Using structural MRI to identify bipolar disorders-13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group

Imagem de Miniatura
Arquivos
art_NUNES_Using_structural_MRI_to_identify_bipolar_disorders13_site_2020.PDF.pdf (2.9 MB)
Citações na Scopus
76
Tipo de produção
article
Data de publicação
2020
DOI
Scopus
Web of Science
PubMed
Título da Revista
ISSN da Revista
Título do Volume
Editora
SPRINGERNATURE
Autores
NUNES, Abraham
SCHNACK, Hugo G.
CHING, Christopher R. K.
AGARTZ, Ingrid
AKUDJEDU, Theophilus N.
ALDA, Martin
ALNAES, Dag
ALONSO-LANA, Silvia
BAUER, Jochen
BAUNE, Bernhard T.
Citação
MOLECULAR PSYCHIATRY, v.25, n.9, p.2130-2143, 2020
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47-67.00, ROC-AUC = 71.49%, 95% CI = 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa = 0.83, 95% CI = 0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.
Palavras-chave
URI
https://observatorio.fm.usp.br/handle/OPI/37878
Referências
  1. Abraham A, 2017, NEUROIMAGE, V147, P736, DOI 10.1016/j.neuroimage.2016.10.045
  2. Arbabshirani MR, 2017, NEUROIMAGE, V145, P137, DOI 10.1016/j.neuroimage.2016.02.079
  3. Atluri G, 2013, NEUROIMAGE-CLIN, V3, P123, DOI 10.1016/j.nicl.2013.07.004
  4. Bansal R, 2012, PLOS ONE, V7, DOI 10.1371/journal.pone.0050698
  5. Bates D, 2015, J STAT SOFTW, V67, P1, DOI 10.18637/jss.v067.i01
  6. Bengio Y, 2013, IEEE T PATTERN ANAL, V35, P1798, DOI 10.1109/TPAMI.2013.50
  7. Berk M, 2011, NEUROSCI BIOBEHAV R, V35, P804, DOI 10.1016/j.neubiorev.2010.10.001
  8. Bschor T, 2012, J AFFECT DISORDERS, V142, P45, DOI 10.1016/j.jad.2012.03.042
  9. Castellanos FX, 2013, NEUROIMAGE, V80, P527, DOI 10.1016/j.neuroimage.2013.04.083
  10. Chawla NV, 2002, J ARTIF INTELL RES, V16, P321, DOI 10.1613/jair.953
  11. Conus P, 2014, BIPOLAR DISORD, V16, P548, DOI 10.1111/bdi.12137
  12. CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1007/BF00994018
  13. Davatzikos C, 2004, NEUROIMAGE, V23, P17, DOI 10.1016/j.neuroimage.2004.05.010
  14. Davatzikos C, 2005, ARCH GEN PSYCHIAT, V62, P1218, DOI 10.1001/archpsyc.62.11.1218
  15. Dluhos P, 2017, NEUROIMAGE, V155, P10, DOI 10.1016/j.neuroimage.2017.03.027
  16. Doan NT, 2017, NEUROIMAGE-CLIN, V15, P719, DOI 10.1016/j.nicl.2017.06.014
  17. Duffy A, 2009, BRIT J PSYCHIAT, V195, P457, DOI 10.1192/bjp.bp.108.062810
  18. Ecker C, 2010, NEUROIMAGE, V49, P44, DOI 10.1016/j.neuroimage.2009.08.024
  19. Fu CHV, 2013, CAN J PSYCHIAT, V58, P499, DOI 10.1177/070674371305800904
  20. Fung G, 2015, BMC PSYCHIATRY, V15, DOI 10.1186/s12888-015-0685-5
  21. Ganzola R, 2017, BIPOLAR DISORD, V19, P74, DOI 10.1111/bdi.12488
  22. Ghaemi SN, 1999, J AFFECT DISORDERS, V52, P135, DOI 10.1016/S0165-0327(98)00076-7
  23. Goodfellow I, 2016, DEEP LEARNING
  24. Gustavsson A, 2011, EUR NEUROPSYCHOPHARM, V21, P718, DOI 10.1016/j.euroneuro.2011.08.008
  25. Hajek T, 2012, EUR PSYCHIAT, V27
  26. Hajek T, 2016, CURR ALZHEIMER RES, V13, P862, DOI 10.2174/1567205013666160219112712
  27. Hajek T, 2015, J PSYCHIATR NEUROSCI, V40, P316, DOI 10.1503/jpn.140142
  28. Hajek T, 2013, BIOL PSYCHIAT, V73, P144, DOI 10.1016/j.biopsych.2012.06.015
  29. Hajek T, 2012, BIPOLAR DISORD, V14, P261, DOI 10.1111/j.1399-5618.2012.01013.x
  30. Hajek T, 2009, J AFFECT DISORDERS, V115, P395, DOI 10.1016/j.jad.2008.10.007
  31. Haufe S, 2014, NEUROIMAGE, V87, P96, DOI 10.1016/j.neuroimage.2013.10.067
  32. He HB, 2009, IEEE T KNOWL DATA EN, V21, P1263, DOI 10.1109/TKDE.2008.239
  33. Hibar DP, 2018, MOL PSYCHIATR, V23, P932, DOI 10.1038/mp.2017.73
