You are here : Home > News > Artificial intelligence allows identification of a neuroanatomical signature of schizophrenia

Scientific result | Brain | Medical imaging | MRI

Artificial intelligence allows identification of a neuroanatomical signature of schizophrenia

​An international collaboration of researchers in psychiatry, led by a team from NeuroSpin, has shown that machine learning algorithms identify a neuroanatomical signature of schizophrenia that is reproducible in the various image acquisition centers and for the different stages of the disease evolution. These results offer prospects for the early detection and management of people at risk of psychotic transition.

Published on 12 December 2018

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.

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.

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).

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.

Top page