{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T17:31:42Z","timestamp":1781890302798,"version":"3.54.5"},"reference-count":24,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Brain Sciences"],"abstract":"<jats:p>Background: Imaging-transcriptomic analysis, through the integration of multimodal magnetic resonance imaging (MRI) and transcriptomic data, provides complementary structural, functional, and molecular information that is crucial for the early detection and mechanistic exploration of Alzheimer\u2019s disease (AD). However, effectively extracting features from heterogeneous multimodal data and capturing the associations between microscopic molecular variations and macroscopic brain alterations remain key challenges. Recent advances in deep learning and multimodal integration have enhanced the ability to model nonlinear cross-modal relationships, enabling more accurate identification of imaging-transcriptomic biomarkers and subtypes. Developing robust multimodal frameworks is therefore essential for early AD detection, subtype identification, and advancing precision medicine in neurodegenerative diseases. Methods: In this study, a two-stage method of multimodal Feature Extraction based on Association Analysis and Graph Convolutional Network with Self-Attention and Self-Expression framework (MFEAA-GCNSASE) for early diagnosis of AD and effective identification of subtypes of MCI with different progression to AD is proposed. In the first stage, the MFEAA model is applied to integrate multiple association analysis methods on sMRI, PET, and transcriptomic data to identify key multimodal biomarkers for AD and mild cognitive impairment (MCI). In the second stage, the GCNSASE model enhances classification accuracy between AD and MCI patients through self-attention and self-expression layers. Additionally, unsupervised clustering was performed on MCI samples using top multimodal biomarkers to explore subtype heterogeneity and conversion risk. Reliable MCI subtypes were also identified through a consensus clustering approach. Results: The proposed algorithm integrates sMRI, PET, and transcriptomic data, identifying robust biomarkers including the Left Hippocampus, Left Angular Gyrus, and key genes such as SLC25A5 and GABARAP. To ensure statistical robustness given the extreme class imbalance, we employed a rigorous repeated stratified cross-validation (RSCV) framework. GCNSASE achieved state-of-the-art discrimination performance with mean AUC values ranging from 0.946 to 0.961 across feature subsets (10\u201350%), significantly outperforming MOGONET (mean AUC: 0.844\u20130.875, p &lt; 0.001) and conventional machine learning models with tighter 95% confidence intervals, indicating superior stability despite the limited AD sample size. Clustering analysis revealed two distinct MCI subtypes with divergent molecular landscapes: Subtype A was enriched in energy metabolism and cellular maintenance pathways, whereas Subtype B was enriched in neuroinflammatory and aberrant signaling pathways. Notably, the majority of MCI patients who subsequently converted to AD were concentrated in the immune-inflammatory Subtype B. These findings highlight that neuroinflammation coupled with bioenergetic failure constitutes a critical mechanism driving the conversion from MCI to AD. Conclusions: The proposed methods not only provide the key multimodal biomarkers and enhance the accuracy of the classification model for early AD diagnosis but also identify biologically and clinically meaningful MCI subtypes with distinct molecular signatures and conversion risks. Exploring these associated multimodal biomarkers and MCI subtypes is of great significance, as they help elucidate the heterogeneous mechanisms underlying AD onset and progression, enable the identification of high-risk individuals likely to convert to AD, and provide a foundation for targeted therapeutic strategies and individualized clinical management. These findings have important implications for understanding disease heterogeneity, discovering potential intervention targets, and advancing precision medicine in neurodegenerative diseases.<\/jats:p>","DOI":"10.3390\/brainsci16030255","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T10:59:16Z","timestamp":1772017156000},"page":"255","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Two-Stage Framework for Early Detection and Subtype Identification of Alzheimer\u2019s Disease Through Multimodal Biomarker Extraction and Improved GCN"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3139-6039","authenticated-orcid":false,"given":"Junshuai","family":"Li","sequence":"first","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, 1550 Haigang Ave., Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6554-4338","authenticated-orcid":false,"given":"Wei","family":"Kong","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, 1550 Haigang Ave., Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaiqun","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, 1550 Haigang Ave., Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1038\/s41572-021-00269-y","article-title":"Alzheimer disease","volume":"7","author":"Knopman","year":"2021","journal-title":"Nat. Rev. Dis. Prim."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.biopsych.2016.12.030","article-title":"Imaging Genetics and Genomics in Psychiatry: A Critical Review of Progress and Potential","volume":"82","author":"Bogdan","year":"2017","journal-title":"Biol. Psychiatry"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1093\/procel\/pwae026","article-title":"Alzheimer\u2019s disease: Insights into pathology, molecular mechanisms, and therapy","volume":"16","author":"Zheng","year":"2025","journal-title":"Protein Cell"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2551","DOI":"10.1001\/jama.2014.13806","article-title":"The diagnosis and management of mild cognitive impairment: A clinical review","volume":"312","author":"Langa","year":"2014","journal-title":"JAMA"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"151","DOI":"10.3233\/JAD-220471","article-title":"Real-World Use of Symptomatic Treatments in Early Alzheimer\u2019s Disease","volume":"91","author":"Garcia","year":"2023","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.gpb.2023.03.005","article-title":"inMTSCCA: An Integrated Multi-task Sparse Canonical Correlation Analysis for Multi-omic Brain Imaging Genetics","volume":"21","author":"Du","year":"2023","journal-title":"Genom. Proteom. Bioinform."