Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up : Comparison of connectomic, structural, and clinical predictors

Journal article


Kottaram, Akhil, Johnston, Leigh A., Tian, Ye, Ganella, Eleni P., Laskaris, Liliana, Cocchi, Luca, McGorry, Patrick, Pantelis, Christos, Kotagiri, Ramamohanarao, Cropley, Vanessa and Zalesky, Andrew. (2020). Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up : Comparison of connectomic, structural, and clinical predictors. Human Brain Mapping. 41(12), pp. 3342-3357. https://doi.org/10.1002/hbm.25020
AuthorsKottaram, Akhil, Johnston, Leigh A., Tian, Ye, Ganella, Eleni P., Laskaris, Liliana, Cocchi, Luca, McGorry, Patrick, Pantelis, Christos, Kotagiri, Ramamohanarao, Cropley, Vanessa and Zalesky, Andrew
Abstract

In a machine learning setting, this study aims to compare the prognostic utility of connectomic, brain structural, and clinical/demographic predictors of individual change in symptom severity in individuals with schizophrenia. Symptom severity at baseline and 1-year follow-up was assessed in 30 individuals with a schizophrenia-spectrum disorder using the Brief Psychiatric Rating Scale. Structural and functional neuroimaging was acquired in all individuals at baseline. Machine learning classifiers were trained to predict whether individuals improved or worsened with respect to positive, negative, and overall symptom severity. Classifiers were trained using various combinations of predictors, including regional cortical thickness and gray matter volume, static and dynamic resting-state connectivity, and/or baseline clinical and demographic variables. Relative change in overall symptom severity between baseline and 1-year follow-up varied markedly among individuals (interquartile range: 55%). Dynamic resting-state connectivity measured within the default-mode network was the most accurate single predictor of change in positive (accuracy: 87%), negative (83%), and overall symptom severity (77%) at follow-up. Incorporating predictors based on regional cortical thickness, gray matter volume, and baseline clinical variables did not markedly improve prediction accuracy and the prognostic utility of these predictors in isolation was moderate (<70%). Worsening negative symptoms at 1-year follow-up were predicted by hyper-connectivity and hypo-dynamism within the default-mode network at baseline assessment, while hypo-connectivity and hyper-dynamism predicted worsening positive symptoms. Given the modest sample size investigated, we recommend giving precedence to the relative ranking of the predictors investigated in this study, rather than the prediction accuracy estimates.

Keywordsdefault mode network; dynamic functional connectivity; outcome prediction; schizophrenia; symptoms
Year2020
JournalHuman Brain Mapping
Journal citation41 (12), pp. 3342-3357
PublisherJohn Wiley & Sons
ISSN1065-9471
Digital Object Identifier (DOI)https://doi.org/10.1002/hbm.25020
Scopus EID2-s2.0-85085601336
Open accessPublished as ‘gold’ (paid) open access
Research or scholarlyResearch
Page range3342-3357
FunderNational Health and Medical Research Council (NHMRC)
Publisher's version
License
File Access Level
Open
Output statusPublished
Publication dates
Online29 May 2020
Publication process dates
Accepted13 Apr 2020
Deposited12 Jul 2021
Grant IDNHMRC/1065742
NHMRC/601253
NHMRC/628880
NHMRC/628386
NHMRC/1105825
NHMRC/1136649
NHMRC/1099082
NHMRC/1138711
Permalink -

https://acuresearchbank.acu.edu.au/item/8w5v3/predicting-individual-improvement-in-schizophrenia-symptom-severity-at-1-year-follow-up-comparison-of-connectomic-structural-and-clinical-predictors

Download files


Publisher's version
  • 74
    total views
  • 58
    total downloads
  • 2
    views this month
  • 2
    downloads this month
These values are for the period from 19th October 2020, when this repository was created.

