CoChat

Predicting individualized clinical measures by a generalized prediction framework and multimodal fusion of MRI data

Open access
Meng, Xing, Jiang, Rongtao, Lin, Dongdong, Bustillo, Juan, Jones, Thomas, Chen, Jiayu, Yu, Qingbao, Du, Yuhui, Zhang, Yu, Jiang, Tianzi, Sui, Jing, Calhoun, Vince D. · 2017 · NeuroImage
Cited by 106

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

Neuroimaging techniques have greatly enhanced the understanding of neurodiversity (human brain variation across individuals) in both health and disease. The ultimate goal of using brain imaging biomarkers is to perform individualized predictions. Here we proposed a generalized framework that can predict explicit values of the targeted measures by taking advantage of joint information from multiple modalities. This framework also enables whole brain voxel‐wise searching by combining multivariate techniques such as ReliefF, clustering, correlation‐based feature selection and multiple regression models, which is more flexible and can achieve better prediction performance than alternative atlas‐based methods. For 50 healthy controls and 47 schizophrenia patients, three kinds of features derived from resting‐state fMRI (fALFF), sMRI (gray matter) and DTI (fractional anisotropy) were extracted and fed into a regression model, achieving high prediction for both cognitive scores (MCCB composite r = 0.7033, MCCB social cognition r = 0.7084) and symptomatic scores (positive and negative syndrome scale [PANSS] positive r = 0.7785, PANSS negative r = 0.7804). Moreover, the brain areas likely responsible for cognitive deficits of schizophrenia, including middle temporal gyrus, dorsolateral prefrontal cortex, striatum, cuneus and cerebellum, were located with different weights, as well as regions predicting PANSS symptoms, including thalamus, striatum and inferior parietal lobule, pinpointing the potential neuromarkers. Finally, compared to a single modality, multimodal combination achieves higher prediction accuracy and enables individualized prediction on multiple clinical measures. There is more work to be done, but the current results highlight the potential utility of multimodal brain imaging biomarkers to eventually inform clinical decision‐making. HighlightsA generalized framework to predict explicit values of clinical measures using MRI.Locating imaging biomarkers/neuromarkers by whole brain voxel‐wise searching.A prediction model incorporating multi‐stage feature selection and multimodal info.May potentially help clinician to make early intervention for mental disorders.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.neuroimage.2016.05.026

