Predicting Mental Health Symptoms with NBS-Predict
Poster No:
1403
Submission Type:
Abstract Submission
Authors:
Sarah Wellan1, Anna Daniels1, Melanie Schwefel2, Andreas Heissel3, Andreas Ströhle1, Stephan Heinzel4, Henrik Walter1
Institutions:
1Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM, Berlin, Germany, 2Freie Universität Berlin, Department of Education and Psychology, Berlin, Germany, 3University of Potsdam, Social and Preventive Medicine, Potsdam, Germany, 4Technische Universität Dortmund, Institute of Psychology, Dortmund, Germany
First Author:
Sarah Wellan
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Co-Author(s):
Anna Daniels
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Andreas Ströhle
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Henrik Walter
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Charité - Universitätsmedizin Berlin, Department of Psychiatry and Neurosciences CCM
Berlin, Germany
Introduction:
NBS-Predict (Serin et al. 2021) is a fMRI analysis toolbox which combines network-based statistics with machine-learning. With this toolbox resting-state networks predictive of psychological features can be identified. Here, we focused on predicting positive and negative aspects of mental health in two studies. In the ELAN dataset (n = 68 healthy participants) we predicted meaning in life and trait hedonic functioning, two related but distinct components of well-being. In the SPeED (Heinzel et al. 2018) dataset (n = 97 patients with depression) we predicted depressive symptoms. In SPeED, we additionally tried to predict symptom improvements after psychotherapy.
Methods:
fMRI data were preprocessed with HALFpipe (Waller et al. 2022). We used Pearson correlation and the Brainnetome atlas to create correlation matrices. For the NBS-Predict analysis, we chose 5-fold cross-validation with 10 repetitions, hyperparameter optimization and linear regression as well as swmR as machine learning algorithms. In ELAN, we analyzed meaning in life and trait hedonic functioning each separately, controlling for age, sex, max FD and mean FD as covariates of no interest. In SPeED, we added psychopharmacological medication as covariate and predicted depressive symptoms at baseline as well as changes in symptoms after exercise and psychotherapy.
Results:
Using NBS-Predict on two datasets, we were able to predict different aspects of current mental health from resting-state fMRI with a correlation of up to 0.3. However, parameters of baseline resting-state fMRI in SPeED did not predict changes in mental health after psychotherapy in our sample.
Conclusions:
Our results suggest that positive aspects of mental health, such as meaning in life and hedonic functioning, as well as depressive symptoms are valid targets of predictive resting-state functional connectivity analysis. The lack of longitudinal prediction might be due to the relatively small sample size, the parameters used or to the fact that the informational value of resting-state fMRI for predicting therapy response is limited. More analysis in larger samples and with additional methods are needed.
Disorders of the Nervous System:
Psychiatric (eg. Depression, Anxiety, Schizophrenia) 2
Modeling and Analysis Methods:
fMRI Connectivity and Network Modeling 1
Keywords:
FUNCTIONAL MRI
Machine Learning
Psychiatric Disorders
Other - Depression; Meaning in Life; Functional Connectivity
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.
Serin, E., Zalesky, A., Matory, A., Walter, H., & Kruschwitz, J. D. (2021). NBS-Predict: A prediction-based extension of the network-based statistic. NeuroImage, 244, 118625.
Waller, L., Erk, S., Pozzi, E., Toenders, Y. J., Haswell, C. C., Büttner, M., ... & Veer, I. M. (2022). ENIGMA HALFpipe: interactive, reproducible, and efficient analysis for resting‐state and task‐based fMRI data. Human Brain Mapping, 43(9), 2727-2742.