Display options
Cite
Elad D, Cetin-Karayumak S, Zhang F, et al. Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification. Hum Brain Mapp. 2021;42(14):4658-4670doi: 10.1002/hbm.25574.
Elad, D., Cetin-Karayumak, S., Zhang, F., Cho, K. I. K., Lyall, A. E., Seitz-Holland, J., Ben-Ari, R., Pearlson, G. D., Tamminga, C. A., Sweeney, J. A., Clementz, B. A., Schretlen, D. J., Viher, P. V., Stegmayer, K., Walther, S., Lee, J., Crow, T. J., James, A., Voineskos, A. N., Buchanan, R. W., Szeszko, P. R., Malhotra, A. K., Keshavan, M. S., Shenton, M. E., Rathi, Y., Bouix, S., Sochen, N., Kubicki, M. R., & Pasternak, O. (2021). Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification. Human brain mapping, 42(14), 4658-4670. https://doi.org/10.1002/hbm.25574
Elad, Doron, et al. "Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification." Human brain mapping vol. 42,14 (2021): 4658-4670. doi: https://doi.org/10.1002/hbm.25574
Elad D, Cetin-Karayumak S, Zhang F, Cho KIK, Lyall AE, Seitz-Holland J, Ben-Ari R, Pearlson GD, Tamminga CA, Sweeney JA, Clementz BA, Schretlen DJ, Viher PV, Stegmayer K, Walther S, Lee J, Crow TJ, James A, Voineskos AN, Buchanan RW, Szeszko PR, Malhotra AK, Keshavan MS, Shenton ME, Rathi Y, Bouix S, Sochen N, Kubicki MR, Pasternak O. Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification. Hum Brain Mapp. 2021 Oct 01;42(14):4658-4670. doi: 10.1002/hbm.25574. Epub 2021 Jul 29. PMID: 34322947; PMCID: PMC8410550.
Copy Download .nbib Format: NLM
Share it on

Hum Brain Mapp. 2021 Oct 01;42(14):4658-4670. doi: 10.1002/hbm.25574. Epub 2021 Jul 29.

Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification.

Human brain mapping

Doron Elad, Suheyla Cetin-Karayumak, Fan Zhang, Kang Ik K Cho, Amanda E Lyall, Johanna Seitz-Holland, Rami Ben-Ari, Godfrey D Pearlson, Carol A Tamminga, John A Sweeney, Brett A Clementz, David J Schretlen, Petra Verena Viher, Katharina Stegmayer, Sebastian Walther, Jungsun Lee, Tim J Crow, Anthony James, Aristotle N Voineskos, Robert W Buchanan, Philip R Szeszko, Anil K Malhotra, Matcheri S Keshavan, Martha E Shenton, Yogesh Rathi, Sylvain Bouix, Nir Sochen, Marek R Kubicki, Ofer Pasternak

Affiliations

  1. Department of Mathematics, Tel-Aviv University, Tel-Aviv, Israel.
  2. Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
  3. Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
  4. Departments of Psychiatry and Neuroscience, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA.
  5. Department of Psychiatry, University Hospital, Ludwig Maximilian University of Munich, Munich, Germany.
  6. IBM Research AI, Haifa, Israel.
  7. Department of Psychiatry, Yale University, New Haven, Connecticut, USA.
  8. Department of Psychiatry, UT Southwestern Medical Center, Dallas, Texas, USA.
  9. Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati, Cincinnati, Ohio, USA.
  10. Departments of Psychology and Neuroscience, Bio-Imaging Research Center, University of Georgia, Athens, Georgia, USA.
  11. Department of Psychiatry and Behavioral Sciences, Morgan Department of Radiology and Radiological Science, Johns Hopkins Medical Institutions, Baltimore, Maryland, USA.
  12. Translational Research Center, University Hospital of Psychiatry, University of Bern, Bern, Switzerland.
  13. Department of Psychiatry, University of Ulsan College of Medicine, Asan Medical Center, Seoul, South Korea.
  14. Department of Psychiatry, SANE POWIC, Warneford Hospital, University of Oxford, Oxford, UK.
  15. Centre for Addiction and Mental Health, Department of Psychiatry, University of Toronto, Toronto, Canada.
  16. Maryland Psychiatric Research Center, Department of Psychiatry, University of Maryland School of Medicine, Baltimore, Maryland, USA.
  17. Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
  18. Mental Illness Research, Education and Clinical Center, James J. Peters VA Medical Center, New York, New York, USA.
  19. The Feinstein Institute for Medical Research and Zucker Hillside Hospital, Manhasset, New York, USA.
  20. Department of Psychiatry, Beth Israel Deaconess Medical Centre, Harvard Medical School, Boston, Massachusetts, USA.

