Prediction of Alzheimer’s Using Random Forest with Radiomic Features

Alzheimer’s disease is a non-reversible, non-curable, and progressive neurological disorder that induces the shrinkage death of specific neuronal population associated with memory formation retention. It frequently occurring mental illness occurs in about 60%–80% cases dementia. usually observed between people age group 60 years above. Depending upon severity symptoms patients can be categorized Cognitive Normal (CN), Mild Impairment (MCI) Disease (AD). last phase where brain severely damaged, are not able to live on their own. Radiomics an approach extracting huge number features from medical images help data characterization algorithms. Here, 105 radiomic extracted used predict alzhimer’s. This paper uses Support Vector Machine, K-Nearest Neighbour, Gaussian Naïve Bayes, eXtreme Gradient Boosting (XGBoost) Random Forest disease. The proposed random forest-based Radiomic achieved accuracy 85%. also 88% accuracy, recall, precision 87% F1-score for AD vs. CN, it 72% 73% precisionand 71% MCI 69% 68% CN. comparative analysis shows performs better than others approaches.