Machine Learning for the Prediction of Amyloid Positivity in Amnestic Mild Cognitive Impairment

Abstract

Background: Amyloid-beta (A beta) evaluation in amnestic mild cognitive impairment (aMCI) patients is important for predicting conversion to Alzheimer's disease. However, A beta evaluation through A beta positron emission tomography (PET) is limited due to high cost and safety issues. Objective: We therefore aimed to develop and validate prediction models of A beta positivity foraMCIusing optimal interpretable machine learning (ML) approaches utilizing multimodal markers. Methods: We recruited 529 aMCI patients from multiple centers who underwent A beta PET. We trained ML algorithms using a training cohort (324 aMCI from Samsung medical center) with two-phase modelling: model 1 included age, gender, education, diabetes, hypertension, apolipoprotein E genotype, and neuropsychological test scores; model 2 included the same variables as model 1 with additional MRI features. We used four-fold cross-validation during the modelling and evaluated the models on an external validation cohort (187 aMCI from the other centers). Results: Model 1 showed good accuracy (area under the receiver operating characteristic curve [AUROC] 0.837) in crossvalidation, and fair accuracy (AUROC0.765) in external validation. Model 2 led to improvement in the prediction performance with good accuracy (AUROC 0.892) in cross validation compared to model 1. Apolipoprotein E genotype, delayed recall task scores, and interaction between cortical thickness in the temporal region and hippocampal volume were the most important predictors of A beta positivity. Conclusion: Our results suggest that ML models are effective in predicting A beta positivity at the individual level and could help the biomarker-guided diagnosis of prodromal AD.