Amyloid PET-Positive Predictability of Machine Learning Algorithm Based on MDS-OAβ Levels

Abstract Background: The Multimer Detection System-Oligomeric amyloid-β (MDS-OAβ) level is a valuable blood-based biomarker for Alzheimer’s disease (AD). We used machine learning algorithms trained using multi-center datasets to examine whether blood MDS-OAβ values can predict AD-associated changes in the brain.Methods: A logistic regression model using TensorFlow (ver. 2.3.0) was applied to data obtained from 163 participants (amyloid positron emission tomography [PET]-positive and -negative findings in 102 and 61 participants, respectively). Algorithms with various combinations of features (MDS-OAβ levels, age, gender, and anticoagulant type) were tested 50 times on each dataset. Results: The predictive accuracy, sensitivity, and specificity values of blood MDS-OAβ levels for amyloid PET positivity were 78.16±4.97%, 83.87±9.40%, and 70.00±13.13%, respectively.Conclusions: The findings from this multi-center machine learning-based study suggest that MDS-OAβ values may be used to predict amyloid PET-positivity.