Background: The population aging increased the prevalence of brain diseases, like Alzheimer's disease (AD). Early identification of individuals with higher odds of cognitive decline is essential to maintain quality of life. Imaging evaluation of individuals at risk of cognitive decline includes biomarkers extracted from brain positron emission tomography (PET) and structural magnetic resonance imaging (MRI).
Objective: We propose investigating ensemble models to classify groups in the aging cognitive decline spectrum by combining features extracted from single imaging modalities and combinations of imaging modalities (FDG+AMY+MRI, and a PET ensemble).
Methods: We group imaging data of 131 individuals into four classes related to the individuals' cognitive assessment in baseline and follow-up: stable cognitive non-impaired; individuals converting to mild cognitive impairment (MCI) syndrome; stable MCI; and Alzheimer's clinical syndrome. We assess the performance of four algorithms using leave-one-out cross-validation: decision tree classifier, random forest (RF), light gradient boosting machine (LGBM), and categorical boosting (CAT). The performance analysis of models is evaluated using balanced accuracy before and after using Shapley Additive exPlanations with recursive feature elimination (SHAP-RFECV) method.
Results: Our results show that feature selection with CAT or RF algorithms have the best overall performance in discriminating early cognitive decline spectrum mainly using MRI imaging features.
Conclusion: Use of CAT or RF algorithms with SHAP-RFECV shows good discrimination of early stages of aging cognitive decline, mainly using MRI image features. Further work is required to analyze the impact of selected brain regions and their correlation with cognitive decline spectrum.
Keywords: Aging; amyloid; atrophy; fluorodeoxyglucose F18; machine learning; multimodal imaging.