Beta‐amyloid regions related to amyloid positivity using a feature selection method

Background Cerebral beta-amyloid (Aβ) is a hallmark of AD. Few studies have revealed which the regional Aβ markers are associated with abnormal levels status. The aim current study was to identify multivariate predicting positivity (Aβ+). Method Seven hundred and sixty-five participants from ADNI-2 cohort at baseline visit were included in study. We used uptake as predictors predictive model. Flobetapir PET images classified Aβ-positive if standard value ratio over 1.1. least absolute shrinkage selection operator (LASSO) model 1,000 bootstrap implemented traits predict cortical amyloid burden participants. Result Out 116 predictors, 27 thickness significantly predicted Aβ+ among baseline. After bootstrapping, 2 phenotypes had 95% confidence intervals that did not overlap zero: left precuneus (β = 0.684) right rostral middle frontal region 0.605). Conclusion These results demonstrated several brain regions related cerebral Aβ. suggest robust sign may capture AD pathology. To this end, research supported by MSIT (Ministry Science ICT), Korea, under ITRC (Information Technology Research Center) support program (IITP-2022-2017-0-01630) supervised IITP (Institute for Information & communications Promotion).