Individual characteristics outperform resting-state fMRI for the prediction of behavioral phenotypes.
Journal
Communications biology
ISSN: 2399-3642
Titre abrégé: Commun Biol
Pays: England
ID NLM: 101719179
Informations de publication
Date de publication:
26 Jun 2024
26 Jun 2024
Historique:
received:
23
05
2023
accepted:
11
06
2024
medline:
27
6
2024
pubmed:
27
6
2024
entrez:
26
6
2024
Statut:
epublish
Résumé
In this study, we aimed to compare imaging-based features of brain function, measured by resting-state fMRI (rsfMRI), with individual characteristics such as age, gender, and total intracranial volume to predict behavioral measures. We developed a machine learning framework based on rsfMRI features in a dataset of 20,000 healthy individuals from the UK Biobank, focusing on temporal complexity and functional connectivity measures. Our analysis across four behavioral phenotypes revealed that both temporal complexity and functional connectivity measures provide comparable predictive performance. However, individual characteristics consistently outperformed rsfMRI features in predictive accuracy, particularly in analyses involving smaller sample sizes. Integrating rsfMRI features with demographic data sometimes enhanced predictive outcomes. The efficacy of different predictive modeling techniques and the choice of brain parcellation atlas were also examined, showing no significant influence on the results. To summarize, while individual characteristics are superior to rsfMRI in predicting behavioral phenotypes, rsfMRI still conveys additional predictive value in the context of machine learning, such as investigating the role of specific brain regions in behavioral phenotypes.
Identifiants
pubmed: 38926486
doi: 10.1038/s42003-024-06438-5
pii: 10.1038/s42003-024-06438-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
771Informations de copyright
© 2024. The Author(s).
Références
Biswal, B., Zerrin Yetkin, F., Haughton, V. M. & Hyde, J. S. Functional connectivity in the motor cortex of resting human brain using echo-planar MRI. Magn. Reson. Med. 34, 537–541 (1995).
pubmed: 8524021
doi: 10.1002/mrm.1910340409
Biswal, B. B. Resting state fMRI: a personal history. NeuroImage 62, 938–944 (2012).
pubmed: 22326802
doi: 10.1016/j.neuroimage.2012.01.090
Fox, M. D. & Raichle, M. E. Spontaneous fluctuations in brain activity observed with functional magnetic resonance imaging. Nat. Rev. Neurosci. 8, 700–711 (2007).
pubmed: 17704812
doi: 10.1038/nrn2201
Biswal, B. B., Kylen, J. V. & Hyde, J. S. Simultaneous assessment of flow and BOLD signals in resting-state functional connectivity maps. NMR Biomed. 10, 165–170 (1997).
pubmed: 9430343
doi: 10.1002/(SICI)1099-1492(199706/08)10:4/5<165::AID-NBM454>3.0.CO;2-7
Chen, J. et al. Shared and unique brain network features predict cognitive, personality, and mental health scores in the ABCD study. Nat. Commun. 13, 2217 (2022).
pubmed: 35468875
pmcid: 9038754
doi: 10.1038/s41467-022-29766-8
Kong, R. et al. Spatial Topography of Individual-Specific Cortical Networks Predicts Human Cognition, Personality, and Emotion. Cereb. Cortex 29, 2533–2551 (2019).
pubmed: 29878084
doi: 10.1093/cercor/bhy123
Ooi, L. Q. R. et al. Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI. NeuroImage 263, 119636 (2022).
pubmed: 36116616
doi: 10.1016/j.neuroimage.2022.119636
Sripada, C. et al. Prediction of neurocognition in youth from resting state fMRI. Mol. Psychiatry 25, 3413–3421 (2020).
pubmed: 31427753
doi: 10.1038/s41380-019-0481-6
Finn, E. S. et al. Functional connectome fingerprinting: identifying individuals using patterns of brain connectivity. Nat. Neurosci. 18, 1664–1671 (2015).
