AI based Detection of Mild Cognitive Impairment (MCI)

Mild Cognitive Impairment (MCI) is an early stage of cognitive decline that has a potential for developing into dementia, including Alzheimer's disease (AD). Early and timely MCI detection is important in ensuring timely intervention and management. In this study, the use of multiple biomarkers and sophisticated machine learning (ML) methods for proper detection of MCI is investigated. Multimodal biomarkers such as cognitive test scores e.g., Mini Mental State Examination (MMSE) and other demographic factors were used to support diagnostic performance. Feature extraction and selection methods were employed in order to obtain the most informative biomarkers. The results enhance the accuracy of MCI detection and achieve state-of-the-art performance. Models such as Gradient Boosting provides improved balance and more applicable performance than other models such as Logistic Regression, XGBoost and Decision Trees This research presents the possibility of multimodal biomarkers with ML to construct solid, non-invasive methods for early detection of MCI, opening doors for personalized therapeutic interventions.