Sarah E Morgan1, Jonathan Young2, Ameera X Patel3, Kirstie J Whitaker4, Cristina Scarpazza5, Thérèse van Amelsvoort6, Machteld Marcelis6, Jim van Os7, Gary Donohoe8, David Mothersill8, Aiden Corvin9, Celso Arango10, Andrea Mechelli11, Martijn van den Heuvel12, René S Kahn13, Philip McGuire11, Michael Brammer14, Edward T Bullmore15. 1. Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom; Alan Turing Institute, London, United Kingdom. Electronic address: sem91@cam.ac.uk. 2. Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom; IXICO plc, London, United Kingdom. 3. Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom; Cambridge University Hospitals NHS Foundation Trust, Cambridge, United Kingdom. 4. Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom; Alan Turing Institute, London, United Kingdom. 5. Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom; Department of General Psychology, University of Padova, Padova, Italy. 6. Department of Psychiatry and Psychology, Maastricht University, Maastricht, The Netherlands. 7. Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom; Department of Psychiatry and Psychology, Maastricht University, Maastricht, The Netherlands; Department of Psychiatry, University Medical Center Utrecht Brain Center, Utrecht, The Netherlands. 8. School of Psychology, National University of Ireland, Galway, Ireland. 9. Department of Psychiatry, Trinity College, Dublin, Ireland. 10. Child and Adolescent Psychiatry Department, Hospital General Universitario Gregorio Marañón, School of Medicine, Universidad Complutense, Madrid, Spain. 11. Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom. 12. Department of Complex Trait Genetics, Vrije Universiteit, Amsterdam, The Netherlands. 13. Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York. 14. Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom; Department of Forensic and Development Psychiatry, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom. 15. Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom; Cambridgeshire and Peterborough NHS Foundation Trust, Cambridge, United Kingdom.
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 = 0.27, 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.
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 = 0.27, 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.
Authors: Lena Dorfschmidt; Richard A Bethlehem; Jakob Seidlitz; František Váša; Simon R White; Rafael Romero-García; Manfred G Kitzbichler; Athina R Aruldass; Sarah E Morgan; Ian M Goodyer; Peter Fonagy; Peter B Jones; Ray J Dolan; Neil A Harrison; Petra E Vértes; Edward T Bullmore Journal: Sci Adv Date: 2022-05-27 Impact factor: 14.957
Authors: Stefania Tognin; Anja Richter; Matthew J Kempton; Gemma Modinos; Mathilde Antoniades; Matilda Azis; Paul Allen; Matthijs G Bossong; Jesus Perez; Christos Pantelis; Barnaby Nelson; Paul Amminger; Anita Riecher-Rössler; Neus Barrantes-Vidal; Marie-Odile Krebs; Birte Glenthøj; Stephan Ruhrmann; Gabriele Sachs; Bart P F Rutten; Lieuwe de Haan; Mark van der Gaag; Lucia R Valmaggia; Philip McGuire Journal: Schizophr Bull Open Date: 2022-06-20
Authors: Du Lei; Kun Qin; Walter H L Pinaya; Jonathan Young; Therese Van Amelsvoort; Machteld Marcelis; Gary Donohoe; David O Mothersill; Aiden Corvin; Sandra Vieira; Su Lui; Cristina Scarpazza; Celso Arango; Ed Bullmore; Qiyong Gong; Philip McGuire; Andrea Mechelli Journal: Schizophr Bull Date: 2022-06-21 Impact factor: 7.348