Prediction of amyloid PET positivity via machine learning algorithms trained with EDTA-based blood amyloid-beta oligomerization data

Abstract

Background The tendency of amyloid-beta to form oligomers in the blood as measured with Multimer Detection System-Oligomeric Amyloid-beta (MDS-OA beta) is a valuable biomarker for Alzheimer's disease and has been verified with heparin-based plasma. The objective of this study was to evaluate the performance of ethylenediaminetetraacetic acid (EDTA)-based MDS-OA beta and to develop machine learning algorithms to predict amyloid positron emission tomography (PET) positivity. Methods The performance of EDTA-based MDS-OA beta in predicting PET positivity was evaluated in 312 individuals with various machine learning models. The models with various combinations of features (i.e., MDS-OA beta level, age, apolipoprotein E4 alleles, and Mini-Mental Status Examination [MMSE] score) were tested 50 times on each dataset. Results The random forest model best-predicted amyloid PET positivity based on MDS-OA beta combined with other features with an accuracy of 77.14 +/- 4.21% and an F1 of 85.44 +/- 3.10%. The order of significance of predictive features was MDS-OA beta, MMSE, Age, and APOE. The Support Vector Machine using the MDS-OA beta value only showed an accuracy of 71.09 +/- 3.27% and F-1 value of 80.18 +/- 2.70%. Conclusions The Random Forest model using EDTA-based MDS-OA beta combined with the MMSE and apolipoprotein E status can be used to prescreen for amyloid PET positivity.