Predicting Fluid Intelligence from Structural MRI Using Random Forest regression

  • Agata Wlaszczyk
  • Agnieszka Kaminska
  • Agnieszka Pietraszek
  • Jakub Dabrowski
  • Mikolaj A. Pawlak
  • Hanna NowickaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11791)


Fluid intelligence (FI) indicates a set of general abilities like pattern recognition, abstract thinking, and problem-solving. FI is related to inherent, biological factors. We present a method to predict the fluid intelligence score in children (9–10 y/o) from their structural brain scans. For the purposes of this work, we used features derived from the T1-weighted Magnetic Resonance scans from the ABCD study. We used data from 3739 subjects for training and 415 for validation of the model. As features we used the volumes of gray matter regions of interest provided by the challenge organizers, as well as three additional groups of features. These include signal intensity features based on the ROIs, as well as shape-based features derived from the anterior and posterior cross sectional area of the corpus callosum. We used the random forest regressor model for prediction. We compare its performance to other regression-based models (XGBoost Regression and Support Vector Regression). Additionally, we ran a mean decrease accuracy (MDA) algorithm to select features that had high influence on the prediction results. The results we have obtained for the validation set were as follows: MSE = 67.39, R-squared = 0.0762. The proposed method showed promising results and has the potential to provide a good prediction of fluid intelligence based on structural brain scans.


Adolescence development Fluid intelligence Random Forest Regressor 



The authors would like to thank Professor Mark Jenkinson for his helpful comments regarding the manuscript.