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 18 references

Research works printed but not linked: 90

  1. Aharoni, 2013, Neuroprediction of future rearrest, Proc. Natl. Acad. Sci. U. S. A., 110, 6223, 10.1073/pnas.1219302110 · DOI · Paper page
  2. Allen, 2011, A baseline for the multivariate comparison of resting-state networks, Front. Syst. Neurosci., 5, 2, 10.3389/fnsys.2011.00002 · DOI · Paper page
  3. Andreasen, 1998, “Cognitive dysmetria” as an integrative theory of schizophrenia: a dysfunction in cortical–subcortical–cerebellar circuitry?, Schizophr. Bull., 24, 203, 10.1093/oxfordjournals.schbul.a033321 · DOI · Paper page
  4. Argyelan, 2015, Abnormal resting state FMRI activity predicts processing speed deficits in first-episode psychosis, Neuropsychopharmacology, 40, 1631, 10.1038/npp.2015.7 · DOI
  5. August, 2011, The MATRICS Consensus Cognitive Battery (MCCB): clinical and cognitive correlates, Schizophr. Res., 134, 76, 10.1016/j.schres.2011.10.015 · DOI · Paper page
  6. Binder, 2009, Where is the semantic system? A critical review and meta-analysis of 120 functional neuroimaging studies, Cereb. Cortex, 19, 2767, 10.1093/cercor/bhp055 · DOI · Paper page
  7. Boksman, 2005, A 4.0-T fMRI study of brain connectivity during word fluency in first-episode schizophrenia, Schizophr. Res., 75, 247, 10.1016/j.schres.2004.09.025 · DOI
  8. Burton, 2013, Factor structure of the MATRICS Consensus Cognitive Battery (MCCB) in schizophrenia, Schizophr. Res., 146, 244, 10.1016/j.schres.2013.02.026 · DOI
  9. Calhoun, 2009, Feature-based fusion of medical imaging data, IEEE Trans. Inf. Technol. Biomed., 13, 711, 10.1109/TITB.2008.923773 · DOI · Paper page
  10. Calhoun, 2012, Extracting Intrinsic Functional Networks with Feature-based Group Independent Component Analysis, Psychometrika, 1
  11. Calhoun, 2016, Multimodal fusion of brain imaging data: a key to finding the missing link(s) in complex mental illness, Biol. Psychiatry: Cogn. Neurosci. Neuroimaging
  12. Cerasa, 2012, Multimodal MRI in neurodegenerative disorders, Neurol. Res. Int., 2012, 287891, 10.1155/2012/287891 · DOI
  13. Cheng, 2009, Subband weighting with pixel connectivity for 3-D wavelet coding, IEEE Trans. Image Process., 18, 52, 10.1109/TIP.2008.2007067 · doi:10.1109/tip.2008.2007067
  14. Choi, 2012, Phase-specific brain change of spatial working memory processing in genetic and ultra-high risk groups of schizophrenia, Schizophr. Bull., 38, 1189, 10.1093/schbul/sbr038 · DOI
  15. Clark, 2014, Reduced fMRI activity predicts relapse in patients recovering from stimulant dependence, Hum. Brain Mapp., 35, 414, 10.1002/hbm.22184 · DOI · Paper page
  16. Cuthbert, 2014, The RDoC framework: continuing commentary, World Psychiatry, 13, 196, 10.1002/wps.20140 · DOI
  17. Delvecchio, 2013, Evidence of diagnostic specificity in the neural correlates of facial affect processing in bipolar disorder and schizophrenia: a meta-analysis of functional imaging studies, Psychol. Med., 43, 553, 10.1017/S0033291712001432 · DOI · Paper page
  18. Deng, 2010, Robust relief-feature weighting, margin maximization, and fuzzy optimization, IEEE Trans. Fuzzy Syst., 18, 726, 10.1109/TFUZZ.2010.2047947 · DOI
  19. Dumpuri, 2010, A fast and efficient method to compensate for brain shift for tumor resection therapies measured between preoperative and postoperative tomograms, IEEE Trans. Biomed. Eng., 57, 1285, 10.1109/TBME.2009.2039643 · doi:10.1109/tbme.2009.2039643
  20. Edwards, 2011, The value of the CRB65 score to predict mortality in exacerbations of COPD requiring hospital admission, Respirology, 16, 625, 10.1111/j.1440-1843.2011.01926.x · DOI
  21. Eichele, 2008, Prediction of human errors by maladaptive changes in event-related brain networks, Proc. Natl. Acad. Sci. U. S. A., 105, 6173, 10.1073/pnas.0708965105 · DOI · Paper page
  22. Epstein, 2014, White matter abnormalities and cognitive impairment in early-onset schizophrenia-spectrum disorders, J. Am. Acad. Child Adolesc. Psychiatry, 53, e361
  23. Fletcher, 1999, Abnormal cingulate modulation of fronto-temporal connectivity in schizophrenia, NeuroImage, 9, 337, 10.1006/nimg.1998.0411 · DOI · Paper page
