Post-traumatic stress disorder (PTSD) presents with complex and diverse clinical manifestations, making accurate and objective diagnosis challenging when relying solely on clinical assessments. Therefore, there is an urgent need to develop reliable and objective auxiliary diagnostic models to provide effective diagnosis for PTSD patients. Currently, the application of graph neural networks for representing PTSD is limited by the expressiveness of existing models, which does not yield optimal classification results. To address this, we proposed a multi-graph multi-kernel graph convolutional network (MK-GCN) model for classifying PTSD data. First, we constructed functional connectivity matrices at different scales for the same subjects using different atlases, followed by employing the k-nearest neighbors algorithm to build the graphs. Second, we introduced the MK-GCN methodology to enhance the feature extraction capability of brain structures at different scales for the same subjects. Finally, we classified the extracted features from multiple scales and utilized graph class activation mapping to identify the top 10 brain regions contributing to classification. Experimental results on seismic-induced PTSD data demonstrated that our model achieved an accuracy of 84.75%, a specificity of 84.02%, and an AUC of 85% in the classification task distinguishing between PTSD patients and non-affected subjects. The findings provide robust evidence for the auxiliary diagnosis of PTSD following earthquakes and hold promise for reliably identifying specific brain regions in other PTSD diagnostic contexts, offering valuable references for clinicians.
Humans ; Stress Disorders, Post-Traumatic/diagnostic imaging* ; Neural Networks, Computer ; Algorithms ; Brain/diagnostic imaging* ; Magnetic Resonance Imaging

OBJECTIVETo explore the central regulatory mechanism of electroacupuncture (EA) on patients with post-traumatic stress disorder (PTSD).

METHODSFourteen patients of PTSD were selected as study objects and treated with "regulating mind and restoring consciousness" acupuncture method, in which Baihui (GV 20) and Shenting (GV 24) were used as main acupoints and Sishencong (EX-HN 1) and Fengchi (GB 20) were used as supporting acupoints for acupuncture. After the arrival of qi, Han's acupoint nerve stimulator was connected for 30 min per treatment, three times a week for consecutive 12 weeks. Before treatment and 12 weeks into treatment, the clinician administered PTSD scale (CAPS), self-rating anxiety scale (SAS) and self-rating depression scale (SDS) were evaluated; a Siemens 3.0 T magnetic resonance imaging system was used to perform resting-state scan, and bilateral hippocampus were taken as region of interested to perform encephalic function connectivity analysis.

RESULTSAfter the treatment, the scores of CAPS, SAS and SDS were all reduced compared with those before treatment (all P<0.05) ; function connectivity was enhanced in bilateral hippocampus, right posterior central gyrus and left superior parietal lobule (2.3

CONCLUSIONElectroacupuncture has certain improving effects on PTSD symptoms, which is likely to be related with enhancing the connectivity between parietal lobe and hippocampus, suppressing the connectivity between hippocampus and parahippocampal gyrus, amygdaloid, leading to an indirect influence on limbic system.

Acupuncture Points ; Adolescent ; Adult ; Brain ; diagnostic imaging ; physiopathology ; Electroacupuncture ; Female ; Humans ; Magnetic Resonance Imaging ; Male ; Radiography ; Stress Disorders, Post-Traumatic ; diagnostic imaging ; physiopathology ; therapy ; Young Adult