pubmed: 26457551
pmcid: 5008686
doi: 10.1038/nn.4135
Pläschke, R. N. et al. Age differences in predicting working memory performance from network-based functional connectivity. Cortex J. Devoted Study Nerv. Syst. Behav. 132, 441–459 (2020).
doi: 10.1016/j.cortex.2020.08.012
Smith, S. M. et al. A positive-negative mode of population covariation links brain connectivity, demographics and behavior. Nat. Neurosci. 18, 1565–1567 (2015).
pubmed: 26414616
pmcid: 4625579
doi: 10.1038/nn.4125
Weis, S. et al. Sex Classification by Resting State Brain Connectivity. Cereb. Cortex 30, 824–835 (2020).
pubmed: 31251328
doi: 10.1093/cercor/bhz129
Khosla, M., Jamison, K., Ngo, G. H., Kuceyeski, A. & Sabuncu, M. R. Machine learning in resting-state fMRI analysis. Magn. Reson. Imaging 64, 101–121 (2019).
pubmed: 31173849
pmcid: 6875692
doi: 10.1016/j.mri.2019.05.031
He, T. et al. Meta-matching as a simple framework to translate phenotypic predictive models from big to small data. Nat. Neurosci. 25, 795–804 (2022).
pubmed: 35578132
pmcid: 9202200
doi: 10.1038/s41593-022-01059-9
Marek, S. et al. Reproducible brain-wide association studies require thousands of individuals. Nature 603, 654–660 (2022).
pubmed: 35296861
pmcid: 8991999
doi: 10.1038/s41586-022-04492-9
More, S., Eickhoff, S. B., Caspers, J. & Patil, K. R. Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study. In Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track. ECML PKDD 2020. Lecture Notes in Computer Science (eds Dong, Y. et al.) vol. 12461. https://doi.org/10.1007/978-3-030-67670-4_1 (Springer, Cham, 2021)
Alfaro-Almagro, F. et al. Confound modelling in UK Biobank brain imaging. NeuroImage 224, 117002 (2021).
pubmed: 32502668
doi: 10.1016/j.neuroimage.2020.117002
Brown, M. et al. ADHD-200 Global Competition: diagnosing ADHD using personal characteristic data can outperform resting state fMRI measurements. Front. Syst. Neurosci. 6, 69 (2012).
pubmed: 23060754
pmcid: 3460316
doi: 10.3389/fnsys.2012.00069
Dadi, K. et al. Population modeling with machine learning can enhance measures of mental health. GigaScience 10, giab071 (2021).
pubmed: 34651172
pmcid: 8559220
doi: 10.1093/gigascience/giab071
Miller, K. L. et al. Multimodal population brain imaging in the UK Biobank prospective epidemiological study. Nat. Neurosci. 19, 1523–1536 (2016).
pubmed: 27643430
pmcid: 5086094
doi: 10.1038/nn.4393
Deco, G. & Corbetta, M. The Dynamical Balance of the Brain at Rest. Neuroscientist 17, 107–123 (2011).
pubmed: 21196530
doi: 10.1177/1073858409354384
Friston, K. J. Functional and effective connectivity: a review. Brain Connect. 1, 13–36 (2011).
pubmed: 22432952
doi: 10.1089/brain.2011.0008
Friston, K. J., Mechelli, A., Turner, R. & Price, C. J. Nonlinear Responses in fMRI: The Balloon Model, Volterra Kernels, and Other Hemodynamics. NeuroImage 12, 466–477 (2000).
pubmed: 10988040
doi: 10.1006/nimg.2000.0630
Friston, K. J., Josephs, O., Rees, G. & Turner, R. Nonlinear event-related responses in fMRI. Magn. Reson. Med. 39, 41–52 (1998).
pubmed: 9438436
doi: 10.1002/mrm.1910390109
Churchill, N. W. et al. The suppression of scale-free fMRI brain dynamics across three different sources of effort: aging, task novelty and task difficulty. Sci. Rep. 6, 30895 (2016).
