Early Detection Of Alzheimer Disease In Elderly Web-Based Using Support Vector Machine Classification Method

Abstract

Alzheimer's disease is characterized by dimentia diseases that usually begin with a decrease in

memory. The number of people in around the world with dimentia diseases is estimated to reach 47.5 million

and is increased to quadruple by 2050. The risk factors that make someone exposed Alzheimer's disease are

aging, alcohol consumption, anterosclerosis, diabetes mellitus, down syndrome, genetics, hypertension,

depression, and smoking. Aging is the biggest risk factor for Alzheimer's disease. People with age 65 years and

over have a higher risk. Therefore, it is important to early detect Alzheimer's disease in order to start planning

adequate care and medical needs. This study aims to create a web-based system for early detection of

Alzheimer's disease in the elderly using support vector machine classification. Detection of Alzheimer's disease

using the metric Mini Mental State Examination (MMSE) and Clinical Dementia Rating (CDR) obtained

through questionnaires to find out about cognitive function, thinking ability and ability to perform daily tasks.

Classification is carried out using the Support Vector Machine (SVM) algorithm. Alzheimer's classification

testing uses a confusion matrix with an accuracy value of 85%. For system testing carried out User Acceptance

Test with general practitioner, the results were obtained that all the features and functions of the system had run

as expected.