Despite significant advances in the treatment of major depression, there is a high degree of variability in how patients respond to treatment. Approximately 70% of patients show some improvement following standard antidepressant treatment and are classified as having non-refractory depressive disorder (NDD), while the remaining 30% of patients do not respond to treatment and are classified as having refractory depressive disorder (RDD). At present, there are no objective, neurological markers which can be used to identify individuals with depression and predict clinical outcome. We therefore examined the diagnostic and prognostic potential of pre-treatment structural neuroanatomy using support vector machine (SVM). Sixty-one drug-naïve adults suffering from depression and 42 healthy volunteers were scanned using structural magnetic resonance imaging (sMRI). Patients then received standard antidepressant medication (either tricyclic, typical serotonin-norepinephrine reuptake inhibitor or typical selective serotonin reuptake inhibitor). Based on clinical outcome, we selected two groups of RDD (n=23) and NDD (n=23) patients matched for age, sex and pre-treatment severity of depression. Diagnostic accuracy of gray matter was 67.39% for RDD (p=0.01) and 76.09% for NDD (p<0.001), while diagnostic accuracy of white matter was 58.70% for RDD (p=0.13) and 84.65% for NDD (p<0.001). SVM applied to gray matter correctly distinguished between RDD and NDD patients with an accuracy of 69.57% (p=0.006); in contrast, SVM applied to white matter predicted clinical outcome with an accuracy of 65.22% (p=0.02). These results indicate that both gray and white matter have diagnostic and prognostic potential in major depression and may provide an initial step towards the use of biological markers to inform clinical treatment. Future studies will benefit from the integration of structural neuroimaging with other imaging modalities as well as genetic, clinical and cognitive information.

Among the general population, individuals with subthreshold psychotic-like experiences, or psychosis proneness (PP), can be psychometrically identified and are thought to have a 10-fold increased risk of psychosis. They also show impairments in measures of emotional functioning parallel to schizophrenia. Whilst previous studies have revealed altered brain activation in patients with schizophrenia during emotional processing, it is unclear whether these alterations are also expressed in individuals with high PP. Here we used Support Vector Machine (SVM) to perform multivariate pattern classification based on brain activation during emotional processing in 20 individuals with high PP and 20 comparison subjects (low PP). In addition, we performed a standard univariate analysis based on the General Linear Model (GLM) on the same data for comparison. The experimental task involved passively viewing negative and neutral pictures from the International Affective Picture System (IAPS). SVM allowed classification of the two groups with statistically significant accuracy (p=0.017) and identified group differences within an emotional circuitry including the amygdala, insula, anterior cingulate and medial prefrontal cortex. In contrast, the standard univariate analysis did not detect any significant between-group differences. Our results reveal a distributed and subtle set of alterations in brain function within the emotional circuitry of individuals with high PP, providing neurobiological support for the notion of dysfunctional emotional circuitry in this group. In addition, these alterations are best detected using a multivariate approach rather than standard univariate methods. Further application of this approach may aid in characterising people at clinical and genetic risk of developing psychosis.

• We present Neuroharmony, a harmonization tool for images from unseen scanners. • We developed Neuroharmony using a total of 15,026 sMRI images. • The tool was able to reduce scanner-related bias from unseen scans. • Neuroharmony represents a significant step towards imaging-based clinical tools. • Neuroharmony is available at https://github.com/garciadias/Neuroharmony.