Modulatory interactions of resting-state brain functional connectivity in major depressive disorder

Diagnostic deep learning algorithms that use resting EEG to distinguish major depressive disorder, bipolar disorder, and schizophrenia from each other and from healthy volunteers

BACKGROUND

Mood disorders and schizophrenia affect millions worldwide. Currently, diagnosis is primarily determined by reported symptomatology. As symptoms may overlap, misdiagnosis is common, potentially leading to ineffective or destabilizing treatment. Diagnostic biomarkers could significantly improve clinical care by reducing dependence on symptomatic presentation.

METHODS

We used deep learning analysis (DLA) of resting electroencephalograph (EEG) to differentiate healthy control (HC) subjects (N = 239), from those with major depressive disorder (MDD) (N = 105), MDD-atypical (MDD-A) (N = 27), MDD-psychotic (MDD-P) (N = 35), bipolar disorder-depressed episode (BD-DE) (N = 71), BD-manic episode (BD-ME) (N = 49), and schizophrenia (SCZ) (N = 122) and also differentiate subjects with mental disorders on a pair-wise basis. DSM-III-R diagnoses were determined and supplemented by computerized Quick Diagnostic Interview Schedule. After EEG preprocessing, robust exact low-resolution electromagnetic tomography (ReLORETA) computed EEG sources for 82 brain regions. 20 % of all subjects were then set aside for independent testing. Feature selection methods were then used for the remaining subjects to identify brain source regions that are discriminating between diagnostic categories.

RESULTS

Pair-wise classification accuracies between 90 % and 100 % were obtained using independent test subjects whose data were not used for training purposes. The most frequently selected features across various pairs are in the postcentral, supramarginal, and fusiform gyri, the hypothalamus, and the left cuneus. Brain sites discriminating SCZ from HC were mainly in the left hemisphere while those separating BD-ME from HC were on the right.

LIMITATIONS

The use of superseded DSM-III-R diagnostic system and relatively small sample size in some disorder categories that may increase the risk of overestimation.

CONCLUSIONS

DLA of EEG could be trained to autonomously classify psychiatric disorders with over 90 % accuracy compared to an expert clinical team using standardized operational methods.

A Treatment-Response Comparison Study of Resting-State Functional Magnetic Resonance Imaging Between Standard Treatment of SSRI and Standard Treatment of SSRI Plus Non-dominant Hand-Writing Task in Patients With Major Depressive Disorder

Background: Researches have recently shifted from functional/structural imaging studies to functional connectivity (FC) studies in major depressive disorder (MDD). We aimed to compare treatment response of two treatment groups before and after treatment, in terms of both with psychiatric evaluation scales and resting-state functional connectivity (RSFC) changes in order to objectively demonstrate the possible contribution of the non-dominant hand-writing exercise (NHE) effect on depression treatment. Methods: A total of 26 patients who were right-handed women with similar sociodemographic characteristics were enrolled. Their pre-treatment resting-state functional magnetic resonance imaging (rs-fMRI) and neuropsychiatric tests were recorded, and then, patients were divided into two groups randomly. A standard treatment (ST) (fix sertraline 50 mg/day) was given to both groups. One randomly selected group was given the NHE in addition to the ST. After 8 weeks of treatment, all patients were reevaluated with rs-fMRI and neuropsychiatric tests. Pre- and post-treatment FC changes within the groups and post-treatment connectivity changes between groups were evaluated. Results: Post-treatment neuropsychiatric tests were significantly different in both groups. Post-treatment, two brain regions' connectivity changed in the ST group, whereas 10 brain regions' connectivity changed significantly in the ST + NHE group. When treatment groups were compared with each other after the treatment, the FC of 13 regions changed in the ST + NHE group compared to the ST group (p-unc/p-PFD <0.05). The density of connectivity changes in the frontal and limbic regions, especially connectivities shown to change in depression treatment, in the ST + NHE group indicates a positive contribution to depression treatment, which is also supported by neuropsychiatric scale changes. Conclusion: NHE, which we developed with inspiration from the Eye Movement Desensitization and Reprocessing (EMDR) method, showed significantly more connecitivity changes related with MDD treatment. Beyond offering a new additional treatment method, our study will also contribute to the current literature with our efforts to evaluate all brain regions and networks that may be related to MDD and its treatment together, without being limited to a few regions. Trial Registration: The rs-fMRI and treatment registers were recorded in the BizMed system, which is the patient registration system of Bezmialem Vakif University Medicine Faculty, under the BAP support project approval code and the registration number 3.2018/8.