A Dynamic Biomarker-Driven Framework for Characterizing Clinical High-Risk Cohort
Poster No:
559
Submission Type:
Abstract Submission
Authors:
Najme Soleimani1, Sir-Lord Wiafe2, Vince Calhoun3
Institutions:
1Center for Translational Research in Neuroimaging and Data Science (TReNDS), GSU, GATech, Emory, Atlanta, GA, 2Georgia State University, TRENDS, Atlanta, GA, 3GSU/GATech/Emory, Atlanta, GA
First Author:
Najme Soleimani
Center for Translational Research in Neuroimaging and Data Science (TReNDS), GSU, GATech, Emory
Atlanta, GA
Center for Translational Research in Neuroimaging and Data Science (TReNDS), GSU, GATech, Emory
Atlanta, GA
Co-Author(s):
Introduction:
Functional Network Connectivity (FNC), derived from resting-state functional magnetic resonance imaging (fMRI), has emerged as a critical modality for uncovering neural disruptions underlying mental health disorders (Rashid & Calhoun, 2020),(Yan et al., 2024). By analyzing temporal and spatial interactions between intrinsic connectivity networks (ICNs), FNC facilitates the identification of biomarkers that reveal characteristic alterations associated with psychiatric and neurological conditions (Soleimani et al., 2024),(Du et al., 2015). These biomarkers offer a means to detect early indicators and develop predictive risk scores, particularly for clinical high-risk (CHR) populations. This study focuses on utilizing ICA-based biomarkers to assess elevated risk in CHR individuals.
Methods:
Datasets
The mental disorders dataset includes data from multiple sites and cohorts, providing a diverse representation of psychiatric conditions. CHR cohort was obtained from the AMP-SCZ study, which focuses on early identification and intervention in individuals at elevated risk for developing schizophrenia (SCZ).
Population-Level Connectivity Templates
To analyze risk score, we began by applying spatially constrained independent component analysis (ICA) to the preprocessed fMRI data of all participants using the Neuromark fMRI 1.0 template (Du et al., 2020) to identify 53 ICNs. Subsequently, time-resolved connectivity matrices were calculated via a sliding window approach to capture temporal variations in connectivity between the identified ICNs.
Population-level connectivity templates were derived by concatenating dyamic FNC matrices across participants and applying blind ICA, yielding 15 independent components, termed dynamic double functional independent primitives (ddFIPs) serving as connectivity templates capturing shared network interactions.
Constrained ICA for Subject-Specific Patterns
The 15 ddFIPs were subsequently used as priors in a constrained ICA framework to extract subject-specific connectivity patterns (c-ddFIP). This back-reconstruction step ensured that individual patterns were aligned with the population-wide templates while allowing for subject-specific variability.
Application to Clinical High-Risk Data
The 15 ddFIPs derived from the general population dataset were used as priors to perform constrained ICA on the CHR cohort. The correlation between the CHR cohort's reconstructed components and those of schizophrenia subjects was computed, resulting in 15-dimensional risk scores for each individual. This approach provided a detailed characterization of how CHR individuals' connectivity dynamics align with population-wide connectivity templates and their relationship to schizophrenia-related patterns.
The mental disorders dataset includes data from multiple sites and cohorts, providing a diverse representation of psychiatric conditions. CHR cohort was obtained from the AMP-SCZ study, which focuses on early identification and intervention in individuals at elevated risk for developing schizophrenia (SCZ).
Population-Level Connectivity Templates
To analyze risk score, we began by applying spatially constrained independent component analysis (ICA) to the preprocessed fMRI data of all participants using the Neuromark fMRI 1.0 template (Du et al., 2020) to identify 53 ICNs. Subsequently, time-resolved connectivity matrices were calculated via a sliding window approach to capture temporal variations in connectivity between the identified ICNs.
Population-level connectivity templates were derived by concatenating dyamic FNC matrices across participants and applying blind ICA, yielding 15 independent components, termed dynamic double functional independent primitives (ddFIPs) serving as connectivity templates capturing shared network interactions.
Constrained ICA for Subject-Specific Patterns
The 15 ddFIPs were subsequently used as priors in a constrained ICA framework to extract subject-specific connectivity patterns (c-ddFIP). This back-reconstruction step ensured that individual patterns were aligned with the population-wide templates while allowing for subject-specific variability.
Application to Clinical High-Risk Data
The 15 ddFIPs derived from the general population dataset were used as priors to perform constrained ICA on the CHR cohort. The correlation between the CHR cohort's reconstructed components and those of schizophrenia subjects was computed, resulting in 15-dimensional risk scores for each individual. This approach provided a detailed characterization of how CHR individuals' connectivity dynamics align with population-wide connectivity templates and their relationship to schizophrenia-related patterns.
Results:
Key findings indicate that differences in c-ddFIPs between CHR individuals and healthy controls (HC) are milder in magnitude compared to those observed between SCZ patients and HCs, suggesting that CHR individuals lie along a continuum of brain network alterations that may progress toward SCZ in converters. Furthermore, Certain constrained ddFIPs (e.g., c-ddFIP 4 in the visual and cerebellar domains) showed similar differences in both SCZ vs. HC and CHR vs. HC comparisons. This indicates shared neural disruptions between CHR individuals and SCZ patients, aligning with the elevated risk of CHR individuals developing SCZ. Conversely, some regions in other c-ddFIPs (e.g., different regions in c-ddFIP 7 and 14) displayed opposite patterns between SCZ vs. HC and CHR vs. HC. This finding suggests that while CHR individuals exhibit early neural changes, these do not fully mirror the extent or direction of disruptions seen in SCZ, potentially reflecting the absence of later-stage disease progression.
Conclusions:
This study shows that introduced biomarkers can assess risk in clinical high-risk individuals, revealing neural disruptions that may indicate early stage or progression to schizophrenia.
Disorders of the Nervous System:
Psychiatric (eg. Depression, Anxiety, Schizophrenia) 1
Modeling and Analysis Methods:
Classification and Predictive Modeling
Connectivity (eg. functional, effective, structural)
fMRI Connectivity and Network Modeling
Methods Development 2
Keywords:
FUNCTIONAL MRI
Psychiatric Disorders
Schizophrenia
Other - Biomarkers, independent component analysis (ICA)
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?
Are you Internal Review Board (IRB) certified? Please note: Failure to have IRB, if applicable will lead to automatic rejection of abstract.
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.
Du, Y. (2015). A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear: application to schizophrenia, bipolar, and schizoaffective disorders. Neuroimage, 122, 272–280.
Rashid, B.(2020). Towards a brain‐based predictome of mental illness. Human Brain Mapping, 41(12), 3468–3535.
Soleimani, N. (2024). Unraveling the Neural Landscape of Mental Disorders using Double Functional Independent Primitives (dFIPs). BioRxiv.
Yan, W. (2024). A brainwide risk score for psychiatric disorder evaluated in a large adolescent population reveals increased divergence among higher-risk groups relative to control participants. Biological Psychiatry, 95(7), 699–708.