Open AccessPredicting Aphasia from Strokes
Author(s) -
Joseph Jia,
Joanna Gilberti
Publication year - 2021
Publication title -
journal of student research
Language(s) - English
Resource type - Journals
ISSN - 2167-1907
DOI - 10.47611/jsrhs.v10i3.1535
Subject(s) - aphasia , lesion , stroke (engine) , linear discriminant analysis , medicine , psychology , physical medicine and rehabilitation , surgery , artificial intelligence , computer science , psychiatry , mechanical engineering , engineering
Strokes can occur when someone’s blood vessels get blocked and the nutrients and oxygen being transported will not reach the brain. When a stroke happens, the brain cells don’t get the nutrients they need and start to die [3]. This could cause different side effects after stroke. In this study, we try to predict the possibility of one type of after-stroke side effect, aphasia, using Machine Learning (ML) techniques. Using the data of a study about brain lesion damage after a stroke and what effects the patients were experiencing afterward, we trained a model to predict whether a person may have aphasia based on where their lesion was, how big the lesion was, how long ago their stroke was, and some other factors. We evaluated several classification methods and found that using linear discriminant analysis was the most accurately predicting when we used age, sex, lesion location, lesion volume, and many more. By linear discriminant analysis, we were able to have a 91% overall predictive rate of patients having aphasia or not after experiencing a stroke.