Export as

Related outputs

Does cortical brain morphology act as a mediator between childhood trauma and transition to psychosis in young individuals at ultra-high risk?
Rapado-Castro, Marta, Whittle, Sarah, Pantelis, Christos, Thompson, Andrew, Nelson, Barnaby, Ganella, Eleni P., Lin, Ashleigh, Reniers, Renate L. E. P., McGorry, Patrick D., Yung, Alison R., Wood, Stephen J. and Bartholomeusz, Cali F.. (2020). Does cortical brain morphology act as a mediator between childhood trauma and transition to psychosis in young individuals at ultra-high risk? Schizophrenia Research. 224, pp. 116-125. https://doi.org/10.1016/j.schres.2020.09.017
Linking cortical and connectional pathology in Schizophrenia
Di Biase, Maria Angelique, Cropley, Vanessa L., Cocchi, Luca, Fornito, Alexander, Calamante, Fernando, Ganella, Eleni P., Pantelis, Christos and Zalesky, Andrew. (2019). Linking cortical and connectional pathology in Schizophrenia. Schizophrenia Bulletin. 45(4), pp. 911-923. https://doi.org/10.1093/schbul/sby121
Evidence for network-based cortical thickness reductions in schizophrenia
Wannan, Cassandra M. J., Cropley, Vanessa L., Chakravarty, M. Mallar, Bousman, Chad, Ganella, Eleni P., Bruggemann, Jason M., Weickert, Thomas W., Weickert, Cynthia Shannon, Everall, Ian, McGorry, Patrick, Velakoulis, Dennis, Wood, Stephen J., Bartholomeusz, Cali F., Pantelis, Christos and Zalesky, Andrew. (2019). Evidence for network-based cortical thickness reductions in schizophrenia. American Journal of Psychiatry. 176(7), pp. 552-563. https://doi.org/10.1176/appi.ajp.2019.18040380
Brain network dynamics in schizophrenia: Reduced dynamism of the default mode network
Kottaram, Akhil, Johnston, Leigh A., Cocchi, Luca, Ganella, Eleni P., Everall, Ian, Pantelis, Christos, Kotagiri, Ramamohanarao and Zalesky, Andrew. (2019). Brain network dynamics in schizophrenia: Reduced dynamism of the default mode network. Human Brain Mapping. 40(7), pp. 2212 - 2228. https://doi.org/10.1002/hbm.24519
Spatio-temporal dynamics of resting-state brain networks improve single-subject prediction of schizophrenia diagnosis
Akhil Kottaram, Leigh A. Johnston, Eleni P Ganella, Christos Pantelis, Ramamohanarao Kotagiri and Andrew Zalesky. (2018). Spatio-temporal dynamics of resting-state brain networks improve single-subject prediction of schizophrenia diagnosis. Human Brain Mapping. 39(9), pp. 3663-3681. https://doi.org/10.1002/hbm.24202
Risk and resilience brain networks in treatment-resistant schizophrenia
Eleni P Ganella, Caio Seguin, Cali F Bartholomeusz, Sarah Whittle, Chad Bousman, Cassandra M.J. Wannan, Maria Angelique Di Biase, Christina Phassouliotis, I P Everall, Christos Pantelis and Andrew Zalesky. (2018). Risk and resilience brain networks in treatment-resistant schizophrenia. Schizophrenia Research. 193, pp. 284-292. https://doi.org/10.1016/j.schres.2017.07.014
Resting-state functional brain networks in first-episode psychosis: A 12-month follow-up study
Eleni P Ganella, Caio Seguin, Christos Pantelis, Sarah Whittle, Bernhard T Baune, James Olver, G Paul Amminger, Patrick D. McGorry, Vanessa L. Cropley, Andrew Zalesky and Cali F Bartholomeusz. (2018). Resting-state functional brain networks in first-episode psychosis: A 12-month follow-up study. Australian and New Zealand Journal of Psychiatry. 52(9), pp. 864-875. https://doi.org/10.1177/0004867418775833
Extinction of conditioned fear in adolescents and adults: A human fmri study
Despina E. Ganella, Katherine D. Drummond, Eleni P Ganella, Sarah Whittle and Jee Hyun Kim. (2018). Extinction of conditioned fear in adolescents and adults: A human fmri study. Frontiers in Human Neuroscience. 11, pp. 1-13. https://doi.org/10.3389/fnhum.2017.00647
An fMRI study of theory of mind in individuals with first episode psychosis
Cali F Bartholomeusz, Eleni P Ganella, Sarah Whittle, Kelly Allott, Andrew Thompson, Ahmad Abu-Akel, Henrik Walter, Patrick D. McGorry, Eoin Killackey, Christos Pantelis and Stephen J. Wood. (2018). An fMRI study of theory of mind in individuals with first episode psychosis. Psychiatry Research: Neuroimaging. 281, pp. 1-11. https://doi.org/10.1016/j.pscychresns.2018.08.011
Functional brain networks in treatment-resistant schizophrenia
Ganella, Eleni P., Bartholomeusz, Cali F., Seguin, Caio, Whittle, Sarah, Bousman, Chad, Phassouliotis, Christina, Everall, Ian, Pantelis, Christos and Zalesky, Andrew. (2017). Functional brain networks in treatment-resistant schizophrenia. Schizophrenia Research. 184, pp. 73-81. https://doi.org/10.1016/j.schres.2016.12.008
Role of orbitofrontal sulcogyral pattern on lifetime cannabis use and depressive symptoms
Chye, Yann, Solowij, Nadia, Ganella, Eleni P., Suo, Chao, Yücel, Murat, Batalla, Albert, Cousijn, Janna, Goudriaan, Anna E., Martin-Santos, Rocio, Whittle, Sarah, Bartholomeusz, Cali F. and Lorenzetti, Valentina. (2017). Role of orbitofrontal sulcogyral pattern on lifetime cannabis use and depressive symptoms. Progress in Neuropsychopharmacology and Biological Psychiatry. 79, pp. 392 - 400. https://doi.org/10.1016/j.pnpbp.2017.07.017
Abnormalities in orbitofrontal cortex gyrification and mental health outcomes in adolescents born extremely preterm and/or at an extremely low birth weight
Ganella, Eleni P., Burnett, Alice, Cheong, Jeanie, Thompson, Deanne, Roberts, Gehan, Wood, Stephen, Lee, Katherine, Duff, Julianne, Anderson, Peter J., Pantelis, Christos, Doyle, Lex W., Bartholomeusz, Cali and on behalf of the Victorian Infant Collaborative Study, Group. (2015). Abnormalities in orbitofrontal cortex gyrification and mental health outcomes in adolescents born extremely preterm and/or at an extremely low birth weight. Human Brain Mapping. 36(3), pp. 1138-1150.
Effects of oxytocin and genetic variants on brain and behaviour : Implications for treatment in schizophrenia
Bartholomeusz, Cali, Ganella, Eleni, Labuschagne, Izelle, Bousman, Chad and Pantelis, Christos. (2015). Effects of oxytocin and genetic variants on brain and behaviour : Implications for treatment in schizophrenia. Schizophrenia Research. 168(3), pp. 614 - 627. https://doi.org/10.1016/j.schres.2015.06.007