Depression-Related Patterns Using Scaled Subprofile Model of Principal Component Analysis
Poster No:
503
Submission Type:
Abstract Submission
Authors:
Yue Yin1,2,3, Dan-Hui Chen1,2,3, Li-Hang Li1,2,3, Hong-Fei Zhang1,2,3, Qi-Qi Fu1,2,3, Yu-Feng Zang1,2,3, Na Zhao1,2,3
Institutions:
1Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University, Hangzhou, Zhejiang, China, 2Institutes of Psychological Sciences, Hangzhou Normal University, Hangzhou, Zhejiang, China, 3Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments, Hangzhou, Zhejiang, China
First Author:
Yue Yin
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Co-Author(s):
Dan-Hui Chen
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Li-Hang Li
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Hong-Fei Zhang
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Qi-Qi Fu
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Yu-Feng Zang
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Na Zhao
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Center for Cognition and Brain Disorders, the Affiliated Hospital of Hangzhou Normal University|Institutes of Psychological Sciences, Hangzhou Normal University|Zhejiang Key Laboratory for Research in Assessment of Cognitive Impairments
Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China|Hangzhou, Zhejiang, China
Introduction:
Major depressive disorder (MDD) is the second leading cause of disability worldwide, yet its pathophysiological mechanisms remain unclear, and objective biomarkers for clinical diagnosis are lacking. The Scaled Subprofile Model of Principal Component Analysis (SSM-PCA) united resting-state functional magnetic resonance imaging (RS-fMRI) metrics has been used to investigate the neuropsychiatric dysfunctions, such as Parkinson's disease, effectively distinguishing patients from healthy controls (HCs) (Tomše et al., 2017), but fewer studies have explored its application in MDD. Therefore, this study aims to: 1) apply SSM-PCA to identify MDD-related disease patterns based on RS-fMRI local activity metrics; 2) validate these patterns by distinguishing MDD patients from HCs; and 3) explore the correlation between these patterns and clinical measures for MDD.
Methods:
A dataset was obtained from the REST-meta-MDD which includes RS-fMRI data from 1,300 MDDs and 1,128 HCs (http://rfmri.org/REST-meta-MDD) (Yan et al., 2019). After excluding subjects with incomplete data, poor spatial normalization, insufficient brain coverage, excessive head motion, or those from sites with fewer than 10 subjects in either group, 848 MDDs and 794 HCs were included in the study. All data were preprocessed using DPABI (Yan & Zang, 2010) and SPM12 (https://www.fil.ion.ucl.ac.uk/spm/). Notably, analyses were performed both with and without global signal regression (GSR). Local activity metrics, i.e., Amplitude of Low Frequency Fluctuation (ALFF), Degree Centrality (DC), and Regional Homogeneity (ReHo), were calculated. ComBat, an empirical Bayesian estimation method was used to account for site-specific variability. Following that, SSM-PCA decomposes metric maps (i.e., ALFF, DC, and ReHo maps) from all subjects into orthogonal components, each representing a brain pattern, known as the Group Invariant Subprofile (GIS). The proportion of variance explained by each GIS is called Variance Accounting For (VAF). Moreover, the projection of each individual's metric map onto a particular pattern is termed the Subject Scaling Factor (SSF), reflecting the pattern's expression within the subject (Yuan et al., 2017). To compare group differences between MDDs and HCs, we conducted two-sample t-tests on the SSF values, considering patterns with p<0.05 to represent difference-related patterns. To ensure robustness, we employed leave-one-subject-out and leave-one-site-out cross-validation. Specifically, one subject or one site was removed at a time, and followed by a two-sample t-test on the remaining subjects to estimate the results. Finally, we calculated the Pearson correlation coefficients between the SSF values (p<0.05) and clinical scale scores of the Hamilton Depression Rating Scale (HAMD) and Hamilton Anxiety Rating Scale (HAMA).
Results:
The VAF values for ranging from GIS1 to GIS5 were relatively large across metrics (Figure 1A). Two-sample t-tests on the SSF values for MDDs and HCs revealed significant differences (p < 0.05) in the following patterns: GIS2 for ALFF, GIS2 for ALFF-GSR, GIS1 and GIS2 for DC, GIS3 for DC-GSR, and GIS1 and GIS5 for ReHo and ReHo-GSR (Figure 1B, only results without GSR were displayed). The leave-one-subject-out and leave-one-site-out cross-validation consistently showed significant differences, which means that these patterns could effectively differentiate individuals between MDDs and HCs. Additionally, Pearson correlation analyses revealed that GIS1 of ReHo and ReHo-GSR were positively correlated with HAMD scores (Figure 2).
Conclusions:
SSM-PCA could help identify the MDD-related patterns, which were found to be correlated with the depression severity for MDD patients. These identified disease-related patterns could reliably distinguish individuals between MDDs and HCs, revealing the underlying neurological mechanisms. This highlights the potential unitality of these patterns as biomarkers for MDD.
Disorders of the Nervous System:
Psychiatric (eg. Depression, Anxiety, Schizophrenia) 1
Modeling and Analysis Methods:
Classification and Predictive Modeling 2
Novel Imaging Acquisition Methods:
BOLD fMRI
Keywords:
Affective Disorders
FUNCTIONAL MRI
Other - Scaled subprofile model of principal component analysis (SSM-PCA)
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
Yan, C. G., Chen, X., Li, L., Castellanos, F. X., Bai, T. J., Bo, Q. J., Cao, J., Chen, G. M., Chen, N. X., Chen, W., Cheng, C., Cheng, Y. Q., Cui, X. L., Duan, J., Fang, Y. R., Gong, Q. Y., Guo, W. B., Hou, Z. H., Hu, L., Kuang, L., … Zang, Y. F. (2019). Reduced default mode network functional connectivity in patients with recurrent major depressive disorder. Proceedings of the National Academy of Sciences of the United States of America, 116(18), 9078–9083.
Yan, C., & Zang, Y. (2010). DPARSF: A MATLAB toolbox for" pipeline" data analysis of resting-state fMRI. Frontiers in Systems Neuroscience, 4, 13.
Yuan, L. X., Wang, J. B., Zhao, N., Li, Y. Y., Ma, Y., Liu, D. Q., He, H. J., Zhong, J. H., & Zang, Y. F. (2018). Intra- and Inter-scanner Reliability of Scaled Subprofile Model of Principal Component Analysis on ALFF in Resting-State fMRI Under Eyes Open and Closed Conditions. Frontiers in neuroscience, 12, 311.