TY - GEN
T1 - Early Screening of Mild Cognitive Impairment using Multimodal VR-EP-EEG-MRI (VEEM) Biomarkers via Machine Learning
AU - Kim, Se Young
AU - Park, Bogyeom
AU - Kim, Dohyun
AU - Choi, Hojin
AU - Park, Jinseok
AU - Ryu, Hokyoung
AU - Seo, Kyoungwon
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Alzheimer's disease
KW - Biomarkers
KW - Electroencephalogram
KW - Evoked potential
KW - Machine learning
KW - Magnetic resonance imaging
KW - Mild cognitive impairment
KW - Multimodal
KW - Virtual reality
UR - https://www.scopus.com/pages/publications/85189243084
U2 - 10.1109/ICEIC61013.2024.10457109
DO - 10.1109/ICEIC61013.2024.10457109
M3 - Conference contribution
AN - SCOPUS:85189243084
T3 - 2024 International Conference on Electronics, Information, and Communication, ICEIC 2024
BT - 2024 International Conference on Electronics, Information, and Communication, ICEIC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 International Conference on Electronics, Information, and Communication, ICEIC 2024
Y2 - 28 January 2024 through 31 January 2024
ER -