  24. Frank, 2004, Data mining in bioinformatics using Weka, Bioinformatics, 20, 2479, 10.1093/bioinformatics/bth261 · DOI · Paper page
  25. Freire, 2002, What is the best similarity measure for motion correction in fMRI time series?, IEEE Trans. Med. Imaging, 21, 470, 10.1109/TMI.2002.1009383 · DOI · Paper page
  26. Friston, 1995, Spatial registration and normalization of images, Hum. Brain Mapp., 2, 165, 10.1002/hbm.460030303 · DOI · Paper page
  27. Gabrieli, 2015, Prediction as a humanitarian and pragmatic contribution from human cognitive neuroscience, Neuron, 85, 11, 10.1016/j.neuron.2014.10.047 · DOI · Paper page
  28. Gudmundsson, 2012, Test–retest reliability and feature selection in physiological time series classification, Comput. Methods Prog. Biomed., 105, 50, 10.1016/j.cmpb.2010.08.005 · doi:10.1016/j.cmpb.2010.08.005
  29. Hadley, 2014, Ventral tegmental area/midbrain functional connectivity and response to antipsychotic medication in schizophrenia, Neuropsychopharmacology, 39, 1020, 10.1038/npp.2013.305 · DOI
  30. Hardoy, 2004, Impairment in visual and spatial perception in schizophrenia and delusional disorder, Psychiatry Res., 127, 163, 10.1016/j.psychres.2004.03.002 · DOI
  31. Hazlett, 2014, Visual–spatial working memory performance and temporal gray matter volume predict schizotypal personality disorder group membership, Schizophr. Res., 152, 350, 10.1016/j.schres.2013.12.006 · DOI
  32. Hiyoshi-Taniguchi, 2015, The uncinate fasciculus as a predictor of conversion from amnestic mild cognitive impairment to Alzheimer disease, J. Neuroimaging, 25, 748, 10.1111/jon.12196 · DOI
  33. Ho, 2011, Long-term antipsychotic treatment and brain volumes: a longitudinal study of first-episode schizophrenia, Arch. Gen. Psychiatry, 68, 128, 10.1001/archgenpsychiatry.2010.199 · DOI · Paper page
  34. Hutcheson, 2014, Basal ganglia volume in unmedicated patients with schizophrenia is associated with treatment response to antipsychotic medication, Psychiatry Res., 221, 6, 10.1016/j.pscychresns.2013.10.002 · DOI
  35. Hutton, 2009, A comparison between voxel-based cortical thickness and voxel-based morphometry in normal aging, NeuroImage, 48, 371, 10.1016/j.neuroimage.2009.06.043 · DOI · Paper page
  36. Jakulin, 2003, Attribute interactions in medical data analysis, Artif. Intell. Med. Proc., 2780, 229, 10.1007/978-3-540-39907-0_32 · DOI
  37. Johnston, 2015, Structural MRI-Based Predictions in Patients with Treatment-Refractory Depression (TRD), PLoS One, 10, 10.1371/journal.pone.0132958 · DOI · Paper page
  38. Kawada, 2009, Brain volume and dysexecutive behavior in schizophrenia, Prog. Neuro-Psychopharmacol. Biol. Psychiatry, 33, 1255, 10.1016/j.pnpbp.2009.07.014 · DOI
  39. Kay, 1987, The positive and negative syndrome scale (PANSS) for schizophrenia, Schizophr. Bull., 13, 261, 10.1093/schbul/13.2.261 · DOI · Paper page
  40. Kim, 2015, Emotional effect on cognitive control in implicit memory tasks in patients with schizophrenia, Neuroreport, 26, 647, 10.1097/WNR.0000000000000405 · DOI
  41. Kohavi, 1997, Wrappers for feature subset selection, Artif. Intell., 97, 273, 10.1016/S0004-3702(97)00043-X · DOI · Paper page
  42. Langley, 1995, Applications of machine learning and rule induction, Commun. ACM, 38, 55, 10.1145/219717.219768 · DOI · Paper page
  43. Leergaard, 2012, Mapping the connectome: multi-level analysis of brain connectivity, Front. Neuroinform., 6, 14, 10.3389/fninf.2012.00014 · DOI
  44. Lui, 2010, Short-term effects of antipsychotic treatment on cerebral function in drug-naive first-episode schizophrenia revealed by “resting state” functional magnetic resonance imaging, Arch. Gen. Psychiatry, 67, 783, 10.1001/archgenpsychiatry.2010.84 · DOI · Paper page
  45. Makinen, 2008, Negative symptoms in schizophrenia: a review, Nord. J. Psychiatry, 62, 334, 10.1080/08039480801959307 · DOI · Paper page
  46. Mark Hall, 2009, The WEKA data mining software: an update, SIGKDD Explor., 11
  47. Mars, 2011, Diffusion-weighted imaging tractography-based parcellation of the human parietal cortex and comparison with human and macaque resting-state functional connectivity, J. Neurosci., 31, 4087, 10.1523/JNEUROSCI.5102-10.2011 · DOI · Paper page
