Effective Diagnosis of Alzheimer’s Disease via Multimodal Fusion Analysis Framework

Abstract

Alzheimer’s disease (AD) is a complex neurodegenerative disease involving a variety of pathogenic factors, and the etiology detection of this disease has been a major concern of researchers. Neuroimaging is a basic and important means to explore the problem. It is the main current scientific research direction for combining neuroimaging with other modal data to dig deep into the potential information of AD through the complementarities among multiple data points. Machine learning methods possess great potentiality and have reached some achievements in this research area. A few studies have proposed some solutions to the effects of multimodal data fusion, however, the overall analytical framework for data fusion and fusion result analysis has thus far been ignored. In this paper, we first put forward a novel multimodal data fusion method, and further present a new machine learning framework of data fusion, classification, feature selection, and disease-causing factor extraction. The real dataset of 37 AD patients and 35 normal controls (NC) with functional magnetic resonance imaging (fMRI) and genetic data was used to verify the effectiveness of the framework, which was more accurate in classification and optimal feature extraction than other methods. Furthermore, we revealed disease-causing brain regions and genes, such as the olfactory cortex, insula, posterior cingulate gyrus, lingual gyrus, CNTNAP2, LRP1B, FRMD4A, and DAB1. The results show that the machine learning framework could effectively perform multimodal data fusion analysis, providing new insights and perspectives for the diagnosis of Alzheimer’s disease.

Machine learning for the life-time risk prediction of Alzheimer’s disease: a systematic review

“…Bi et al 57 used an iterative process to determine the optimum number of decision trees to use in their RF approach. Furthermore, grid search and CV techniques were employed to optimize varying hyperparameters across the studies ( Supplementary Table 6 , last column).…”

A review of brain imaging biomarker genomics in Alzheimer’s disease: implementation and perspectives

“…Moreover, Bi et al . [ 158 ] combined fMRI and SNP data and used the multimodal RF algorithm to distinguish AD from normal control, and finally obtained AD prediction accuracy of 87%. Varol et al [ 159 ] proposed the heterogeneity through discriminative analysis (HYDRA) algorithm to predict AD based on combined sMRI and SNP data, with the highest AUC value being 0.942.…”

“…To distinguish between stable and progressive MCI, Dukart et al [157] used a plain Bayesian (naive Bayesian, NB) algorithm based on APOE genotype, neuropsychological assessment, sMRI, and FDG PET, achieving an accuracy of approximately 87%. Moreover, Bi et al [158] combined fMRI and SNP data and used the multimodal RF algorithm to distinguish AD from normal control, and finally obtained AD prediction accuracy of 87%. Varol et al [159] proposed the heterogeneity through discriminative analysis (HYDRA) algorithm to predict AD based on combined sMRI and SNP data, with the highest AUC value being 0.942.…”

Multimodal Brain Connectomics-Based Prediction of Parkinson’s Disease Using Graph Attention Networks

“…Neuroimaging studies have developed and employed machine learning frameworks for performing a brain connectome-based multimodal classification of the diseased population by fusing brain connectivity with a phenotypic score, a clinical variable, or a genetic marker ( Ingalhalikar et al, 2012 ; Calhoun and Sui, 2016 ; Bi et al, 2019 ; Markello et al, 2021 ). Recently, neuroimaging studies have begun exploring GNNs on multimodal brain connectomes by using structural and FC features together or in combination with a phenotypic score.…”