Welcome to the InfoSci Platform
Reference Hub2
Performance Comparison of Machine Learning Algorithms for Dementia Progression Detection

Performance Comparison of Machine Learning Algorithms for Dementia Progression Detection

Tripti Tripathi, Rakesh Kumar
Copyright: © 2022 |Volume: 14 |Issue: 1 |Pages: 18
ISSN: 1942-9045|EISSN: 1942-9037|EISBN13: 9781683181019|DOI: 10.4018/IJSSCI.312553
Cite Article Cite Article

MLA

Tripathi, Tripti, and Rakesh Kumar. "Performance Comparison of Machine Learning Algorithms for Dementia Progression Detection." IJSSCI vol.14, no.1 2022: pp.1-18. http://doi.org/10.4018/IJSSCI.312553

APA

Tripathi, T. & Kumar, R. (2022). Performance Comparison of Machine Learning Algorithms for Dementia Progression Detection. International Journal of Software Science and Computational Intelligence (IJSSCI), 14(1), 1-18. http://doi.org/10.4018/IJSSCI.312553

Chicago

Tripathi, Tripti, and Rakesh Kumar. "Performance Comparison of Machine Learning Algorithms for Dementia Progression Detection," International Journal of Software Science and Computational Intelligence (IJSSCI) 14, no.1: 1-18. http://doi.org/10.4018/IJSSCI.312553

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Dementia is a neurological disease that that encompasses a wide range of conditions like verbal communication, problem-solving, and other judgment abilities that are severely sufficient to interfere with daily life. It is among the leading causes of vulnerability among the elderly all over the world. A considerable amount of research has been conducted in this area so that we can perform early detection of the disease, yet further research into its betterment is still an emerging trend. This article compares the performance of multiple machine learning models for dementia detection and classification using brain MRI data, including support vector machine, random forest, AdaBoost, and XGBoost. Meanwhile, the research conducts a systematic assessment of papers for the clinical categorization of dementia using ML algorithms and neuroimaging data. The authors used 373 participants from the OASIS database. Among the tested models, RF model exhibited the best performance with 83.92% accuracy, 87.5% precision, 81.67% recall, 84.48% F1-score, 81.67% sensitivity, and 88.46% specificity.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.