the therapeutics. Machine learning, a branch of artificial intelligence, employs a variety of probabilistic and optimization techniques that permits discovery of post-concussion syndrome from huge and multipart datasets. This has motivated researchers to focus on using machine learning repeatedly for diagnosis of early stages of Alzheimer’s disease. In this venture, many other factors such as preprocessing the number of important attributes for feature selection, and class imbalance appear to distinctively influence the assessment of prediction accuracy. In order to overcome these limitations, this chapter proposes a model that consists of an initial preprocessing step, which is followed by an attributes selection step, after which classification is achieved using association rule mining. This proposed model gives the appropriate direction for future research on early diagnosis of AD and has the potential to distinguish AD from healthy controls.
