Early Diagnosis of Alzheimer’s Disease Using Machine Learning in MCI Individuals

To find the Alzheimer’s Disease biomarkers K-means clustering, Principal Component Analysis and hierarchical clustering are employed in categorization of patients. In Machine Learning introductory results manifest that unsupervised learning is effective in differentiating between healthy people and Mild Cognitive Impairment patients. Clusters are provided using this method which shows further the metabolic abnormalities and brain shrinkage related to Alzheimer’s Disease. Functional changes and brain shrinkage before clinical symptoms are revealed by anomaly detection. Employing these methods could help doctors determine patients at risk at the initial stage and improve illness management. To advance neurodegenerative disease identification this study emphasizes the need to integrate and develop Machine Learning technologies into the diagnostics. Machine Learning for early diagnosis of disease is promising for clinical application and research. Later this study adds to the data supporting machine learning in the patient’s medical diagnostics that shows the patient’s outcomes and care.