Early Detection of Cognitive Decline Using Machine Learning Algorithm and Cognitive Ability Test. (20th January 2022)

• Record Type: Journal Article
• Authors: Revathi, A.; Kaladevi, R.; Ramana, Kadiyala; Jhaveri, Rutvij H.; Rudra Kumar, Madapuri; Sankara Prasanna Kumar, M.
• Other Names: Iwendi Celestine Academic Editor.
• Is Part Of: Security and communication networks. Volume 2022(2022)
• Publication Date: 2022-01-20
• Subjects: Computer networks -- Security measures -- Periodicals; Computer security -- Periodicals; Cryptography -- Periodicals; 005.805
• DOI: 10.1155/2022/4190023
• Languages: English
• ISSNs: 1939-0114

Abstract

Abstract : Elderly people are the assets of the country and the government can ensure their peaceful and healthier life. Life expectancy of individuals has expanded with technological advancements and survey tells that the elderly population will become double in the year 2030. The noninfectious cognitive dysfunction is the most important risk factor among elderly people due to a decline in their physiological function. Alzheimer, Vascular Dementia, and Dementia are the key reasons for cognitive inabilities. These diseases require manual assistance, which is difficult to provide in this fast-growing world. Prevention and early detection are the wise solution for the above diseases. Diabetes and hypertension are considered as main risk factors allied with Alzheimer's disease. Our proposed work applies a two-stage classification technique to improve prediction accuracy. In the first stage, we train a Support vector machine and a Random Forest algorithm to analyze the influence of diabetes and high blood pressure on cognitive decline. In the second stage, the cognitive function of the person with the possibility of Dementia is assessed using the neuropsychological test called Cognitive Ability Test (CAT). Multinomial Logistic Regression algorithm is applied to CAT results to predict the possibility of cognitive decline in their postlife. We classified the risk factor using the operational definitions: "No Alzheimer's, " "Uncertain Alzheimer's, " and "Definite Alzheimer's". SVM of stage 1 classifier predicts with an accuracy of 0.86 and Random Forest with an accuracy of 0.71. Multinomial Logistic algorithm of stage 2 classifier accuracy is 0.89. The proposed work enables early prediction of a person at risk of Alzheimer's Disease using clinical data.