Primary Progressive Aphasia (PPA) refers to a group of clinical syndromes caused by a neurodegenerative disease and is categorized into 3 types: APP-S, APP-NF/A, and APP-L. The Grammar Reception Test, in the Brazilian version (TROG2-Br), which focuses on the detection of problems in the Portuguese-Brazilian language, was used in individuals with PPA. The objective of this work is to show the feasibility of using Machine Learning algorithms to classify APP types, based on the individual's performance in the TROG-Br test. For this, the algorithms of Decision Tree, Naive Bayes, kNN, and SVM are applied and evaluated. The results are promising and show that it is possible to classify the types of APP using the individual's performance in the TROG-Br test as predictive attributes.
In old age, a series of common health conditions, chronic diseases, and disabilities affect the individual's physical and mental health and prevent the performing of Activities of Daily Living. This paper presents a solution to identify abnormalities in the behavior of the elderly based on ADL (Activities of Daily Living), using Machine Learning, through the Novelty Detection technique. The ADL data were used to create a model that defines the baseline behavior of the elderly, and new observations, to verify significant changes in behavior, are classified as discrepant or abnormal. The Local Outlier Factor, One-class Vector Machine, Robust Covariance, and Isolation Forest novelty detection algorithms were used and evaluated. The model presented reached an accuracy and F1-Score of 96%.
According to estimates by Alzheimer's Disease International, approximately 1.2 million people in Brazil live with some form of dementia and 100,000 new cases are diagnosed each year. Worldwide, the number reaches 50 million people, and the numbers could reach 74.7 million in 2030 and 131.5 million in 2050 due to an aging population. This scenario shows that the disease characterizes a global health crisis that must be faced. In this context, the article presents the solutions proposed by the academy in recent years according to systematic literature mapping and seeks to encourage scientists and researchers to dedicate efforts to this important topic.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.