Comparative Analysis of the Machine and Deep Learning Classifier for Dementia Prediction

The most frequent kinds of neurodegenerative sickness are Alzheimer's disease and dementia, and both of these conditions worsen with time. Research suggests that those with mild cognitive impairment are more likely to develop this condition. Standardized clinical criteria have made it possible to diagnose Alzheimer's disease (AD), the most common form of dementia, with a high degree of certainty. This makes it far more challenging to identify dementia as a whole than it is to define Alzheimer's disease specifically, since different types of dementia share so many clinical and pathological aspects. Several methodologies are existing for dementia prediction. Hence to better predict and diagnose diseases, several data miners and computer scientists are already using ML algorithms to healthcare data. The purpose of this study is to identify a model (comparison of several ML classifiers with a user-supplied convolutional neural network (CNN) model) along with the Infograin feature selection framework that can reliably predict whether or not a specific patient is connected with dementia.