Analysis of Dementia Prognostication Using Computational Models

Dementia is a progressive neurological condition characterized by a decline in cognitive function. Predicting dementia early offers numerous benefits by allowing for timely interventions and planning. Early diagnosis enables individuals to access treatments and support services, potentially slowing the disease's progression and improving their quality of life. Ultimately, early prediction enhances the overall well-being of individuals affected by this challenging condition. The focus of this investigation centers on the prediction of Dementia by employing a range of Machine Learning algorithms to identify the most suitable one for the task. The dataset employed encompasses 373 individual imaging sessions that were conducted on each patient, spanning a minimum of two visits with a time gap of at least one year between them. We applied algorithms both with and without ensemble techniques, namely the Light Gradient Boost machine, XG Boost Model, Random Forest, and the Support Vector Machine Model (SVM). Notably, the ensemble Gradient Boosting Model demonstrated the most promising performance, achieving an accuracy rate of 91.2%.