Predicting Alzheimer’s Disease Conversion From Mild Cognitive Impairment Using an Extreme Learning Machine-Based Grading Method With Multimodal Data

Abstract

Identifying patients with mild cognitive impairment (MCI) who are at high risk of progressing to Alzheimer's disease (AD) is crucial for early treatment of AD. However, it is difficult to predict the cognitive states of patients. This study developed an extreme learning machine (ELM)-based grading method to efficiently fuse multimodal data and predict MCI-to-AD conversion. First, features were extracted from magnetic resonance (MR) images, and useful features were selected using a feature selection method. Second, multiple modalities of MCI subjects, including MRI, positron emission tomography, cerebrospinal fluid biomarkers, and gene data, were individually graded using the ELM method. Finally, these grading scores calculated from different modalities were fed into a classifier to discriminate subjects with progressive MCI from those with stable MCI. The proposed approach has been validated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, and an accuracy of 84.7% was achieved for an AD prediction within 3 years. Experiments on predicting AD conversion from MCI within different periods showed similar results with the 3-year prediction. The experimental results demonstrate that the proposed approach benefits from the efficient fusion of four modalities, resulting in an accurate prediction of MCI-to-AD conversion.

Prediction of Alzheimer’s Disease Progression Based on Magnetic Resonance Imaging

“…The combination of cognitive scores and MRI biomarkers helps to accurately predict the year of dementia before it occurs. Lin et al 23 proposed an ELM-based grading method to individually grade multiple modalities of MCI subjects, including sMRI, positron emission tomography (PET), CSF biomarkers, and gene data. The grading scores were fed into the classifier to discriminate the progression of MCI for sMCI patients.…”

Artificial Intelligence for Alzheimer’s Disease: Promise or Challenge?

“…Therefore, it is not surprising for an AI model to solve the task of AD vs. NC subject classification with high accuracy, when taking into account NPS test results or neuroimaging data [55]. To date, several predictive models have been developed [55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72], yielding peak accuracy values of 100% in AD vs. NC classification [55]. In contrast, a much more challenging task for AI is to identify individuals with subjective or mild impairment who will develop AD dementia, with respect to stable MCI or MCI not due to AD, given the shaded differences and the overlapping symptoms in the clinical or biological variables defining these groups in the early phases [73].…”

“…For example, the integration of MRI with multiple modality data, such as PET, CSF biomarkers, and genomic data, reached 84.7% accuracy in an MCI-c vs. MCI-nc classification task. When only single-modality data was used, the accuracy of the model was lower than the all-modalities implementation [64]. Different data modalities reflect the AD-related pathological markers that are complementary to each other, which can be concatenated as multi-modal features as input to an ML model for classification [75][76][77].…”

Multimodal Classification: Current Landscape, Taxonomy and Future Directions

“…[52] also used SVMs for feature extraction and classification for predicting clinical pain states using brain imaging and heart rate data. To differentiate between healthy patients and those with either Alzheimer's disease or mild cognitive impairment, [61] developed a predictive model using MRI, fluorodeoxyglucose positron emission tomography (FDG-PET), cerebrospinal fluid (CSF), and apolipoprotein E (APOE) 𝜖4 gene data. Unlike the previous two methods, this model used the ELM classifier [40] which is a variant of the traditional SVM algorithm.…”