Predicting individual cognitive ability with the relationship of lateralization between functions
Poster No:
1898
Submission Type:
Abstract Submission
Authors:
Haokun Li1, Gaolang Gong1
Institutions:
1Beijing Normal University, Beijing, China
First Author:
Co-Author:
Introduction:
While the lateralization of human cognitive functions has been well documented at the population level, how the lateralization between these functions relates to each other at the individual level is largely unknown [1]. In this study, we proposed a new method to quantify the relationship between functions' lateralization within individuals, and applied a machine learning approach to explore whether and how the cognitive ability could be individually predicted by this relationship, using fMRI data from nearly 1000 healthy adults.
Methods:
A total of 999 subjects (female/male: 529/470; age: 28.71±3.7 years) from the "HCP1200" dataset were included in our analysis. All the subjects completed functional MRI scanning for language, emotion, gambling, relational, social, and working memory tasks [2]. The structural and functional images was pre-processed using the HCP pipelines [2,3].
The group-average activation maps of the main contrasts of six tasks (i.e., "story vs. math"; "2-back vs. 0-back"; "reward vs. baseline"; "tom vs. random"; "relational vs. match"; "faces vs. shapes") were used to locate the activated regions. The mean of positive Cohen's d values across the vertices of the entire cortex was calculated as the threshold, and the final region of each function was then identified as the HCP-MMP parcels above the threshold (Fig. 1A) [4] [5]. For each pair of the functions, the union areas of both sides and functions were identified to calculate the laterality effect and the pattern similarity of lateralization.
For each individual, the laterality effect of each function was defined as (left - right) of Z-values of the paired vertices in the two hemispheres within the union areas, forming a spacial pattern actually, which could be used to calculate the correlation of lateralization for each combination. All the subjects could form 15 distributions of pattern similarity of lateralization for each two paired functions. The significance of each combination was tested by one-sample t test or Wilcoxon test. The cognitive ability for each subject was obtained through a principal components analysis from 10 cognitive behavioral scores from HCP, taking the first principal component as the general cognitive score. And each individual ended up with a feature vector of r-values with a length of 15. A ridge regression with a nested 5-fold cross-validation approach (5F-CV) was then applied to predict the general score [6] (Fig. 1B). A nonparametric permutation method was used to assess the significance of the Pearson correlation coefficient, mean absolute error (MAE), and feature weight.
The group-average activation maps of the main contrasts of six tasks (i.e., "story vs. math"; "2-back vs. 0-back"; "reward vs. baseline"; "tom vs. random"; "relational vs. match"; "faces vs. shapes") were used to locate the activated regions. The mean of positive Cohen's d values across the vertices of the entire cortex was calculated as the threshold, and the final region of each function was then identified as the HCP-MMP parcels above the threshold (Fig. 1A) [4] [5]. For each pair of the functions, the union areas of both sides and functions were identified to calculate the laterality effect and the pattern similarity of lateralization.
For each individual, the laterality effect of each function was defined as (left - right) of Z-values of the paired vertices in the two hemispheres within the union areas, forming a spacial pattern actually, which could be used to calculate the correlation of lateralization for each combination. All the subjects could form 15 distributions of pattern similarity of lateralization for each two paired functions. The significance of each combination was tested by one-sample t test or Wilcoxon test. The cognitive ability for each subject was obtained through a principal components analysis from 10 cognitive behavioral scores from HCP, taking the first principal component as the general cognitive score. And each individual ended up with a feature vector of r-values with a length of 15. A ridge regression with a nested 5-fold cross-validation approach (5F-CV) was then applied to predict the general score [6] (Fig. 1B). A nonparametric permutation method was used to assess the significance of the Pearson correlation coefficient, mean absolute error (MAE), and feature weight.
Results:
As shown in Fig. 2A, the r-values for each two paired functions were all significantly different from zero. In Fig. 2B, the pattern similarity of lateralization could significantly predict the general score at the individual level (r=0.53, p<0.0001). In Fig. 2C, the absolute value of the weight represents the importance of corresponding feature in the prediction model, and the positive or negative feature value indicates whether the pattern similarity changes in a similar way with the score or the opposite. That is, a stronger positive correlation between wm-gambling, gambling-relational, and a stronger negative correlation between language-wm, indicated a better cognitive ability.
Conclusions:
The present study demonstrated significant correlation of lateralization between cognitive functions, and the cognitive ability could be individually predicted by multivariate machine learning approach using this pattern similarity of lateralization. This suggested an interaction of functional lateralization between different functions, which might considerably impact the behavioral performance.
Modeling and Analysis Methods:
Activation (eg. BOLD task-fMRI)
Classification and Predictive Modeling 2
Novel Imaging Acquisition Methods:
BOLD fMRI 1
Keywords:
Cognition
FUNCTIONAL MRI
Hemispheric Specialization
Machine Learning
Other - lateralization
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:
Provide references using APA citation style.
[2] Barch, D. M. et al. (2013), “Function in the human connectome: Task-fMRI and individual differences in behavior”, NeuroImage, vol. 80, pp. 169–189
[3] Glasser, M. F. et al. (2013), “The minimal preprocessing pipelines for the Human Connectome Project”, NeuroImage, vol. 80, pp. 105–124
[4] Glasser, M. F. et al. (2016), “A multi-modal parcellation of human cerebral cortex”, Nature, vol. 536, no. 7615, pp. 171–178
[5] Rajimehr, R. et al. (2022), “Complementary hemispheric lateralization of language and social processing in the human brain”, Cell Reports, vol. 41, no. 6, pp. 111617
[6] Cui, Z. et al. (2018), “The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features”, NeuroImage, vol. 178, pp. 622–637