A de Pierrefeu1, T Löfstedt2, C Laidi1,3,4,5, F Hadj-Selem6, J Bourgin7,8, T Hajek9,10, F Spaniel10, M Kolenic10, P Ciuciu1,11, N Hamdani3,4,5, M Leboyer3,4,5, T Fovet12,13, R Jardri11,12,13, J Houenou1,3,4,5, E Duchesnay1. 1. NeuroSpin, CEA, Gif-sur-Yvette, France. 2. Department of Radiation Sciences, Umeå University, Umeå, Sweden. 3. Institut National de la Santé et de la Recherche Médicale (INSERM), U955, Institut Mondor de Recherche Biomédicale, Psychiatrie Translationnelle, Créteil, France. 4. Fondation Fondamental, Créteil, France. 5. Pôle de Psychiatrie, Assistance Publique-Hôpitaux de Paris (AP-HP), Faculté de Médecine de Créteil, DHU PePsy, Hôpitaux Universitaires Mondor, Créteil, France. 6. Energy Transition Institute: VeDeCoM, Versailles, France. 7. Department of Psychiatry, Louis-Mourier Hospital, AP-HP, Colombes, France. 8. INSERM U894, Centre for Psychiatry and Neurosciences, Paris, France. 9. Department of Psychiatry, Dalhousie University, Halifax, NS, Canada. 10. National Institute of Mental Health, Klecany, Czech Republic. 11. INRIA, CEA, Parietal team, University of Paris-Saclay, Lille, France. 12. Laboratoire de Sciences Cognitives et Sciences Affectives (SCALab-PsyCHIC), CNRS UMR 9193, University of Lille, Lille, France. 13. Pôle de Psychiatrie, Unité CURE, CHU Lille, Lille, France.
Abstract
OBJECTIVE: Structural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross-sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings' reproducibility. METHOD: We propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophrenia patients, 330 controls), we assessed cross-site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first-episode patients. RESULTS: Machine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first-episode psychosis patients (73% accuracy). CONCLUSION: These results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.
OBJECTIVE: Structural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross-sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings' reproducibility. METHOD: We propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophreniapatients, 330 controls), we assessed cross-site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first-episode patients. RESULTS: Machine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first-episode psychosispatients (73% accuracy). CONCLUSION: These results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.
Authors: Dominic B Dwyer; Nikolaos Koutsouleris; Johannes Lieslehto; Erika Jääskeläinen; Vesa Kiviniemi; Marianne Haapea; Peter B Jones; Graham K Murray; Juha Veijola; Udo Dannlowski; Dominik Grotegerd; Susanne Meinert; Tim Hahn; Anne Ruef; Matti Isohanni; Peter Falkai; Jouko Miettunen Journal: NPJ Schizophr Date: 2021-06-14