Gene Expression analysis for the diagnosis of Alzhemiers disease using Machine Learning

Alzheimer's Disease is the one among the repetitive neurological disorder. Diagnosing Alzheimer's disorder uses a combination of different symptoms and diagnostic tests. However, accurate diagnosis is difficult in the early stages. In this study, each cell in gene dataset from various sources and applied machine learning (ML)-based methods to diagnose Alzheimer's disease. Set of important genetic signatures that contribute to the disease diagnosis. The PCA, t-SNE and Ridge for feature selection. Classifying AD cases and healthy controls using cutting-edge ML algorithms like SVM, RFC, DT, and LR. The diagnostic accuracy of the SVM was the greatest. A number of important biomarkers contributing to the diagnosis of AD have been identified. Some of these genes are associated with other neurological diseases. Examining each cell in the gene dataset from different sources made this model robust.