pubmed: 27498696
pmcid: 4976369
doi: 10.1038/srep30895
Gao, S., Mishne, G. & Scheinost, D. Nonlinear manifold learning in functional magnetic resonance imaging uncovers a low-dimensional space of brain dynamics. Hum. Brain Mapp. 42, 4510–4524 (2021).
pubmed: 34184812
pmcid: 8410525
doi: 10.1002/hbm.25561
Omidvarnia, A. et al. Temporal complexity of fMRI is reproducible and correlates with higher order cognition. NeuroImage 230, 117760 (2021).
pubmed: 33486124
doi: 10.1016/j.neuroimage.2021.117760
Saxe, G. N., Calderone, D. & Morales, L. J. Brain entropy and human intelligence: A resting-state fMRI study. PLOS ONE 13, e0191582 (2018).
pubmed: 29432427
pmcid: 5809019
doi: 10.1371/journal.pone.0191582
Wang, Z., Li, Y., Childress, A. R. & Detre, J. A. Brain Entropy Mapping Using fMRI. PLoS ONE 9, e89948 (2014).
pubmed: 24657999
pmcid: 3962327
doi: 10.1371/journal.pone.0089948
Power, J. D. et al. Methods to detect, characterize, and remove motion artifact in resting state fMRI. NeuroImage 84, 320–341 (2014).
Zou, Q.-H. et al. An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: Fractional ALFF. J. Neurosci. Methods 172, 137–141 (2008).
pubmed: 18501969
pmcid: 3902859
doi: 10.1016/j.jneumeth.2008.04.012
Deshpande, G., LaConte, S., Peltier, S. & Hu, X. Integrated local correlation: a new measure of local coherence in fMRI data. Hum. Brain Mapp. 30, 13–23 (2009).
pubmed: 17979117
doi: 10.1002/hbm.20482
Saad, Z. S. et al. Correcting brain-wide correlation differences in resting-state FMRI. Brain Connect. 3, 339–352 (2013).
pubmed: 23705677
pmcid: 3749702
doi: 10.1089/brain.2013.0156
Rubinov, M. & Sporns, O. Complex network measures of brain connectivity: uses and interpretations. NeuroImage 52, 1059–1069 (2010).
pubmed: 19819337
doi: 10.1016/j.neuroimage.2009.10.003
Hurst, H. E. Long-Term Storage Capacity of Reservoirs. Trans. Am. Soc. Civ. Eng. 116, 770–799 (1951).
doi: 10.1061/TACEAT.0006518
Fadlallah, B., Chen, B., Keil, A. & Príncipe, J. Weighted-permutation entropy: a complexity measure for time series incorporating amplitude information. Phys. Rev. E Stat. Nonlin. Soft Matter Phys. 87, 022911 (2013).
pubmed: 23496595
doi: 10.1103/PhysRevE.87.022911
Omidvarnia, A., Mesbah, M., Pedersen, M. & Jackson, G. Range Entropy: A Bridge between Signal Complexity and Self-Similarity. Entropy 20, 962 (2018).
pubmed: 33266686
pmcid: 7512560
doi: 10.3390/e20120962
Costa, M., Goldberger, A. L. & Peng, C.-K. Multiscale entropy analysis of complex physiologic time series. Phys. Rev. Lett. 89, 068102 (2002).
pubmed: 12190613
doi: 10.1103/PhysRevLett.89.068102
Dadi, K. et al. Benchmarking functional connectome-based predictive models for resting-state fMRI. NeuroImage 192, 115–134 (2019).
pubmed: 30836146
doi: 10.1016/j.neuroimage.2019.02.062
He, T. et al. Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics. NeuroImage 206, 116276 (2020).
pubmed: 31610298
doi: 10.1016/j.neuroimage.2019.116276
Fawns-Ritchie, C. & Deary, I. J. Reliability and validity of the UK Biobank cognitive tests. PLoS ONE 15, e0231627 (2020).
