Schizophrenia (SZ) stands as a severe psychiatric disorder. This study applied diffusion tensor imaging (DTI) data in conjunction with graph neural networks to distinguish SZ patients from normal controls (NCs) and showcases the superior performance of a graph neural network integrating combined fractional anisotropy and fiber number brain network features, achieving an accuracy of 73.79% in distinguishing SZ patients from NCs. Beyond mere discrimination, our study delved deeper into the advantages of utilizing white matter brain network features for identifying SZ patients through interpretable model analysis and gene expression analysis. These analyses uncovered intricate interrelationships between brain imaging markers and genetic biomarkers, providing novel insights into the neuropathological basis of SZ. In summary, our findings underscore the potential of graph neural networks applied to multimodal DTI data for enhancing SZ detection through an integrated analysis of neuroimaging and genetic features.
Humans ; Schizophrenia/pathology* ; Diffusion Tensor Imaging/methods* ; Male ; Female ; Adult ; Brain/metabolism* ; Young Adult ; Middle Aged ; White Matter/pathology* ; Gene Expression ; Nerve Net/diagnostic imaging* ; Graph Neural Networks

Objective:To analyze the clinical efficacy and learning curve for robot-assisted cortical bone trajectory (CBT) screw fixation performed by surgeons with different seniority in the treatment of lumbar degenerative disease.Methods:The clinical data of 91 lumbar degenerative disease patients underwent robot-assisted CBT screw fixation from August 2020 to December 2022 in Beijing Shijitan Hospital, Capital Medical University were retrospectively analyzed. Among them, 48 patients underwent surgery performed by the same senior surgeon (senior group), with a total of 234 CBT screws were placed; while 43 patients underwent surgery performed by the same junior surgeon (junior group), with a total of 206 CBT screws were placed. The surgical related indexes, functional improvement score, lower back pain and lower limb radiation pain scores, acceptable nail insertion rate, non invasion rate of facet joints and incidence of postoperative complications were compared between two groups. The functional improvement score was evaluated using the Japanese Orthopaedic Association (JOA) score, the pain score was evaluated using visual analog score (VAS). The cumulative sum (CUSUM) method was used to depict the learning curve with "single screw placement time" as the observation index.Results:There were no statistical difference in incision length, operation time, intraoperative blood loss and postoperative hospital stay between two groups ( P>0.05). The least squares means of JOA scores 1, 3 and 6 months after surgery in both groups increased significantly compared to baseline, while the least squares means of lower back pain VAS and lower limb radiation pain VAS decreased significantly compared to baseline; there were no statistical differences between two groups ( P>0.05). There were no statistical difference in acceptable nail insertion rate, non invasion rate of facet joints and incidence of postoperative complications between two group ( P>0.05). The CUSUM learning curves were fitting well and the inflection point for senior surgeon corresponded to 18 cases, while it was reached after performing surgery on 21 cases for junior surgeon. Conclusions:Robot-assisted CBT screw fixation performed by surgeons with different seniority could achieve similar clinical outcomes for treating lumbar degenerative disease. The senior surgeons are able to complete the initial learning stage faster than the junior surgeons, but there is not much difference in the number of surgeries performed the learning curve.

Objective:To analyze the clinical efficacy and learning curve for robot-assisted cortical bone trajectory (CBT) screw fixation performed by surgeons with different seniority in the treatment of lumbar degenerative disease.Methods:The clinical data of 91 lumbar degenerative disease patients underwent robot-assisted CBT screw fixation from August 2020 to December 2022 in Beijing Shijitan Hospital, Capital Medical University were retrospectively analyzed. Among them, 48 patients underwent surgery performed by the same senior surgeon (senior group), with a total of 234 CBT screws were placed; while 43 patients underwent surgery performed by the same junior surgeon (junior group), with a total of 206 CBT screws were placed. The surgical related indexes, functional improvement score, lower back pain and lower limb radiation pain scores, acceptable nail insertion rate, non invasion rate of facet joints and incidence of postoperative complications were compared between two groups. The functional improvement score was evaluated using the Japanese Orthopaedic Association (JOA) score, the pain score was evaluated using visual analog score (VAS). The cumulative sum (CUSUM) method was used to depict the learning curve with "single screw placement time" as the observation index.Results:There were no statistical difference in incision length, operation time, intraoperative blood loss and postoperative hospital stay between two groups ( P>0.05). The least squares means of JOA scores 1, 3 and 6 months after surgery in both groups increased significantly compared to baseline, while the least squares means of lower back pain VAS and lower limb radiation pain VAS decreased significantly compared to baseline; there were no statistical differences between two groups ( P>0.05). There were no statistical difference in acceptable nail insertion rate, non invasion rate of facet joints and incidence of postoperative complications between two group ( P>0.05). The CUSUM learning curves were fitting well and the inflection point for senior surgeon corresponded to 18 cases, while it was reached after performing surgery on 21 cases for junior surgeon. Conclusions:Robot-assisted CBT screw fixation performed by surgeons with different seniority could achieve similar clinical outcomes for treating lumbar degenerative disease. The senior surgeons are able to complete the initial learning stage faster than the junior surgeons, but there is not much difference in the number of surgeries performed the learning curve.