Multimodal ensemble model for Alzheimer's disease conversion prediction from Early Mild Cognitive Impairment subjects

Abstract

Alzheimer's Disease (AD) is the most common type of dementia. Predicting the conversion to Alzheimer's from the mild cognitive impairment (MCI) stage is a complex problem that has been studied extensively. This study centers on individualized EMCI (the earliest MCI subset) to AD conversion prediction on multimodal data such as diffusion tensor imaging (DTI) scans and electronic health records (EHR) for their patients using the combination of both a balanced random forest model alongside a convolutional neural network (CNN) model. Our random forest model leverages EHR's patient biometric and neuropsychiatric test score features, while our CNN model uses the patient's diffusion tensor imaging (DTI) scans for conversion prediction. To accomplish this, 383 Early Mild Cognitive Impairment (EMCI) patients were collected from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Within this set, 49 patients would eventually convert to AD (EMCI_C), whereas the remaining 335 did not convert (EMCI_NC). For the EHR-based classifier, 288 patients were used to train the random forest model, with 95 set aside for testing. For the CNN classifier, 405 DTI images were collected across 90 distinct patients. Nine clinical features were selected to be combined with the visual predictor. Due to the imbalanced classes, oversampling was performed for the clinical features and augmentation for the DTI images. A grid search algorithm is also used to determine the ideal weighting between our two models. Our results indicate that an ensemble model was effective (98.81% accuracy) at EMCI to AD conversion prediction. Additionally, our ensemble model provides explainability as feature importance can be assessed at both the model and individual prediction levels. Therefore, this ensemble model could serve as a diagnostic support tool or a means for identifying clinical trial candidates.