PMID: 34322947 PMCID: PMC8410550 DOI: 10.1002/hbm.25574

Abstract

Diffusion MRI studies consistently report group differences in white matter between individuals diagnosed with schizophrenia and healthy controls. Nevertheless, the abnormalities found at the group-level are often not observed at the individual level. Among the different approaches aiming to study white matter abnormalities at the subject level, normative modeling analysis takes a step towards subject-level predictions by identifying affected brain locations in individual subjects based on extreme deviations from a normative range. Here, we leveraged a large harmonized diffusion MRI dataset from 512 healthy controls and 601 individuals diagnosed with schizophrenia, to study whether normative modeling can improve subject-level predictions from a binary classifier. To this aim, individual deviations from a normative model of standard (fractional anisotropy) and advanced (free-water) dMRI measures, were calculated by means of age and sex-adjusted z-scores relative to control data, in 18 white matter regions. Even though larger effect sizes are found when testing for group differences in z-scores than are found with raw values (p < .001), predictions based on summary z-score measures achieved low predictive power (AUC < 0.63). Instead, we find that combining information from the different white matter tracts, while using multiple imaging measures simultaneously, improves prediction performance (the best predictor achieved AUC = 0.726). Our findings suggest that extreme deviations from a normative model are not optimal features for prediction. However, including the complete distribution of deviations across multiple imaging measures improves prediction, and could aid in subject-level classification.

© 2021 The Authors. Human Brain Mapping published by Wiley Periodicals LLC.

Keywords: diffusion magnetic resonance imaging; machine learning; precision medicine; schizophrenia; white matter

References

  1. Schizophr Res. 2015 Jan;161(1):113-8 - PubMed
  2. Med Image Comput Comput Assist Interv. 2010;13(Pt 1):657-65 - PubMed
  3. Brain. 2020 Mar 1;143(3):1027-1038 - PubMed
  4. Mol Psychiatry. 2020 Dec;25(12):3208-3219 - PubMed
  5. Hum Brain Mapp. 2021 Jun 1;42(8):2546-2555 - PubMed
  6. Med Image Comput Comput Assist Interv. 2012;15(Pt 2):305-12 - PubMed
  7. Schizophr Res. 2017 Nov;189:153-161 - PubMed
  8. J Psychiatr Res. 2007 Jan-Feb;41(1-2):15-30 - PubMed
  9. J Neurosurg. 2014 Apr;120(4):873-81 - PubMed
  10. Cereb Cortex. 2021 Jan 1;31(1):201-212 - PubMed
  11. Neuroimage. 2014 Feb 1;86:544-53 - PubMed
  12. Neuroimage. 2014 May 1;91:177-86 - PubMed
  13. Neuroimage Clin. 2017 Jan 06;14:54-66 - PubMed
  14. Neuroimage. 2019 Jan 1;184:180-200 - PubMed
  15. Biol Psychiatry. 2016 Oct 1;80(7):552-61 - PubMed
  16. Psychiatry Res. 2009 Nov 30;174(2):110-5 - PubMed
  17. Biophys J. 1994 Jan;66(1):259-67 - PubMed
  18. Am J Psychiatry. 2019 Oct 1;176(10):820-828 - PubMed
  19. J Neurosci. 2012 Nov 28;32(48):17365-72 - PubMed
  20. Schizophr Bull. 2017 Mar 1;43(2):425-435 - PubMed
  21. World Psychiatry. 2019 Feb;18(1):67-76 - PubMed
  22. Neuroimage Clin. 2018 Feb 12;18:467-474 - PubMed
  23. Neurology. 2020 Mar 10;94(10):e1021-e1026 - PubMed
  24. Mol Psychiatry. 2018 May;23(5):1261-1269 - PubMed
  25. Magn Reson Med. 2003 Nov;50(5):1077-88 - PubMed
  26. Am J Psychiatry. 2013 Aug;170(8):886-98 - PubMed
  27. BMC Psychiatry. 2018 Apr 10;18(1):97 - PubMed
  28. Schizophr Res. 2019 Feb;204:238-244 - PubMed
  29. Am J Psychiatry. 2013 Nov;170(11):1275-84 - PubMed
  30. Comput Math Methods Med. 2013;2013:867924 - PubMed
  31. Hum Brain Mapp. 2011 Jan;32(1):1-9 - PubMed
  32. JAMA Psychiatry. 2018 Nov 1;75(11):1146-1155 - PubMed
  33. Neuroimage. 2020 Nov 1;221:117128 - PubMed
  34. Am J Psychiatry. 2013 Nov;170(11):1263-74 - PubMed
  35. Neuroimage. 2011 Feb 1;54(3):2033-44 - PubMed
  36. Cereb Cortex. 2020 Jul 30;30(9):4800-4810 - PubMed
  37. Hum Brain Mapp. 2021 Oct 1;42(14):4658-4670 - PubMed
  38. Biol Psychiatry. 2014 Sep 15;76(6):438-46 - PubMed
  39. Neuroimage. 2016 Jan 1;124(Pt B):1115-1119 - PubMed
  40. Mol Psychiatry. 2020 Sep 22;: - PubMed
  41. NPJ Schizophr. 2017 May 16;3:22 - PubMed
  42. PLoS One. 2013 Jun 11;8(6):e66205 - PubMed
  43. Neuroimage. 2018 Nov 15;182:259-282 - PubMed
  44. Harv Rev Psychiatry. 2016 Mar-Apr;24(2):80-6 - PubMed
  45. Mol Psychiatry. 2019 Oct;24(10):1415-1424 - PubMed
  46. Schizophr Res. 1998 Mar 10;30(2):115-25 - PubMed
  47. Schizophr Res. 2009 Mar;108(1-3):3-10 - PubMed
  48. Neuroimage. 2017 Jan 15;145(Pt B):137-165 - PubMed
  49. Mol Psychiatry. 2018 Mar;23(3):701-707 - PubMed
  50. Trends Neurosci. 2017 Dec;40(12):681-690 - PubMed

Publication Types

Grant support