pubmed: 32310977
pmcid: 7170235
doi: 10.1371/journal.pone.0231627
Schulz, M.-A. et al. Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets. Nat. Commun. 11, 4238 (2020).
pubmed: 32843633
pmcid: 7447816
doi: 10.1038/s41467-020-18037-z
Bassett, D. S. & Gazzaniga, M. S. Understanding complexity in the human brain. Trends Cogn. Sci. 15, 200–209 (2011).
pubmed: 21497128
pmcid: 3170818
doi: 10.1016/j.tics.2011.03.006
CIUCIU, P., Varoquaux, G., Abry, P., Sadaghiani, S. & Kleinschmidt, A. Scale-free and multifractal properties of fMRI signals during rest and task. Front. Physiol. 3, 186 (2012).
pubmed: 22715328
pmcid: 3375626
doi: 10.3389/fphys.2012.00186
He, B. J. Scale-Free Properties of the Functional Magnetic Resonance Imaging Signal during Rest and Task. J. Neurosci. 31, 13786–13795 (2011).
pubmed: 21957241
pmcid: 3197021
doi: 10.1523/JNEUROSCI.2111-11.2011
Liégeois, R. et al. Resting brain dynamics at different timescales capture distinct aspects of human behavior. Nat. Commun. 10, 2317 (2019).
pubmed: 31127095
pmcid: 6534566
doi: 10.1038/s41467-019-10317-7
Michon, K. J., Khammash, D., Simmonite, M., Hamlin, A. M. & Polk, T. A. Person-specific and precision neuroimaging: Current methods and future directions. NeuroImage 263, 119589 (2022).
pubmed: 36030062
doi: 10.1016/j.neuroimage.2022.119589
Tejavibulya, L. et al. Predicting the future of neuroimaging predictive models in mental health. Mol. Psychiatry 27, 3129–3137 (2022).
pubmed: 35697759
pmcid: 9708554
doi: 10.1038/s41380-022-01635-2
Dhamala, E., Jamison, K. W., Jaywant, A., Dennis, S. & Kuceyeski, A. Distinct functional and structural connections predict crystallised and fluid cognition in healthy adults. Hum. Brain Mapp. 42, 3102–3118 (2021).
pubmed: 33830577
pmcid: 8193532
doi: 10.1002/hbm.25420
Mansour, L. S., Tian, Y., Yeo, B. T. T., Cropley, V. & Zalesky, A. High-resolution connectomic fingerprints: Mapping neural identity and behavior. NeuroImage 229, 117695 (2021).
doi: 10.1016/j.neuroimage.2020.117695
Rasero, J., Sentis, A. I., Yeh, F.-C. & Verstynen, T. Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability. PLOS Comput. Biol. 17, e1008347 (2021).
pubmed: 33667224
pmcid: 7984650
doi: 10.1371/journal.pcbi.1008347
Van Essen, D. C. et al. The Human Connectome Project: a data acquisition perspective. NeuroImage 62, 2222–2231 (2012).
pubmed: 22366334
doi: 10.1016/j.neuroimage.2012.02.018
Cui, Z. & Gong, G. The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features. NeuroImage 178, 622–637 (2018).
pubmed: 29870817
doi: 10.1016/j.neuroimage.2018.06.001
Berg, A. T. et al. Revised terminology and concepts for organization of seizures and epilepsies: report of the ILAE Commission on Classification and Terminology, 2005-2009. Epilepsia 51, 676–685 (2010).
pubmed: 20196795
doi: 10.1111/j.1528-1167.2010.02522.x
Vieira, B. H. et al. On the prediction of human intelligence from neuroimaging: A systematic review of methods and reporting. Intelligence 93, 101654 (2022).
doi: 10.1016/j.intell.2022.101654
Murphy, K., Bodurka, J. & Bandettini, P. A. How long to scan? The relationship between fMRI temporal signal to noise and necessary scan duration. NeuroImage 34, 565–574 (2007).
pubmed: 17126038
doi: 10.1016/j.neuroimage.2006.09.032
Gell, M. et al. The Burden of Reliability: How Measurement Noise Limits Brain-Behaviour Predictions. 2023.02.09.527898. Preprint at https://doi.org/10.1101/2023.02.09.527898 (2023).
