Abstract #2834

Combined Use of Gray Matter Volume and Quantitative Susceptibility Mapping to Predict Early Alzheimer’s Disease Using a Machine Learning-based Optimized Combination-Feature Set

Hyug-Gi Kim¹, Soonchan Park², Hak Young Rhee³, Kyung Mi Lee⁴, Chang-Woo Ryu², Soo Yeol Lee⁵, Seong Jong Yun², Eui Jong Kim⁴, Yi Wang⁶, Wook Jin², Dal Mo Yang², and Geon-Ho Jahng²

¹Biomedical Engineering, Graduate School, Kyung Hee University, Suwon, Korea, Republic of, ²Radiology, Kyung Hee University Hospital at Gangdong, Seoul, Korea, Republic of, ³Neurology, Kyung Hee University Hospital at Gangdong, Seoul, Korea, Republic of, ⁴Radiology, Kyung Hee University Hospital, Seoul, Korea, Republic of, ⁵Biomedical Engineering, College of Electronics & Information, Kyung Hee University, Suwon, Korea, Republic of, ⁶Biomedical Engineering and Radiology, Cornell University, New York, NY, United States

To investigate the approach of classification and prediction methods using the machine learning (ML)-based optimized combination-feature (OCF) set on gray matter volume (GMV) and QSM in elderly subjects with a cognitive normal (CN) profile, those with amnestic MCI (aMCI), and mild and moderate AD patients, GMV and QSM in the brain were calculated. To differentiate the three subject groups, the support vector machine (SVM) with the three different kernels and with the OCF set was conducted with GMV and QSM values. To predict the aMCI stage, regression-based ML models were developed with the OCF set.

This abstract and the presentation materials are available to members only; a login is required.

Join Here