Early Screening of Mild Cognitive Impairment using Multimodal VR-EP-EEG-MRI (VEEM) Biomarkers via Machine Learning

This study introduces a novel multimodal biomarker approach for the early screening of mild cognitive impairment (MCI), integrating biomarkers from virtual reality (VR), evoked potential (EP), electroencephalogram (EEG), and magnetic resonance imaging (MRI). A total of 46 participants, including 21 healthy controls and 25 MCI patients, were recruited, and nine distinct biomarkers from VR, EP, EEG, and MRI were collected for each participant. These nine biomarkers showed significant differences between healthy controls and MCI patients. Leveraging a machine learning model trained on these multimodal biomarkers, the study achieved outstanding classification performance with 94.12% accuracy, 100.0% sensitivity, 88.89% specificity, 88.89% precision, and 94.12% F1-score. These results surpassed the performance of models using unimodal biomarkers from VR, EP, EEG, or MRI. The findings highlight the significance of employing multimodal VR-EP-EEG-MRI biomarkers in MCI screening and advocate for further research in this domain.