  48. Meshkin, 2009, Prediction of Relative Solvent Accessibility Using Pace Regression, Excli J., 8, 211
  49. Mohammadi, 2013, A comparative study on remote tracking of Parkinsons disease progression using data mining methods, CoRR, 3
  50. Mori, 2000, Automated anatomical labeling of the bronchial branch and its application to the virtual bronchoscopy system, IEEE Trans. Med. Imaging, 19, 103, 10.1109/42.836370 · doi:10.1109/42.836370
  51. Moulis, 2014, Imaging in Erdheim–Chester disease: classic features and new insights, Clin. Exp. Rheumatol., 32, 410
  52. Mwangi, 2012, Prediction of illness severity in patients with major depression using structural MR brain scans, J. Magn. Reson. Imaging, 35, 64, 10.1002/jmri.22806 · DOI · Paper page
  53. Natsopoulos, 1998, Do the hands talk on mind's behalf? Differences in language ability between left- and right-handed children, Brain Lang., 64, 182, 10.1006/brln.1998.1970 · doi:10.1006/brln.1998.1970
  54. Oakes, 2007, Integrating VBM into the General Linear Model with voxelwise anatomical covariates, NeuroImage, 34, 500, 10.1016/j.neuroimage.2006.10.007 · DOI · Paper page
  55. Oto, 2011, Diffusion-weighted and dynamic contrast-enhanced MRI of prostate cancer: correlation of quantitative MR parameters with Gleason score and tumor angiogenesis, AJR Am. J. Roentgenol., 197, 1382, 10.2214/AJR.11.6861 · DOI · Paper page
  56. Perlstein, 2001, Relation of prefrontal cortex dysfunction to working memory and symptoms in schizophrenia, Am. J. Psychiatry, 158, 1105, 10.1176/appi.ajp.158.7.1105 · DOI · Paper page
  57. Qiu, 2011, Neuroanatomical circuitry associated with exploratory eye movement in schizophrenia: a voxel-based morphometric study, PLoS One, 6, 10.1371/journal.pone.0025805 · DOI
  58. Radua, 2010, Neural response to specific components of fearful faces in healthy and schizophrenic adults, NeuroImage, 49, 939, 10.1016/j.neuroimage.2009.08.030 · DOI · Paper page
  59. Radua, 2014, Validity of modulation and optimal settings for advanced voxel-based morphometry, NeuroImage, 86, 81, 10.1016/j.neuroimage.2013.07.084 · DOI
  60. Salgado-Pineda, 2004, Decreased cerebral activation during CPT performance: structural and functional deficits in schizophrenic patients, NeuroImage, 21, 840, 10.1016/j.neuroimage.2003.10.027 · DOI
  61. Schultz, 2012, Multimodal functional and structural imaging investigations in psychosis research, Eur. Arch. Psychiatry Clin. Neurosci., 262, S97, 10.1007/s00406-012-0360-5 · DOI
  62. Segall, 2009, Voxel-based morphometric multisite collaborative study on schizophrenia, Schizophr. Bull., 35, 82, 10.1093/schbul/sbn150 · DOI · Paper page
  63. Serra, 2012, White matter damage along the uncinate fasciculus contributes to cognitive decline in AD and DLB, Curr. Alzheimer Res., 9, 326, 10.2174/156720512800107555 · DOI · Paper page
  64. Shaffer, 2013, Predicting cognitive decline in subjects at risk for Alzheimer disease by using combined cerebrospinal fluid, MR imaging, and PET biomarkers, Radiology, 266, 583, 10.1148/radiol.12120010 · DOI · Paper page
  65. Shen, 2014, Genetic analysis of quantitative phenotypes in AD and MCI: imaging, cognition and biomarkers, Brain Imaging Behav., 8, 183, 10.1007/s11682-013-9262-z · DOI · Paper page
  66. Simpson, 2014, Liver planning software accurately predicts postoperative liver volume and measures early regeneration, J. Am. Coll. Surg., 219, 199, 10.1016/j.jamcollsurg.2014.02.027 · DOI
  67. Stokes, 2012, Application of a spatially-weighted Relief algorithm for ranking genetic predictors of disease, BioData Min., 5, 20, 10.1186/1756-0381-5-20 · DOI
  68. Stonnington, 2010, Predicting clinical scores from magnetic resonance scans in Alzheimer's disease, NeuroImage, 51, 1405, 10.1016/j.neuroimage.2010.03.051 · DOI · Paper page
  69. Sui, 2011, Discriminating schizophrenia and bipolar disorder by fusing fMRI and DTI in a multimodal CCA+ joint ICA model, NeuroImage, 57, 839, 10.1016/j.neuroimage.2011.05.055 · DOI · Paper page
  70. Sui, 2012, A review of multivariate methods for multimodal fusion of brain imaging data, J. Neurosci. Methods, 204, 68, 10.1016/j.jneumeth.2011.10.031 · DOI · Paper page