Halchenko, Y. O. et al. DataLad: distributed system for joint management of code, data, and their relationship. J. Open Source Softw. 6, 3262 (2021).
doi: 10.21105/joss.03262
Beckmann, C. F. & Smith, S. M. Probabilistic independent component analysis for functional magnetic resonance imaging. IEEE Trans. Med. Imaging 23, 137–152 (2004).
pubmed: 14964560
doi: 10.1109/TMI.2003.822821
Griffanti, L. et al. ICA-based artefact removal and accelerated fMRI acquisition for improved resting state network imaging. NeuroImage 95, 232–247 (2014).
pubmed: 24657355
doi: 10.1016/j.neuroimage.2014.03.034
Salimi-Khorshidi, G. et al. Automatic denoising of functional MRI data: combining independent component analysis and hierarchical fusion of classifiers. NeuroImage 90, 449–468 (2014).
pubmed: 24389422
doi: 10.1016/j.neuroimage.2013.11.046
Schaefer, A. et al. Local-Global Parcellation of the Human Cerebral Cortex from Intrinsic Functional Connectivity MRI. Cereb. Cortex N. Y. N. 1991 28, 3095–3114 (2018).
Glasser, M. F. et al. A multi-modal parcellation of human cerebral cortex. Nature 536, 171–178 (2016).
pubmed: 27437579
pmcid: 4990127
doi: 10.1038/nature18933
Gaser, C. et al. CAT—A Computational Anatomy Toolbox for the Analysis of Structural MRI Data. 2022.06.11.495736. Preprint at https://doi.org/10.1101/2022.06.11.495736 (2022).
Campbell, O. L. & Weber, A. M. Monofractal analysis of functional magnetic resonance imaging: An introductory review. Hum. Brain Mapp. 43, 2693–2706 (2022).
pubmed: 35266236
pmcid: 9057087
doi: 10.1002/hbm.25801
Bandt, C. & Pompe, B. Permutation entropy: a natural complexity measure for time series. Phys. Rev. Lett. 88, 174102 (2002).
pubmed: 12005759
doi: 10.1103/PhysRevLett.88.174102
Pincus, S. M. Approximate entropy as a measure of system complexity. Proc. Natl Acad. Sci. 88, 2297–2301 (1991).
pubmed: 11607165
pmcid: 51218
doi: 10.1073/pnas.88.6.2297
Richman, J. S. & Moorman, J. R. Physiological time-series analysis using approximate entropy and sample entropy. Am. J. Physiol. Heart Circ. Physiol. 278, H2039–H2049 (2000).
pubmed: 10843903
doi: 10.1152/ajpheart.2000.278.6.H2039
Joachims, T. Fast Heuristics For The Estimation Of the C Constant Of A Support Vector Machine. SVM light https://search.r-project.org/CRAN/refmans/LiblineaR/html/heuristicC.html (2002).
Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. Preprint at https://doi.org/10.48550/arXiv.1201.0490 (2018).
Chyzhyk, D., Varoquaux, G., Milham, M. & Thirion, B. How to remove or control confounds in predictive models, with applications to brain biomarkers. GigaScience 11, giac014 (2022).
pubmed: 35277962
pmcid: 8917515
doi: 10.1093/gigascience/giac014
Amico, E. & Goñi, J. The quest for identifiability in human functional connectomes. Sci. Rep. 8, 8254 (2018).
pubmed: 29844466
pmcid: 5973945
doi: 10.1038/s41598-018-25089-1