The most prevalent form of dementia of the central nervous system, Alzheimer’s disease (AD), leads to a reduction in a number of brain functions (e.g., memory loss). Non-invasive timely identification of Alzheimer’s disease has received a lot of research attention recently, as correct detection is the most important factor in improving patient health care and treatment outcomes. This study employs machine learning algorithms for the definitive reading and extreme inequality of Alzheimer’s disease stages. In this study, algorithms such as KNN and XG Boost are used to detect maximum accuracy across the dataset. The higher accuracy is achieved from the XGBoost classifier which is 86%. This present work aims to be a help to the medical fraternity for enhanced research in the field of Alzheimer’s and detection of dementia.