Plasma Aß level alterations after sleep deprivation correspond to brain structural remodeling in medical night shift workers.

The relationship between brain structure alteration and metabolic product clearance after night shift work with total sleep deprivation (SD) remains unclear. Twenty-two intensive care unit staff on regularly rotating shift work were implemented with structural and diffusion MRI under both rest wakefulness (RW) and SD conditions. Peripheral blood samples were collected for the measurement of cerebral metabolites. Voxel-based morphometry and diffusion tensor imaging analysis were used to investigate the alterations in the gray matter density (GMD) and mean diffusivity (MD) within the participants. Furthermore, correlation analysis was performed to investigate the relationship between the neuroimaging metrics and hematological parameters. A significant increase in the GMD values was observed in the anterior and peripheral areas of the brain under SD. In contrast, a decrease in the values was observed in the posterior regions, such as the bilateral cerebellum and thalamus. In addition, a significant reduction in the total cerebrospinal fluid volume was observed under SD. The Aß42/Aß40 levels in participants under SD were significantly lower than those under RW. The mean MD increment values extracted from the region of interest (ROI) of the anterior brain were negatively correlated with the increment of plasma Aß42/Aß40 levels (r = -0.658, P = 0.008). The mean GMD decrement values extracted from the posterior ROI were positively correlated with the increment of plasma Aß-40 levels (r = 0.601, P = 0.023). The findings of this study suggest that one night of shift work under SD induces extensive and direction-specific structural alterations of the brain, which are associated with aberrant brain metabolic waste clearance.

Machine learning predicts lymph node metastasis of poorly differentiated-type intramucosal gastric cancer.

To construct a machine learning algorithm model of lymph node metastasis (LNM) in patients with poorly differentiated-type intramucosal gastric cancer. 1169 patients with postoperative gastric cancer were divided into a training group and a test group at a ratio of 7:3. The model for lymph node metastasis was established with python machine learning. The Gbdt algorithm in the machine learning results finds that number of resected nodes, lymphovascular invasion and tumor size are the primary 3 factors that account for the weight of LNM. Effect of the LNM model of PDC gastric cancer patients in the training group: Among the 7 algorithm models, the highest accuracy rate was that of GBDT (0.955); The AUC values for the 7 algorithms were, from high to low, XGB (0.881), RF (0.802), GBDT (0.798), LR (0.778), XGB + LR (0.739), RF + LR (0.691) and GBDT + LR (0.626). Results of the LNM model of PDC gastric cancer patients in test group : Among the 7 algorithmic models, XGB had the highest accuracy rate (0.952); Among the 7 algorithms, the AUC values, from high to low, were GBDT (0.788), RF (0.765), XGB (0.762), LR (0.750), RF + LR (0.678), GBDT + LR (0.650) and XGB + LR (0.619). Single machine learning algorithm can predict LNM in poorly differentiated-type intramucosal gastric cancer, but fusion algorithm can not improve the effect of machine learning in predicting LNM.