Performance evaluation of different classification factors for early diagnosis of alzheimer’s disease

Abstract

In India, approximately 4 million people are being suffered from some form of dementia. 44 million people are affected with dementia worldwide, so it becomes the global health crisis that must be resolved. Identification of pre-MCI and MCI patients at higher level of risk before conversion to AD is very effective for patient treatment. Before the content-based image retrieval (CBIR) system only clinical inputs were taken with some relevant data from genetic analysis where the diagnosis is totally dependent on knowledge and experience of doctor, which can be biased also. Multi-modality, network structure, and measures of classification play very important role to predict AD and its prodromal stages. Neuroimaging scanners likeMRI, PET,CT scan; biomarkers likeCSF, cerebral glucose, tau proteins, amyloid precursor proteins, apolipoproteins E (APOE); and clinical scores like ADAS-Cog, MMSE are being used as multi-modality inputs to predict disease and its prodromal stages. These imaging techniques along with clinical inputs and biomarkers have their own level of mechanisms to refine classification technique. AI techniques like machine learning, deep learning, and artificial neural network play an important role to diagnose and predict the AD and its prodromal stages. KNN, SVM, RF, naïve Bayes classifier, and CNN are techniques which are used for feature selection as well as for classification. Different combinations of these techniques are being used for optimal prediction. Somebody used them as multi-stage classifier and others used them as multi-view classifier.