A hybrid multimodal machine learning model for Detecting Alzheimer's disease

• Published in: Computers in biology and medicine Vol. 170; p. 108035
• Main Authors: Sheng, Jinhua, Zhang, Qian, Zhang, Qiao, Wang, Luyun, Yang, Ze, Xin, Yu, Wang, Binbing
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2024; Elsevier Limited
• Subjects: Accuracy; Algorithms; Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Anatomy; Artificial intelligence; Artificial neural networks; Biomarkers; Brain mapping; Brain research; Cerebrospinal fluid; Classification; Cognitive ability; Cognitive Dysfunction - diagnosis; Comparative analysis; Deep learning; Dementia; Diagnosis; Feature selection; Harris hawks optimization; Heuristic methods; Humans; Internal Medicine; Iterative methods; Kernel extreme learning machine; Learning algorithms; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Multimodality; Neural networks; Neurodegenerative diseases; Neuroimaging; Neuroimaging - methods; Operators (mathematics); Optimization; Optimization techniques; Other; Positron emission; Positron emission tomography; Positron-Emission Tomography - methods; Support vector machines; Multimodality; Alzheimer's disease; Machine learning; Kernel extreme learning machine; Harris hawks optimization
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108035

Alzheimer's disease (AD) diagnosis utilizing single modality neuroimaging data has limitations. Multimodal fusion of complementary biomarkers may improve diagnostic performance. This study proposes a multimodal machine learning framework integrating magnetic resonance imaging (MRI), positron emission tomography (PET) and cerebrospinal fluid (CSF) assays for enhanced AD characterization. The model incorporates a hybrid algorithm combining enhanced Harris Hawks Optimization (HHO) algorithm referred to as ILHHO, with Kernel Extreme Learning Machine (KELM) classifier for simultaneous feature selection and classification. ILHHO enhances HHO's search efficiency by integrating iterative mapping (IM) to improve population diversity and local escaping operator (LEO) to balance exploration-exploitation. Comparative analysis with other improved HHO algorithms, classic meta-heuristic algorithms (MHAs), and state-of-the-art MHAs on IEEE CEC2014 benchmark functions indicates that ILHHO achieves superior optimization performance compared to other comparative algorithms. The synergistic ILHHO-KELM model is evaluated on 202 AD Neuroimaging Initiative (ADNI) subjects. Results demonstrate superior multimodal classification accuracy over single modalities, validating the importance of fusing heterogeneous biomarkers. MRI + PET + CSF achieves 99.2 % accuracy for AD vs. normal control (NC), outperforming conventional and proposed methods. Discriminative feature analysis provides further insights into differential AD-related neurodegeneration patterns detected by MRI and PET. The differential PET and MRI features demonstrate how the two modalities provide complementary biomarkers. The neuroanatomical relevance of selected features supports ILHHO-KELM's potential for extracting sensitive AD imaging signatures. Overall, the study showcases the advantages of capitalizing on complementary multimodal data through advanced feature learning techniques for improving AD diagnosis. •We propose ILHHO as an enhanced Harris Hawks Optimization (HHO) algorithm for improving original HHO through IM and LEO mechanisms.•ILHHO-KELM is proposed to improve AD detection by integrating MRI, PET and CSF data.•ILHHO demonstrates significantly better optimization performance over other algorithms.•The performance of multimodal classification outperforms single modalities, confirming the importance of complementing biomarkers.