Intelligent classification of Alzheimer's disease based on support vector machine

Wenzhe Cai; Chengli Chu; Xianao Zhu

doi:10.1117/12.2686137

28 July 2023 Intelligent classification of Alzheimer's disease based on support vector machine

Wenzhe Cai, Chengli Chu, Xianao Zhu

Proceedings Volume 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023); 127563J (2023) https://doi.org/10.1117/12.2686137
Event: 2023 3rd International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC 2023), 2023, Tangshan, China

Abstract

Alzheimer's disease (AD) is a kind of people memory decline, brain function slow and gradually mutated mental loss performance of the disease. Early diagnosis and prediction of AD can delay the onset of patients and may prolong the life span of patients, which is of great scientific significance to the whole society. In this paper, machine learning and other methods are used to analyze and model AD data, add brain characteristic indicators, and conduct data preprocessing. The intelligent diagnosis of AD is realized by using SVM, which is a paired classification method. The accuracy of five classifications obtained by SVM reaches 0.7. The accuracy of LMCI (68%), SMC (58%) and EMCI (76%) is good. By extracting and discovering key symptoms that affect the diagnosis and prediction of AD and classifying patients, early diagnosis and prediction of the incidence of AD can be achieved effectively and quickly, so as to achieve effective measures to prevent AD. SVM based on the pair classification method can realize the intelligent diagnosis of AD, and can be extended to more classification problems.

Citation Download Citation

Wenzhe Cai, Chengli Chu, and Xianao Zhu "Intelligent classification of Alzheimer's disease based on support vector machine", Proc. SPIE 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023), 127563J (28 July 2023); https://doi.org/10.1117/12.2686137

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available