Diagnosis of Cognitive Impairment Using Egret Swarm Optimization

Parkinson’s, Alzheimer’s etc. neurodegenerative diseases are diseases with a very high prevalence rate that generally occur among the elderly. Neurodegenerative nerve diseases affect many activities of your body such as balance, movement, speech, breathing and heart function and one of its most evident symptoms is impaired handwriting, which is often the first sign of Parkinson’s disease. These diseases cannot be cured, but early detection can help better manage the symptoms and development of these diseases. Therefore, early diagnosis of these diseases is very important. Computer-assisted methods such as machine learning techniques and artificial intelligence have been widely used in the diagnosis of diseases today. Feature selection is also an important factor that increases performance in diagnosis with artificial intelligence. In this study, a study was carried out on the diagnosis of cognitive disorder by handwriting by using the features obtained by the feature selection method for the first time in the literature with the Egret Swarm Optimization algorithm in the classification process with the Support Vector Machine. Working codes were written in python programming language and 500 iterations were made. In the study, kfold was used for both feature reduction and validation. As a result of the study, the test success rate was 80%.