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.
ObjectiveTo evaluate the feasibility and effectiveness of percutaneous cannulated screw fixation for the treatment of Day type Ⅱ pelvic crescent fracture.MethodsThe clinical data of 14 patients with Day type Ⅱ pelvic crescent fractures underwent closed reduction and percutaneous cannulated screw fixation between January 2009 and July 2016 were retrospectively analysed. There were 9 males and 5 females, aged 17-65 years (mean, 38 years). The causes of injury included traffic accident in 8 cases, falling from height in 3 cases, bruise injury in 3 cases; all were closed fractures. According to Tile classification, there were 8 cases of type B, 6 cases of type C. There were 13 cases combined with fracture of the anterior pelvic ring, including 8 cases of superior and inferior ramus of pubis fracture, 1 case of superior ramus of pubis fracture with symphysis separation, and 4 cases of symphysis separation. The interval of injury and admission was 1- 72 hours (mean, 16 hours), and the interval of injury and operation was 3-8 days (mean, 5 days). After operation, the reduction of fracture was evaluated by the Matta evaluation criteria, the clinical function was assessed by Majeed function assessment.ResultsThe operation time was 35-95 minutes (mean, 55 minutes), cumulative C-arm fluoroscopy time was 3-8 minutes (mean, 5 minutes), no iatrogenic vascular injury and pelvic organ damage occurred. Postoperative X-ray films at 2 days indicated that 2 cases of vertical shift and 2 cases of mild rotation were not completely corrected. Postoperative CT examination at 3 days indicated that 2 pubic joint screws broke through the obturator bone cortex. None of the pubic ramus screws entered into the acetabulum, but a screw of superior pubic branch broke through the posterior cortical of superior pubic branch, a screw of posterior ilium column broke through the medial bone cortex of the ilium, and no clinical symptom was observed. One patient suffered from wound infection in the pubic symphysis, then healed after 2 weeks of wound drainage, the other wounds healed by first intention. According to Matta criterion for fracture reduction, the results were excellent in 9 cases, good in 4 cases, and fair in 1 case with an excellent and good rate of 92.9%. All patients were followed up 8-24 months (mean, 14 months). All fractures healed at 4 months and restored to the normal walking at 6 months after operation, 3 patients suffered from slight pain in the sacroiliac joints and slight claudication when they were tired or walked for a long time and unnecessary for special treatment. One patient felt pain in the back of the iliac spine when he was lying down. During the follow-up, no screw loosening or other internal fixation failure occurred. At last follow-up, according to Majeed functional evaluation criteria, the results were excellent in 7 cases, good in 5 cases, and fair in 2 cases with an excellent and good rate of 85.7%.ConclusionThe percutaneous cannulated screw fixation is a safe treatment for Day type Ⅱ pelvic crescent fracture, which has a reliable fixation and good effectiveness.