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1109\/TCBB.2019.2947428","article-title":"Multi-Task Sparse Canonical Correlation Analysis with Application to Multimodal Brain Imaging Genetics","volume":"18","author":"Du","year":"2021","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1109\/TBME.2022.3203152","article-title":"Identifying Modality-Consistent and Modality-Specific Features via Label-Guided Multi-Task Sparse Canonical Correlation Analysis for Neuroimaging Genetics","volume":"70","author":"Hao","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1093\/biostatistics\/kxp008","article-title":"A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis","volume":"10","author":"Witten","year":"2009","journal-title":"Biostatistics"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102003","DOI":"10.1016\/j.media.2021.102003","article-title":"The Alzheimer\u2019s Disease Neuroimaging Initiative. Identifying associations among genomic, proteomic and imaging biomarkers via adaptive sparse multi-view canonical correlation analysis","volume":"70","author":"Du","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.pscychresns.2015.08.014","article-title":"Neuroimaging of hippocampal atrophy in early recognition of Alzheimer\u2019s disease\u2014A critical appraisal after two decades of research","volume":"247","author":"Pantel","year":"2016","journal-title":"Psychiatry Res. Neuroimaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1016\/S1474-4422(17)30343-5","article-title":"Pathology and hippocampal atrophy in Alzheimer\u2019s disease","volume":"16","author":"Halliday","year":"2017","journal-title":"Lancet Neurol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"fcae199","DOI":"10.1093\/braincomms\/fcae199","article-title":"Atypical intrinsic neural timescale in the left angular gyrus in Alzheimer\u2019s disease","volume":"6","author":"Murai","year":"2024","journal-title":"Brain Commun."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2267","DOI":"10.1111\/cns.14177","article-title":"Multi-networks connectivity at baseline predicts the clinical efficacy of left angular gyrus-navigated rTMS in the spectrum of Alzheimer\u2019s disease: A sham-controlled study","volume":"29","author":"Chen","year":"2023","journal-title":"CNS Neurosci. Ther."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.mam.2012.05.006","article-title":"The mitochondrial ADP\/ATP carrier (SLC25 family): Pathological implications of its dysfunction","volume":"34","author":"Babot","year":"2013","journal-title":"Mol. Asp. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1038\/s41467-020-20624-z","article-title":"Structural basis of GABA-RAP-mediated GABAA receptor trafficking and functions on GABAergic synaptic transmission","volume":"12","author":"Ye","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/S0925-4439(00)00039-9","article-title":"Role of the proteasome in Alzheimer\u2019s disease","volume":"1502","author":"Checler","year":"2000","journal-title":"Biochim. Biophys. Acta"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/s13195-023-01205-w","article-title":"Uncovering heterogeneous cognitive trajectories in mild cognitive impairment: A data-driven approach","volume":"15","author":"Wang","year":"2023","journal-title":"Alzheimer\u2019s Res. Ther."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.neuroscience.2024.11.056","article-title":"Risk factors and predictive models in the progression from MCI to Alzheimer\u2019s disease","volume":"565","author":"Li","year":"2025","journal-title":"Neuroscience"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Han, J., Zhang, Z., Zhang, P., Yu, Q., Cheng, Q., Lu, Z., and Zong, S. (2025). The roles of microglia and astrocytes in neuroinflammation of Alzheimer\u2019s disease. Front. Neurosci., 19.","DOI":"10.3389\/fnins.2025.1575453"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"112936","DOI":"10.1016\/j.intimp.2024.112936","article-title":"Targeting STAT3 signaling pathway in the treatment of Alzheimer\u2019s disease with compounds from natural products","volume":"141","author":"Wen","year":"2024","journal-title":"Int. Immunopharmacol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"105311","DOI":"10.1016\/j.neuint.2022.105311","article-title":"mTOR signaling as a molecular target for the alleviation of Alzheimer\u2019s disease pathogenesis","volume":"155","author":"Rapaka","year":"2022","journal-title":"Neurochem. Int."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Subramanian, A., Tamilanban, T., Alsayari, A., Ramachawolran, G., Wong, L.S., Sekar, M., Gan, S.H., Subramaniyan, V., Chinni, S.V., and Izzati Mat Rani, N.N. (2022). Trilateral association of autophagy, mTOR and Alzheimer\u2019s disease: Potential pathway in the development for Alzheimer\u2019s disease therapy. Front. Pharmacol., 13.","DOI":"10.3389\/fphar.2022.1094351"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102713","DOI":"10.1016\/j.arr.2025.102713","article-title":"Mitochondrial dysfunction in Alzheimer\u2019s disease","volume":"107","author":"Kanaan","year":"2025","journal-title":"Ageing Res. Rev."}],"container-title":["Brain Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3425\/16\/3\/255\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T11:24:18Z","timestamp":1772018658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3425\/16\/3\/255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,25]]},"references-count":24,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["brainsci16030255"],"URL":"https:\/\/doi.org\/10.3390\/brainsci16030255","relation":{},"ISSN":["2076-3425"],"issn-type":[{"value":"2076-3425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,25]]}}}