Machine learning and deep learning algorithms used to diagnosis of Alzheimer’s: Review

• Published in: Materials today : proceedings Vol. 47; pp. 5151 - 5156
• Main Authors: Balne, Sridevi, Elumalai, Anupriya
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 2021
• Subjects: Alzheimer’s diagnosis; Convolution neural networks; Deep learning; Faster RCNN; Inception V2; Deep learning; Alzheimer’s diagnosis; Faster RCNN; Inception V2; Convolution neural networks
• ISSN: 2214-7853; 2214-7853
• DOI: 10.1016/j.matpr.2021.05.499

A notable contribution to medical diagnosis is made by artificial intelligence algorithms. The objective of this contribution is to help researchers and clinicians with the required machine learning algorithm to classify Alzheimer's. In this article, we demonstrate the previous work in the medical research area of Alzheimer’s disease, compared the efficiency and error of various algorithms. Therefore, the purpose of this study is to include all the relevant knowledge about the machine learning models used in the identification of Alzheimer's. This paper represents the results of different algorithms which are used for the diagnosis of this. The production of this work provides a list of the best machine learning algorithms with precision for disease diagnosis. In recent years, several high-dimensional, accurate, and effective classification methods have been proposed for the automatic discrimination of the subject between Alzheimer’s disease (AD) or its prodromal phase (i.e., mild cognitive impairment (MCI)) and healthy control (HC) persons based on T1-weighted structural magnetic resonance imaging (sMRI). These methods emphasis only on using the individual feature from sMRI images for the classification of AD, MCI, and HC subjects and their achieved classification accuracy is low. However, latest multimodal studies have shown that combining multiple features from different sMRI analysis techniques can improve the classification accuracy for these types of subjects.