  71. Sui, 2015, In Search of multimodal neuroimaging biomarkers of cognitive deficits in schizophrenia, Biol. Psychiatry, 10.1016/j.biopsych.2015.02.017 · DOI · Paper page
  72. Sun, 2007, Iterative RELIEF for feature weighting: algorithms, theories, and applications, IEEE Trans. Pattern Anal. Mach. Intell., 29, 1035, 10.1109/TPAMI.2007.1093 · DOI · Paper page
  73. Szeszko, 2014, White matter changes associated with antipsychotic treatment in first-episode psychosis, Neuropsychopharmacology, 39, 1324, 10.1038/npp.2013.288 · DOI
  74. Technow, 2014, Stress sensitivity interacts with depression history to predict depressive symptoms among youth: prospective changes following first depression onset, J. Abnorm. Child Psychol.
  75. Tibshirani, 1996, Regression shrinkage and selection via the lasso, J. R. Stat. Soc. Ser. B Methodol., 267, 10.1111/j.2517-6161.1996.tb02080.x · DOI · Paper page
  76. Tripoliti, 2010, A six stage approach for the diagnosis of the Alzheimer's disease based on fMRI data, J. Biomed. Inform., 43, 307, 10.1016/j.jbi.2009.10.004 · DOI
  77. Tsang, 2009, Frontoparietal white matter diffusion properties predict mental arithmetic skills in children, Proc. Natl. Acad. Sci. U. S. A., 106, 22546, 10.1073/pnas.0906094106 · DOI · Paper page
  78. van Waarde, 2015, A functional MRI marker may predict the outcome of electroconvulsive therapy in severe and treatment-resistant depression, Mol. Psychiatry, 20, 609, 10.1038/mp.2014.78 · DOI · Paper page
  79. Vittengl, 2014, Replication and extension: separate personality traits from states to predict depression, J. Personal. Disord., 28, 225, 10.1521/pedi_2013_27_117 · DOI
  80. Wan, 2014, Identifying the neuroanatomical basis of cognitive impairment in Alzheimer's disease by correlation- and nonlinearity-aware sparse Bayesian learning, IEEE Trans. Med. Imaging, 33, 1475, 10.1109/TMI.2014.2314712 · DOI · Paper page
  81. Wang, 2011, Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance, Proc. IEEE Int. Conf. Comput. Vis., 557
  82. Wang, 2011, Identifying AD-sensitive and cognition-relevant imaging biomarkers via joint classification and regression, Med. Image Comput. Comput. Assist. Interv., 14, 115
  83. Wang, 2015, Three dysconnectivity patterns in treatment-resistant schizophrenia patients and their unaffected siblings, NeuroImage Clin., 8, 95, 10.1016/j.nicl.2015.03.017 · DOI
  84. White, 2001, Anatomic and functional variability: the effects of filter size in group fMRI data analysis, NeuroImage, 13, 577, 10.1006/nimg.2000.0716 · DOI
  85. Wilhelm-Benartzi, 2013, Review of processing and analysis methods for DNA methylation array data, Br. J. Cancer, 109, 1394, 10.1038/bjc.2013.496 · DOI · Paper page
  86. Willette, 2014, Prognostic classification of mild cognitive impairment and Alzheimer's disease: MRI independent component analysis, Psychiatry Res., 224, 81, 10.1016/j.pscychresns.2014.08.005 · DOI · Paper page
  87. Wu, 2015, Connectivity-based whole brain dual parcellation by group ICA reveals tract structures and decreased connectivity in schizophrenia, Hum. Brain Mapp., 36, 4681, 10.1002/hbm.22945 · DOI
  88. Yan, 2013, Network-guided sparse learning for predicting cognitive outcomes from MRI measures, Multimodal Brain Image Anal., 8159, 202, 10.1007/978-3-319-02126-3_20 · DOI
  89. Ye, 2012, Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data, BMC Neurol., 12, 46, 10.1186/1471-2377-12-46 · DOI · Paper page
  90. Zhang, 2012, Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer's disease, NeuroImage, 59, 895, 10.1016/j.neuroimage.2011.09.069 · DOI · Paper page

Cited by

Metadata

Authors
Meng, X., Jiang, R., Lin, D., Bustillo, J., Jones, T., Chen, J., Yu, Q., Du, Y., Zhang, Y., Jiang, T., Sui, J., & Calhoun, V. D.
Venue
NeuroImage
Publisher
Elsevier BV
Published
2017-01
Volume
145
Issue
Pt B
Pages
218-229
ISSN
1053-8119 (ISSN-L)
OpenAlex
W2354785768
Cited by
106
References
18
FWCI
8.62
Type
journal article
Language
en
Open access
bronze
Funders
  • National Institutes of Health (P20GM103472, R01EB006841, R01MH084898)
  • National Natural Science Foundation of China (81471367, XDB02060005)
  • Chinese Academy of Sciences

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.