  34. Hibar DP, 2016, MOL PSYCHIATR, V21, P1710, DOI 10.1038/mp.2015.227
  35. Hosmer D, 2013, APPL LOGISTIC REGRES
  36. Iniesta R, 2016, PSYCHOL MED, V46, P2455, DOI 10.1017/S0033291716001367
  37. Iniesta R, 2018, SCI REP-UK, V8, DOI 10.1038/s41598-018-23584-z
  38. Jie NF, 2015, IEEE T AUTON MENT DE, V7, P320, DOI 10.1109/TAMD.2015.2440298
  39. Kambeitz J, 2015, NEUROPSYCHOPHARMACOL, V40, P1742, DOI 10.1038/npp.2015.22
  40. Kelly S, 2018, MOL PSYCHIATR, V23, P1261, DOI 10.1038/mp.2017.170
  41. Kempton MJ, 2009, J NEUROSCI, V29, P10863, DOI 10.1523/JNEUROSCI.2204-09.2009
  42. Koutsouleris N, 2015, BRAIN, V138, P2059, DOI 10.1093/brain/awv111
  43. LaConte S, 2005, NEUROIMAGE, V26, P317, DOI 10.1016/j.neuroimage.2005.01.048
  44. LeCun Y, 2015, NATURE, V521, P436, DOI 10.1038/nature14539
  45. Lemaitre G, 2017, J MACH LEARN RES, V18
  46. Lin A, 2017, J NEUROSCI, V37, P6183, DOI 10.1523/JNEUROSCI.3759-16.2017
  47. Milham MP, 2017, DEPRESS ANXIETY, V34, P578, DOI 10.1002/da.22627
  48. Mourao-Miranda J, 2012, PSYCHOL MED, V42, P1037, DOI 10.1017/S0033291711002005
  49. Mwangi Benson, 2016, Biol Psychiatry Cogn Neurosci Neuroimaging, V1, P186
  50. Mwangi B, 2014, BIPOLAR DISORD, V16, P713, DOI 10.1111/bdi.12222
  51. Nieuwenhuis M, 2012, NEUROIMAGE, V61, P606, DOI 10.1016/j.neuroimage.2012.03.079
  52. Orru G, 2012, NEUROSCI BIOBEHAV R, V36, P1140, DOI 10.1016/j.neubiorev.2012.01.004
  53. Panizzon MS, 2009, CEREB CORTEX, V19, P2728, DOI 10.1093/cercor/bhp026
  54. Pedregosa F, 2011, J MACH LEARN RES, V12, P2825
  55. Pettersson-Yeo W, 2013, PSYCHOL MED, V43, P2547, DOI 10.1017/S003329171300024X
  56. Redlich R, 2014, JAMA PSYCHIAT, V71, P1222, DOI 10.1001/jamapsychiatry.2014.1100
  57. Regier DA, 2013, AM J PSYCHIAT, V170, P59, DOI 10.1176/appi.ajp.2012.12070999
  58. Roberts G, 2016, PSYCHOL MED, V46, P2083, DOI 10.1017/S0033291716000507
  59. ROBINS E, 1970, AM J PSYCHIAT, V126, P983, DOI 10.1176/ajp.126.7.983
  60. Rocha-Rego V, 2014, PSYCHOL MED, V44, P519, DOI 10.1017/S0033291713001013
  61. Rozycki M, 2017, SCHIZOPHR B
  62. Rubin-Falcone H, 2018, J AFFECT DISORDERS, V227, P498, DOI 10.1016/j.jad.2017.11.043
  63. Rutter CM, 2001, STAT MED, V20, P2865, DOI 10.1002/sim.942
  64. Sacchet MD, 2015, J PSYCHIATR RES, V68, P91, DOI 10.1016/j.jpsychires.2015.06.002
  65. Salvador R, 2017, PLOS ONE, V12, DOI 10.1371/journal.pone.0175683
  66. Savitz JB, 2013, MOL PSYCHIATR, V18, P528, DOI 10.1038/mp.2013.25
  67. Schmaal L, 2017, MOL PSYCHIATR, V22, P900, DOI 10.1038/mp.2016.60
  68. Schmitt A, 2016, WORLD J BIOL PSYCHIA, V17, P406, DOI 10.1080/15622975.2016.1183043
  69. Schnack HG, 2016, FRONT PSYCHIATRY, V7, DOI 10.3389/fpsyt.2016.00050
  70. Schnack HG, 2014, NEUROIMAGE, V84, P299, DOI 10.1016/j.neuroimage.2013.08.053
  71. Serpa MH, 2014, BIOMED RES INT, V2014, DOI 10.1155/2014/706157
  72. Tariot PN, 2011, ARCH GEN PSYCHIAT, V68, P853, DOI 10.1001/archgenpsychiatry.2011.72
  73. Varoquaux G, 2017, NEUROIMAGE
  74. Whiteford HA, 2013, LANCET, V382, P1575, DOI 10.1016/S0140-6736(13)61611-6
  75. Winkler AM, 2010, NEUROIMAGE, V53, P1135, DOI 10.1016/j.neuroimage.2009.12.028
  76. Wolfers T, 2015, NEUROSCI BIOBEHAV R, V57, P328, DOI 10.1016/j.neubiorev.2015.08.001
  77. Woo CW, 2017, NAT NEUROSCI, V20, P365, DOI 10.1038/nn.4478
  78. Woodcock J, 2008, ANNU REV MED, V59, P1, DOI 10.1146/annurev.med.59.090506.155819

Coleções
Artigos e Materiais de Revistas Científicas - FM/MPS
Artigos e Materiais de Revistas Científicas - LIM/21
Artigos e Materiais de Revistas Científicas - LIM/27