Move-fmri predict emotion processing better than resting state: connectome-based predictive mod
Poster No:
1410
Submission Type:
Abstract Submission
Authors:
Jasper Mostert1, Shuer Ye1, Maryam Ziaei1
Institutions:
1Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology, Trondheim, Norway
First Author:
Jasper Mostert
Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology
Trondheim, Norway
Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology
Trondheim, Norway
Co-Author(s):
Shuer Ye
Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology
Trondheim, Norway
Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology
Trondheim, Norway
Maryam Ziaei
Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology
Trondheim, Norway
Kavli Institute for Systems Neuroscience, Norwegian University of Science and Technology
Trondheim, Norway
Introduction:
Advances in machine learning are enabling data-driven approaches to better understand brain-behavior relationships (Vu et al., 2018). Functional connectivity (FC) analysis, which focuses on synchronized activity patterns, provides essential data for this pursuit, collected from resting-state or naturalistic movie watching. Movie-fMRI has been shown to produce both higher individual differences and lower inter-subject variability than resting-state scans, making it a promising alternative (Finn, 2021).
Connectome-based predictive modeling (CPM) (Shen et al., 2017) enables the prediction of behaviors from FC data, has high computational efficiency, and offers explainability. It has been widely applied in the prediction of attention (Horien et al., 2022) to psychopathic traits (Ye et al., 2022) and recently also shown promise for movie FC-based predictions (Finn et al., 2020). However, there remains a lack of studies on predicting emotional processing as well as the age-related differences in predicting brain-behavior relationships using CPM and movie-fMRI.
Connectome-based predictive modeling (CPM) (Shen et al., 2017) enables the prediction of behaviors from FC data, has high computational efficiency, and offers explainability. It has been widely applied in the prediction of attention (Horien et al., 2022) to psychopathic traits (Ye et al., 2022) and recently also shown promise for movie FC-based predictions (Finn et al., 2020). However, there remains a lack of studies on predicting emotional processing as well as the age-related differences in predicting brain-behavior relationships using CPM and movie-fMRI.
Methods:
Data from 492 participants (mean age = 51.58 ± 18.55, 251 females), after excluding excessive head motion, from the Cambridge Centre for Ageing and Neuroscience dataset (Taylor et al., 2017) was used for this study. Participants underwent movie-watching and resting-state sessions during the fMRI scans and completed assessments for fluid intelligence (Cattell) and two types of emotional processing; emotion recognition (accuracy and reaction time were measured) and emotion memory (Recall, recognition and priming variables were available). To perform CPM, we first parcellated data according to the Schaefer-400 atlas creating a connectivity matrix over the time of the scan for each participant. Next, predictive features were extracted through machine learning and predictive model was built. Its performance was tested using cross validation (Boyle & Weng, 2023) and lesion analysis were performed to identify the most contributing networks to successful predictions.
Results:
Movie-based CPM could successfully predict fluid intelligence (r = .46, p < .001) and all emotional processing measurements (recall: r = .41, recognition: r = .44, priming: r = .18, emotional recognition accuracy: r = .28, and reaction time: r = .21; all p < .001). In contrast, resting-state models had significantly weaker performance (Fig. 1a). CPM models trained only on older adults were also able to predict all variables while the ones for younger models were only significantly predictive for the fluid intelligence measurments (r = .18, p = .047) (Fig. 1b). Analyses of predictive connections and virtual lesions showed a distributed predictive power across all networks, including the default mode and dorsal attention networks (Fig. 1c), with notably the limbic network playing a distinct role in the prediction of both fluid intelligence and emotional processing.
·Fig 1
Conclusions:
This study confirms and extends the applicability of CPM as a data-driven approach to brain and emotional behavior insights. For the first time, we demonstrated the superiority of movie-based CPM over resting-state CPM for predicting emotional processing. Additionally, age-related differences in the predictive networks shed light into how aging impacts the distributed inter- network structure. Therefore, our study provides insights for clinical application while also demonstrating versatility of the CPM in studying FC for emotional behaviors across the lifespan.
Emotion, Motivation and Social Neuroscience:
Emotion and Motivation Other
Lifespan Development:
Aging 2
Modeling and Analysis Methods:
fMRI Connectivity and Network Modeling 1
Keywords:
Aging
Emotions
FUNCTIONAL MRI
Other - CPM
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.
Horien, C., Greene, A. S., Shen, X., Fortes, D., Brennan‐Wydra, E., Banarjee, C., Foster, R., Donthireddy, V., Butler, M., Powell, K., Vernetti, A., Mandino, F., O’Connor, D., Lake, E., McPartland, J. C., Volkmar, F. R., Chun, M. M., Chawarska, K., Rosenberg, M. D., … Constable, R. T. (2022). A generalizable connectome-based marker of in-scan sustained attention in neurodiverse youth. Cerebral Cortex, 33(10), 6320- 6334. https://doi.org/10.1093/cercor/bhac506
Finn, E. S. (2021). Is it time to put rest to rest? Trends in Cognitive Sciences. https://doi.org/10.1016/j.tics.2021.09.005
Finn, E. S., Bandettini, P. A., & Bandettini, P. A. (2020). Movie-watching outperforms rest for functional connectivity-based prediction of behavior. BioRxiv. https://doi.org/10.1101/2020.08.23.263723
Taylor, J. R., Williams, N., Cusack, R., Auer, T., Shafto, M. A., Dixon, M., Tyler, L. K., Cam‐CAN, & Henson, R. N. (2017). The Cambridge Centre for Ageing and Neuroscience (Cam-CAN) data repository: Structural and functional MRI, MEG, and cognitive data from a cross- sectional adult lifespan sample. NeuroImage, 144, 262–269. https://doi.org/10.1016/j.neuroimage.2015.09.018
Shen, X., Finn, E. S., Mayes, L. C., Scheinost, D., Hedeker, D., Rosenberg, M. D., Chun, M. M., Papademetris, X., & Constable, R. T. (2017). Using connectome-based predictive modeling to predict individual behavior from brain connectivity. Nature Protocols, 12(3), 506– 518. https://doi.org/10.1038/nprot.2016.178
Vu, M.-A. T., Adalı, T., Ba, D., Buzsáki, G., Carlson, D., Heller, K., Liston, C., Rudin, C., Sohal, V. S., Widge, A. S., Mayberg, H. S., Sapiro, G., & Dzirasa, K. (2018). A shared vision for machine learning in neuroscience. The Journal of Neuroscience, 38(7), 1601–1 607. https://doi.org/10.1523/JNEUROSCI.0508-17.2018
Ye, S., Zhu, B., Zhao, L., Tian, X., Yang, Q., & Krueger, F. (2022). Connectome-based model predicts individual psychopathic traits in college students. Neuroscience Letters, 769, 136387. https://doi.org/10.1016/j.neulet.2021.136387