  1. 1.
    Cattell, R.B.: Abilities: Their Structure, Growth, and Action. Houghton Mifflin, Oxford (1971)Google Scholar
  2. 2.
    Conway, A.R.A., Kovacs, K.: New and emerging models of human intelligence. Wiley Interdisc. Rev.: Cognitive Sci. 6(5), 419–426 (2015)CrossRefGoogle Scholar
  3. 3.
    Kaya, F., Stough, L.M., Juntune, J.: Verbal and nonverbal intelligence scores within the context of poverty. Gifted Educ. Int. 33(3), 257–272 (2016)CrossRefGoogle Scholar
  4. 4.
    Rindermann, H., Flores-Mendoza, C., Mansur-Alves, M.: Reciprocal effects between fluid and crystallized intelligence and their dependence on parents’ socioeconomic status and education. Learn. Individ. Differ. 20(5), 544–548 (2010)CrossRefGoogle Scholar
  5. 5.
    Gottfredson, L.S.: Hans Eysenck’s theory of intelligence, and what it reveals about him. Personality Individ. Differ. 103, 116–127 (2016)CrossRefGoogle Scholar
  6. 6.
    Plomin, R., Stumm, S.V.: The new genetics of intelligence. Nat. Rev. Genet. 19, 148–159 (2018)CrossRefGoogle Scholar
  7. 7.
    Ritchie, S.J., et al.: Beyond a bigger brain: multivariable structural brain imaging and intelligence. Intelligence 51, 47–56 (2015)CrossRefGoogle Scholar
  8. 8.
    Cole, M.W., Yarkoni, T., Repovs, G., Anticevic, A., Braver, T.S.: Global connectivity of prefrontal cortex predicts cognitive control and intelligence. J. Neurosci. 32(26), 8988–8999 (2012)CrossRefGoogle Scholar
  9. 9.
    Choi, Y.Y., et al.: Multiple bases of human intelligence revealed by cortical thickness and neural activation. J. Neurosci. 28(41), 10323–10329 (2008)CrossRefGoogle Scholar
  10. 10.
    Gray, J.R., Chabris, C.F., Braver, T.S.: Neural mechanisms of general fluid intelligence. Nat. Neurosci. 6(3), 316 (2003)CrossRefGoogle Scholar
  11. 11.
    Akshoomoff, N., et al.: NIH toolbox cognition battery (cb): Composite scores of crystallized, fluid, and overall cognition. Monogr. Soc. Res. Child Dev. 78(4), 119–132 (2013)CrossRefGoogle Scholar
  12. 12.
    McDaniel, M.A.: Big-brained people are smarter: a meta-analysis of the relationship between in vivo brain volume and intelligence. Intelligence 33, 337–346 (2005)CrossRefGoogle Scholar
  13. 13.
    Luders, E., Thompson, P.M., Narr, K.L., Zamanyan, A., Chou, Y.Y., Gutman, B., Dinov, I.D., Toga, A.W.: The link between callosal thickness and intelligence in healthy children and adolescents. Neuroimage 54(3), 1823–30 (2011)CrossRefGoogle Scholar
  14. 14.
    Westerhausen, R., et al.: The corpus callosum as anatomical marker of intelligence? A critical examination in a large-scale developmental study. Brain Struct Funct. 223(1), 285–296 (2018)CrossRefGoogle Scholar
  15. 15.
    Haász, J., Westlye, E.T., Fjær, S., Espeseth, T., Lundervold, A., Lundervold, A.J.: General fluid-type intelligence is related to indices of white matter structure in middle-aged and old adults. Neuroimage 83, 372–383 (2013)CrossRefGoogle Scholar
  16. 16.
    ABCD study website Accessed 4 Apr 2019
  17. 17.
    Data Supplement of Pfefferbaum et al.: Altered Brain Developmental Trajectories in Adolescents After Initiating Drinking. Am. J. Psychiatry 175(4), 370–380 (2018)Google Scholar
  18. 18.
    Glasser, M.F., Van Essen, D.C.: Mapping human cortical areas in vivo based on myelin content as revealed by T1- and T2-weighted MRI. J. Neurosci. 31(32), 11597–11616 (2011)CrossRefGoogle Scholar
  19. 19.
    Ganzetti, M., Wenderoth, N., Mantini, D.: Whole brain myelin mapping using T1- and T2-weighted MR imaging data. Front Hum Neurosci. 8, 671 (2014)CrossRefGoogle Scholar
  20. 20.
    Koenig, S.H.: Cholesterol of myelin is the determinant of gray-white contrast in MRI of brain. Magn. Reson. Med. 20(2), 285–291 (1991)CrossRefGoogle Scholar
  21. 21.
    Sigalovsky, I.S., Fischl, B., Melcher, J.R.: Mapping an intrinsic MR property of gray matter in auditory cortex of living humans: a possible marker for primary cortex and hemispheric differences. Neuroimage 32(4), 1524–37 (2006)CrossRefGoogle Scholar
  22. 22.
    Jenkinson, M., Beckmann, C.F., Behrens, T.E., Woolrich, M.W., Smith, S.M.: FSL. NeuroImage 62, 782–90 (2012)CrossRefGoogle Scholar
  23. 23.
    Zhang, X., Yang, Y.H., Han, Z., Wang, H., Gao, C.: Object class detection: a survey. ACM Comput. Surv. (CSUR) 46(1) (2013) CrossRefGoogle Scholar
  24. 24.
    Automatic Registration Toolbox. Accessed 4 Apr 2019
  25. 25.
    Ardekani, B.A., Figarsky, K., Sidtis, J.J.: Sexual dimorphism in the human corpus callosum: an MRI study using the OASIS brain database. Cereb. Cortex 23(10), 2514–2520 (2012)CrossRefGoogle Scholar
  26. 26.
    Han, H., Guo, X., Yu, H.: Variable selection using mean decrease accuracy and mean decrease gini based on random forest. In: 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp. 219–224. IEEE (2016)Google Scholar
  27. 27.
    Website of the challenge. Accessed 4 Apr 2019
  28. 28.
    Cole, J.H., et al.: Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. NeuroImage 163, 115–124 (2017)CrossRefGoogle Scholar
  29. 29.
    Abdollahi, R.O., et al.: Correspondences between retinotopic areas and myelin maps in human visual cortex. Neuroimage 99, 509–524 (2014)CrossRefGoogle Scholar
  30. 30.
    Ganzetti, M., Wenderoth, N., Mantini, D.: Whole brain myelin mapping using T1-and T2-weighted MR imaging data. Frontiers Hum. Neurosci. 8, 671 (2014)CrossRefGoogle Scholar
  31. 31.
    Burgaleta, M., et al.: Subcortical regional morphology correlates with fluid and spatial intelligence. Hum. Brain Mapp. 35(5), 1957–1968 (2014)CrossRefGoogle Scholar
  32. 32.
    Bernal, J., et al.: Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review. Artif. Intell. Med. 95, 64–81 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.TooplooxWroclawPoland
  2. 2.Adam Mickiewicz University in PoznanPoznanPoland
  3. 3.LodzPoland
  4. 4.Poznan University of TechnologyPoznanPoland
  5. 5.Poznan University of Medical SciencesPoznanPoland
  6. 6.Inteneural Networks Inc.ChicagoUSA
  7. 7.FMRIB, Wellcome Centre for Integrative NeuroimagingUniversity of OxfordOxfordUK

Personalised recommendations