Academic Journal
Classification of depressed and non-depressed MCI and non-depressed cognitively normal individuals using resting-state metrics: A multi-group study with machine learning and graph reinforcement learning.
| Τίτλος: | Classification of depressed and non-depressed MCI and non-depressed cognitively normal individuals using resting-state metrics: A multi-group study with machine learning and graph reinforcement learning. |
|---|---|
| Συγγραφείς: | Ma H; School of Information and Electronics Technology, Jiamusi University, Jiamusi, 154007, China. Electronic address: mahuibin@jmsu.edu.cn., Song J; School of Information and Electronics Technology, Jiamusi University, Jiamusi, 154007, China. Electronic address: 238103005@stu.jmsu.edu.cn., Xue X; School of Foreign Studies, China University of Petroleum (East China), Qingdao, 266580, China. Electronic address: B24170003@s.upc.edu.cn., Wu J; School of Information and Electronics Technology, Jiamusi University, Jiamusi, 154007, China. Electronic address: 238103012@stu.jmsu.edu.cn., Zhang H; School of Medical Imaging, Shandong Second Medical University, Weifang, 261053, China. Electronic address: zy2206108@buaa.edu.cn., Fu B; School of Foreign Studies, China University of Petroleum (East China), Qingdao, 266580, China. Electronic address: fubingqi@s.upc.edu.cn., Hao Z; School of Psychology, Zhejiang Normal University, Jinhua, 321004, China. Electronic address: serenity@zjnu.edu.cn., Yu Y; Psychiatry Department, The Second Affiliated Hospital Zhejiang University School of Medicine, Zhejiang, Hangzhou, 310009, China. Electronic address: yuyang1023@zju.edu.cn., Cheng L; School of Foreign Studies, China University of Petroleum (East China), Qingdao, 266580, China. Electronic address: cll@upc.edu.cn., Li M; School of Psychology, Zhejiang Normal University, Jinhua, 321004, China. Electronic address: limengting1108@zjnu.edu.cn., Jia X; School of Psychology, Zhejiang Normal University, Jinhua, 321004, China; Intelligent Laboratory of Zhejiang Province in Mental Health and Crisis Intervention for Children and Adolescents, Zhejiang Normal University, Jinhua, 321004, China. Electronic address: jiaxize@zjnu.edu.cn. |
| Πηγή: | Journal of affective disorders [J Affect Disord] 2026 Aug 01; Vol. 406, pp. 121719. Date of Electronic Publication: 2026 Apr 01. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Elsevier/North-Holland Biomedical Press Country of Publication: Netherlands NLM ID: 7906073 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1573-2517 (Electronic) Linking ISSN: 01650327 NLM ISO Abbreviation: J Affect Disord Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Amsterdam, Elsevier/North-Holland Biomedical Press. |
| Ιατρικοί όροι (MeSH): | Cognitive Dysfunction*/classification , Cognitive Dysfunction*/physiopathology , Cognitive Dysfunction*/diagnostic imaging , Cognitive Dysfunction*/psychology , Depression*/physiopathology , Depression*/diagnostic imaging , Depression*/classification , Brain*/physiopathology , Brain*/diagnostic imaging , Machine Learning*, Magnetic Resonance Imaging/methods ; Brain Mapping/methods ; Cerebral Cortex/physiopathology ; Cerebral Cortex/diagnostic imaging ; Humans ; Female ; Reinforcement Machine Learning ; Male ; Aged ; Graph Neural Networks |
| Περίληψη: | Depressive symptoms frequently co-occur in individuals with Mild Cognitive Impairment (MCI) and are thought to accelerate neurodegenerative progression. However, the underlying neural mechanisms of Depressed MCI (DMCI) remain largely unclear. This study employed a multimodal resting-state functional magnetic resonance imaging (rs-fMRI) approach combined with advanced machine learning techniques, to systematically examine spontaneous brain activity patterns and topological organization differences among DMCI, non-depressed MCI (nDMCI), and non-depressed cognitively normal controls (nDCN). The research analyzed amplitude-based rs-fMRI measures and graph-theoretical features. Voxel-wise analyses and connectivity comparisons were conducted between groups. Additionally, classification tasks were performed using classical machine learning models and a graph reinforcement learning (GRL) model. DMCI individuals exhibited increased activity in the right insula and decreased amplitude of low-frequency fluctuation (ALFF) in the left calcarine cortex, along with heightened fractional ALFF (fALFF) and percent amplitude of fluctuation (PerAF) in the precuneus and parahippocampal regions. Graph metrics revealed disrupted global and local efficiency in nDMCI compared to nDCN. Using differential matrices, machine learning achieved optimal accuracies of 0.82 ± 0.15 (DMCI vs. nDMCI) and 0.84 ± 0.15 (DMCI vs. nDCN). Conversely, the GRL model for nDMCI vs. nDCN peaked at 0.66 ± 0.02 using full matrices, dropping to 0.60 ± 0.04 with filtering, indicating deep graph models require complete topological data for subtle differences. Rs-fMRI and graph learning approaches offer promising avenues for subtype classification, highlighting the hyperactivity of the right insula and the integrity of the whole-brain functional connectivity matrix as crucial potential biomarkers of early pathological changes. (Copyright © 2026 Elsevier B.V. All rights reserved.) |
| Competing Interests: | Declaration of competing interest The authors declared that this research has no financial conflicts of interest. |
| Contributed Indexing: | Keywords: Depressed mild cognitive impairment (DMCI); Functional connectivity; Graph reinforcement learning (GRL); Graph theory; Non-depressed mild cognitive impairment (nDMCI) |
| Entry Date(s): | Date Created: 20260404 Date Completed: 20260714 Latest Revision: 20260714 |
| Update Code: | 20260714 |
| DOI: | 10.1016/j.jad.2026.121719 |
| PMID: | 41933620 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!