Stacking models of brain dynamics to improve prediction of subject traits in fMRI
Poster No:
1110
Submission Type:
Abstract Submission
Authors:
Ben Griffin1, Christine Ahrends2, Chetan Gohil3, Fidel Alfaro Almagro4, Mark Woolrich5, Stephen Smith1, Diego Vidaurre6
Institutions:
1University of Oxford, Oxford, Oxfordshire, 2University of Oxford, Oxford, United Kingdom, 3University of Sydney, Sydney, NSW, 4WiN FMRIB - University of Oxford, Oxford, State/Province, 5University of Oxford, Oxford, Oxon, 6Aarhus University, Aarhus, Denmark
First Author:
Co-Author(s):
Introduction:
Beyond structural and static brain measures, brain dynamics can add important information when investigating individual cognitive traits (Vidaurre, 2021). One way to look at dynamics is through the Hidden Markov Model (HMM), a probabilistic model of temporal dynamics of functional connectivity, which can be combined with machine learning models to generate subject-specific trait predictions (Vidaurre, 2021). However, there are two potential sources of variability in these predictions. First, the run-to-run variability (e.g., due to different initialisations) (Vidaurre, 2019); and second, the choice of hyperparameters (e.g., number of HMM states). We propose an approach that leverages this variability to improve prediction accuracy by combining information from different models and runs. We implement a stacked generalisation scheme (Wolpert, 1992) that combines predictions from multiple models of brain dynamics to accomplish two goals: (i) produce robust predictions across multiple cognitive traits; (ii) improve prediction accuracy by combining predictions created by HMMs with varying hyperparameters.
Methods:
We aimed to predict cognitive traits for subjects in the Human Connectome Project (HCP) (Van Essen, 2013) and UK Biobank (Sudlow, 2015) datasets using models based on their resting-state fMRI functional connectivity dynamics. To achieve this, we used a group-level HMM on surface-based node timeseries concatenated across all subjects, which were generated using 25-dimensional group-ICA surface maps. Subsequently, subject-specific HMM parameters were dual-estimated using the parameters obtained from the group-level HMM, which involved generating subject-specific state-time courses, from which subject-specific HMM parameters were inferred.
We then used the Fisher kernel method, a mathematically principled way of combining generative models (here, the HMM) with discriminative methods (here, kernel ridge regression). This method operates directly on the Riemannian manifold of the HMM parameters, capturing the natural geometry of the HMM. The method constructs a subject-by-subject matrix that quantifies the similarities between subjects by examining how the HMM likelihood function varies locally with respect to the subjects' HMM parameters.
This entire process was repeated 100 times; applying the HMM 50 times with fixed hyperparameters but different random initialisations (to investigate the HMM run-to-run variability) and 50 times with varying hyperparameters (to investigate hyperparameter selection variability). Separately for each group-level HMM, Fisher kernels were computed and used with kernel ridge regression to produce subject-specific predictions, which were subsequently combined using stacking.
We then used the Fisher kernel method, a mathematically principled way of combining generative models (here, the HMM) with discriminative methods (here, kernel ridge regression). This method operates directly on the Riemannian manifold of the HMM parameters, capturing the natural geometry of the HMM. The method constructs a subject-by-subject matrix that quantifies the similarities between subjects by examining how the HMM likelihood function varies locally with respect to the subjects' HMM parameters.
This entire process was repeated 100 times; applying the HMM 50 times with fixed hyperparameters but different random initialisations (to investigate the HMM run-to-run variability) and 50 times with varying hyperparameters (to investigate hyperparameter selection variability). Separately for each group-level HMM, Fisher kernels were computed and used with kernel ridge regression to produce subject-specific predictions, which were subsequently combined using stacking.
·Procedure for predicting subject traits from resting-state fMRI (rfMRI) timeseries.
Results:
By combining predictions generated using the Fisher kernel method from group-level HMMs, we achieve our first goal (i) of producing a robust prediction across traits. Furthermore, by varying the hyperparameters of the HMM, our second goal (ii) of improving prediction accuracy is achieved. The diversity created by varying the HMM hyperparameters enabled distinct yet complementary predictions to be generated, and stacking resulted in boosting the prediction accuracy. Stacking performs particularly well when, for a given trait, certain predictions are much better than the remaining predictions.
Conclusions:
For predictions to be useful (e.g., in a clinical setting), we require that they are both robust and accurate. We used the Fisher kernel method, leveraging the natural geometry of the HMM, to generated accurate predictions. To enhance robustness and accuracy further, we employed stacking, combining predictions from different HMM configurations that captured distinct patterns in the data. Looking forward, stacking predictions opens up avenues for integrating a wider variety of data or models, for example combining predictions from different brain imaging modalities, or static functional connectivity and structural information.
Modeling and Analysis Methods:
Classification and Predictive Modeling 1
fMRI Connectivity and Network Modeling 2
Keywords:
FUNCTIONAL MRI
Machine Learning
Modeling
Other - Brain Dynamics
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.
relevance of spontaneous, transient brain network interactions in fMRI. NeuroImage 229,
p. 117713.
Vidaurre, D. (2019). Stable between-subject statistical inference from un-
stable within-subject functional connectivity estimates. Human brain mapping 40.4, 1234–
1243.
Wolpert, D. H. (1992). Stacked generalization. Neural networks 5.2, 241–259.
Van Essen, D. C. (2013). The WU-Minn human connectome
project: an overview. Neuroimage 80, 62–79.
Sudlow, C. (2015). UK biobank: an open access
resource for identifying the causes of a wide range of complex diseases of middle and old age.
PLoS medicine 12.3, e1001779.
Vidaurre, D. (2017). Brain network dynamics are
hierarchically organized in time. Proceedings of the National Academy of Sciences 114.48,
12827–12832.
Jaakkola, T. (1998). Exploiting generative models in discriminative
classifiers. Advances in neural information processing systems, 11.