Combining Blood-Based Biomarkers and Structural MRI Measurements to Distinguish Persons With and Without Significant Amyloid Plaques

Abstract

BackgroundAmyloid-{beta} (A{beta}) plaques play a pivotal role in Alzheimers disease. The current positron emission tomography (PET) is expensive and limited in availability. In contrast, blood-based biomarkers (BBBMs) show potential for characterizing A{beta} plaques more affordably. We have previously proposed an MRI-based hippocampal morphometry measure to be an indicator of A{beta}-plaques. ObjectiveTo develop and validate an integrated model to predict brain amyloid PET positivity combining MRI feature and plasma A{beta}42/40 ratio. MethodsWe extracted hippocampal multivariate morphometry statistics (MMS) from MR images and together with plasma A{beta}42/40 trained a random forest classifier to perform a binary classification of participant brain amyloid PET positivity. We evaluated the model performance using two distinct cohorts, one from the Alzheimers Disease Neuroimaging Initiative (ADNI) and the other from the Banner Alzheimers Institute (BAI), including prediction accuracy, precision, recall rate, F1 score and AUC score. ResultsResults from ADNI (mean age 72.6, A{beta}+ rate 49.5%) and BAI (mean age 66.2, A{beta}+ rate 36.9%) datasets revealed the integrated multimodal (IMM) models superior performance over unimodal models. The IMM model achieved prediction accuracies of 0.86 in ADNI and 0.92 in BAI, surpassing unimodal models based solely on structural MRI (0.81 and 0.87) or plasma A{beta}42/40 (0.73 and 0.81) predictors. ConclusionOur IMM model, combining MRI and BBBM data, offers a highly accurate approach to predict brain amyloid PET positivity. This innovative multiplex biomarker strategy presents an accessible and cost-effective avenue for advancing Alzheimers disease diagnostics, leveraging diverse pathologic features related to A{beta} plaques and structural MRI.