Dementia Identification Using Machine Learning Algorithms: Comparative Analysis

Dementia is a neurocognitive condition that affects individuals in its early stages. Memory loss, abnormal behavior, and linguistic differences are all symptoms of this condition, which is why timely identification is critical for the development of more improved treatments. Machine learning (ML), a subset of Artificial Intelligence (AI), employs multiple statistical and computational strategies to assist machines in learning from large and complex data sets. ML is commonly used by researchers to diagnose dementia in its initial phases. In the proposed work, various ML algorithms are applied to the publically available dementia dataset. It provides a broad overview of current research for the diagnosis of dementia. By analyzing different ML algorithms like Logistic Regression, K-Nearest Neighbors, Decision Tree, and Random Forest, it is observed that the Random Forest algorithm proves to be more accurate with a mean accuracy of 93.7% and therefore can be easily used with large datasets. As per our knowledge, this is one of a kind of work at the present state of study.