Abstract
BACKGROUND: Machine learning (ML) can distinguish cases with psychotic disorder from healthy controls based on magnetic resonance imaging (MRI) data, but it is not yet clear which MRI metrics are the most informative for case-control ML, or how ML algorithms relate to the underlying biology.
METHODS: We analyzed multimodal MRI data from 2 independent case-control studies of psychotic disorders (cases, n = 65, 28; controls, n = 59, 80) and compared ML accuracy across 5 selected MRI metrics from 3 modalities. Cortical thickness, mean diffusivity, and fractional anisotropy were estimated at each of 308 cortical regions, as well as functional and structural connectivity between each pair of regions. Functional connectivity data were also used to classify nonpsychotic siblings of cases (n = 64) and to distinguish cases from controls in a third independent study (cases, n = 67; controls, n = 81).
RESULTS: In both principal studies, the most informative metric was functional MRI connectivity: The areas under the receiver operating characteristic curve were 88% and 76%, respectively. The cortical map of diagnostic connectivity features (ML weights) was replicable between studies (r = .27, p < .001); correlated with replicable case-control differences in functional MRI degree centrality and with a prior cortical map of adolescent development of functional connectivity; predicted intermediate probabilities of psychosis in siblings; and was replicated in the third case-control study.
CONCLUSIONS: ML most accurately distinguished cases from controls by a replicable pattern of functional MRI connectivity features, highlighting abnormal hubness of cortical nodes in an anatomical pattern consistent with the concept of psychosis as a disorder of network development.
| Original language | English |
|---|---|
| Pages (from-to) | 1125-1134 |
| Number of pages | 10 |
| Journal | Biological Psychiatry : Cognitive Neuroscience and Neuroimaging |
| Volume | 6 |
| Issue number | 12 |
| Early online date | 8 Jun 2020 |
| DOIs | |
| Publication status | Published - Dec 2021 |
Funding
This study was supported by grants from the European Commission (PSYSCAN—Translating Neuroimaging Findings From Research Into Clinical Practice; Grant No. 603196 [to PM and RSK]) and the National Institute for Health Research (NIHR) Cambridge Biomedical Research Centre (Mental Health) (to ETB). The Cobre data were downloaded from the Collaborative Informatics and Neuroimaging Suite Data Exchange tool (COINS; http://coins.mrn.org/dx ), and data collection was performed at the Mind Research Network and funded by a Center of Biomedical Research Excellence Grant No. 5P20RR021938/P20GM103472 from the National Institutes of Health to Dr. Vince Calhoun. SEM holds a Henslow Fellowship at Lucy Cavendish College, University of Cambridge, funded by the Cambridge Philosophical Society. KJW was funded by an Alan Turing Institute Research Fellowship under EPSRC Research Grant No. TU/A/000017. MPvdH was supported by a Dutch Research Council (NWO) Vidi and ALW open grant and an MQ Mental Health fellowship. GD is supported by grants from the European Research Council (Grant No. 677467) and Science Foundation Ireland (Grant No. 12/IP/1359). ETB is supported by an NIHR Senior Investigator Award. The views expressed are those of the authors and not necessarily those of the National Health Service, NIHR, or Department of Health and Social Care. This study was supported by grants from the European Commission (PSYSCAN?Translating Neuroimaging Findings From Research Into Clinical Practice; Grant No. 603196 [to PM and RSK]) and the National Institute for Health Research (NIHR) Cambridge Biomedical Research Centre (Mental Health) (to ETB). The Cobre data were downloaded from the Collaborative Informatics and Neuroimaging Suite Data Exchange tool (COINS; http://coins.mrn.org/dx), and data collection was performed at the Mind Research Network and funded by a Center of Biomedical Research Excellence Grant No. 5P20RR021938/P20GM103472 from the National Institutes of Health to Dr. Vince Calhoun. SEM holds a Henslow Fellowship at Lucy Cavendish College, University of Cambridge, funded by the Cambridge Philosophical Society. KJW was funded by an Alan Turing Institute Research Fellowship under EPSRC Research Grant No. TU/A/000017. MPvdH was supported by a Dutch Research Council (NWO) Vidi and ALW open grant and an MQ Mental Health fellowship. GD is supported by grants from the European Research Council (Grant No. 677467) and Science Foundation Ireland (Grant No. 12/IP/1359). ETB is supported by an NIHR Senior Investigator Award. The views expressed are those of the authors and not necessarily those of the National Health Service, NIHR, or Department of Health and Social Care. ETB serves on the Scientific Advisory Board of Sosei Heptares. All other authors report no biomedical financial interests or potential conflicts of interest.
| Funders | Funder number |
|---|---|
| MQ Mental Health | |
| PSYSCAN | |
| National Institutes of Health | |
| Alan Turing Institute | |
| Cambridge Philosophical Society | |
| Engineering and Physical Sciences Research Council | TU/A/000017 |
| Engineering and Physical Sciences Research Council | |
| National Institute for Health Research | |
| European Commission | 603196 |
| European Commission | |
| European Research Council | 677467 |
| European Research Council | |
| Science Foundation Ireland | 12/IP/1359 |
| Science Foundation Ireland | |
| Nederlandse Organisatie voor Wetenschappelijk Onderzoek | |
| UCLH Biomedical Research Centre | 5P20RR021938/P20GM103472 |
| UCLH Biomedical Research Centre |
