Prediction of Neuro Cognitive Disorders using Supervised Comparative Machine Learning Model & Scanpath Representations

Abstract

Dementia has become a pressing public health issue worldwide, with the number of affected individuals steadily increasing. As a syndrome, it is characterized by a decline in cognitive performance that extends beyond normal biological aging, caused by a diverse range of brain disorders and diseases. Alzheimer’s disease is the most prevalent form of dementia, and it constitutes the majority of dementia cases. In addition to its physical and psychological impacts, dementia is also a significant economic burden on families and society at large, given the extensive care required. One potential approach to understanding the cognitive performance of individuals with dementia is the use of scan path representations. A scan path is a visual representation of eye movements and is created by an ordered set of fixations connected by saccades. By analyzing these patterns, researchers aim to better understand the visual behaviors of people with dementia and potentially develop more effective treatment options. To achieve this goal, the proposed supervised comparative machine learning model utilizes scan path representations to provide a more comprehensive understanding of dementia. By exploring the visual behaviors of individuals with the condition, the model aims to provide insights into the use of supervised machine learning algorithms in trail making tests to better classify the dementia patients using their scanpath representations. This research paper aims to contribute to the ongoing efforts to combat the global challenge of dementia and provide a more nuanced understanding of the condition.