Early Detection of Cognitive Skill Impairments using Machine Learning

Cognitive skills are essential for everyday tasks, encompassing mental abilities such as memory, problem-solving, and logical thinking. Conditions such as depression, anxiety, and schizophrenia can impair these skills, affecting memory, attention, and problem-solving abilities. The COVID pandemic and other stress-inducing events have a great impact on individuals, often leading to stress-related diseases. Depression often stems from heightened stress levels, yet individuals may struggle to recognize or seek help due to social stigma. Delayed treatment impairs outcomes. Surveys indicate low success rates in treating cognitive skill impairment. Early identification through routine cognitive testing is crucial, especially for vulnerable individuals due to age, family history, or health conditions. Regular screenings facilitate proactive healthcare management, leading to improved outcomes in patients with cognitive skill impairments. This study explores the application of Support Vector Machine (SVM) algorithms for the early detection of cognitive skill impairments, aiming to develop accurate prediction models for identifying individuals at risk of cognitive decline. By employing feature selection methods, the SVM achieved an 83% accuracy rate. This study aimed to advance the development of efficient cognitive assessment tools, enabling early intervention and personalized care for individuals vulnerable to cognitive impairment.