Thermal analysis of Alzheimer’s disease prediction using random forest classification model

Abstract

Missing and irregularly sampled data points are common in time-dependent data collected in Alzheimer's disease studies. As a result, time-series methods based on regular sampling cannot be applied directly to data without first undergoing pre-processing. In this paper developed to learn the relationship between pairs of data points at different times, we implement random forest model separations in time the input vector contains a summary of the time series history. Due to similar brain patterns and pixel intensities, the diagnosis of AD images to feature representation for categorization. Machine Learning approaches can learn things like representations from data. A 4-way classifier is used in this study to distinguish between Healthy Control (HC) and Mild Alzheimer's disease (AD), Very Mild AD, and Moderate AD patients. Experiments are carried out using the OASIS dataset, and the results are used to classify diseases into multiple categories. The Random Forest Classification Model was used to do a thermal analysis of Alzheimer's disease prediction. The random forest classifier models have been shown to consistently outperform their equivalents. The improved accuracy of tweaking the parameters of random forest classifiers demonstrated in this study work argues for its use in the classification of stages of Alzheimer's disease.