The field of psychiatry would benefit significantly from developing objective biomarkers that could facilitate the early identification of heterogeneous subtypes of illness. Critically, although machine learning pattern recognition methods have been applied recently to predict many psychiatric disorders, these techniques have not been utilized to predict subtypes of posttraumatic stress disorder (PTSD), including the dissociative subtype of PTSD (PTSD + DS).

Using Multiclass Gaussian Process Classification within PRoNTo, we examined the classification accuracy of: (i) the mean amplitude of low-frequency fluctuations (mALFF; reflecting spontaneous neural activity during rest); and (ii) seed-based amygdala complex functional connectivity within 181 participants [PTSD (n = 81); PTSD + DS (n = 49); and age-matched healthy trauma-unexposed controls (n = 51)]. We also computed mass-univariate analyses in order to observe regional group differences [false-discovery-rate (FDR)-cluster corrected p < 0.05, k = 20].

We found that extracted features could predict accurately the classification of PTSD, PTSD + DS, and healthy controls, using both resting-state mALFF (91.63% balanced accuracy, p < 0.001) and amygdala complex connectivity maps (85.00% balanced accuracy, p < 0.001). These results were replicated using independent machine learning algorithms/cross-validation procedures. Moreover, areas weighted as being most important for group classification also displayed significant group differences at the univariate level. Here, whereas the PTSD + DS group displayed increased activation within emotion regulation regions, the PTSD group showed increased activation within the amygdala, globus pallidus, and motor/somatosensory regions.

The current study has significant implications for advancing machine learning applications within the field of psychiatry, as well as for developing objective biomarkers indicative of diagnostic heterogeneity.

Thalamic glutamine loss and grey matter reduction suggest neurodegeneration in first-episode schizophrenia, but the duration is unknown.

To observe glutamine and glutamate levels, grey matter volumes and social functioning in patients with schizophrenia followed to 80 months after diagnosis.

Grey matter volumes and proton magnetic resonance spectroscopy metabolites in left anterior cingulate and left thalamus were measured in 17 patients with schizophrenia before medication and 10 and 80 months after diagnosis. Social functioning was assessed with the Life Skills Profile Rating Scale (LSPRS) at 80 months.

The sum of thalamic glutamate and glutamine levels decreased over 80 months, and correlated inversely with the LSPRS. Thalamic glutamine and grey matter loss were significantly correlated in frontal, parietal, temporal and limbic regions.

Brain metabolite loss is correlated with deteriorated social functioning and grey matter losses in schizophrenia, consistent with neurodegeneration.

Progressive volumetric changes in the brains of people with schizophrenia have been attributed to a number of factors.

To determine whether glutamatergic changes in patients with schizophrenia correlated with grey-matter losses during the first years of illness.

Left anterior cingulate and thalamic glutamatergic metabolite levels and grey-matter volumes were examined in 16 patients with first-episode schizophrenia before and after 10 months and 30 months of antipsychotic treatment and in 16 healthy participants on two occasions 30 months apart.

Higher than normal glutamine levels were found in the anterior cingulate and thalamus of never-treated patients. Thalamic levels of glutamine were significantly reduced after 30 months. Limited grey-matter reductions were seen in patients at 10 months followed by widespread grey-matter loss at 30 months. Parietal and temporal lobe grey-matter loss was correlated with thalamic glutamine loss.

Elevated glutamine levels in never-treated patients followed by decreased thalamic glutamine and grey-matter loss in connected regions could indicate either neurodegeneration or a plastic response to reduced subcortical activity.

Membrane phospholipid and high-energy abnormalities measured with phosphorus magnetic resonance spectroscopy (31P-MRS) have been reported in patients with schizophrenia in several brain regions.

Using improved imaging techniques, previously inaccessible brain regions were examined in patients with first-episode schizophrenia and healthy volunteers with 4.0 T 31P-MRS.

Brain spectra were collected in vivo from 15 patients with first-episode schizophrenia and 15 healthy volunteers from 15 cm3 effective voxels in the thalamus, cerebellum, hippocampus, anterior/posterior cingulate, prefrontal cortex and parieto-occipital cortex.

People with first-episode schizophrenia showed increased levels of glycerophosphocholine in the anterior cingulate. Inorganic phosphate, phosphocreatine and adenosine triphosphate concentrations were also increased in the anterior cingulate in this group.

The increased phosphodiester and high-energy phosphate levels in the anterior cingulate of brains of people with first-episode schizophrenia may indicate neural overactivity in this region during the early stages of the illness, resulting in increased excitotoxic neural membrane breakdown.

Membrane phospholipid abnormalities in people with schizophrenia, measured with 31P magnetic resonance spectroscopy (31P-MRS), have been previously reported in brain regions involved in this disorder.

In this 4.0 Tesla 31P-MRS study of people with schizophrenia, membrane phospholipid metabolism was examined in brain regions previously inaccessible due to their small volumes.

Three-dimensional chemical-shift imaging (3D–CSI) examined 15 cc volumes in 12 brain regions in 11 people with chronic schizophrenia and 11 healthy control volunteers.

Glycerophosphoethanolamine was decreased in the anterior cingulate, right prefrontal cortex and left thalamus, but increased in the left hippocampus and cerebellum in those with schizophrenia. Phosphoethanolamine and glycerophosphocholine were decreased in the right prefrontal region and phosphocholine was decreased in the anterior cingulate. No significant difference in membrane phospholipid levels existed between groups in the parieto-occipital and posterior cingulate regions.

Altered membrane phospholipid metabolism was demonstrated in all regions implicated in schizophrenia.