Performance Study Of Machine Learning Algorithms Used For Alzheimer’s Disease Detection

Abstract

Dementia is widely recognized. With age comes a dramatic surge in dementia cases. It is an irreversible brain disorder that impairs thinking, memory, and judgment, causing a person’s cognitive ability to decline. Around 50 million individuals worldwide have dementia, and 10 million new cases are identified yearly. Therefore, solving this problem has become urgently necessary, and dementia must be diagnosed early for more advanced treatments to develop. Cognitive tests are used to assess a person’s mental capacity to diagnose this condition early. In the present study, we tried to detect dementia in its early stages using machine learning approaches. Data collected for the analysis comprised gender, age, education, MMSE (Mini‐Mental State Examination), CDR (Clinical Dementia Rating), ASF (Atlas scaling factor), handedness, and hospital visits for patients classified as demented or non-demented. We applied machine learning approaches such as KNN, DT (Decision Tree), and RF (Random Forest) classifiers to analyze the data. Each algorithm is compared in a study. The most accurate algorithm will be employed to continue examining the data. Our suggested study used an additional tree classifier for deeper data analysis.