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.
BackgroundIntensive care unit (ICU) medical staffs undergoing sleep deprivation with perennial night shift work were usually at high risk of depression. However, shift work on depression-related resting-state functional magnetic resonance imaging was still not fully understood. The objective of this study was to explore the effects of sleep deprivation in ICU medical staffs after one night of shift work on brain functional connectivity density (FCD) and Hamilton Depression Rating Scale (HAMD) scores. Also, serum neurotransmitter concentrations of serotonin (5-HT) and norepinephrine (NE) were obtained simultaneously.MethodsA total of 21 ICU medical staffs without psychiatric history were recruited. All participants received HAMD score assessment and resting-state functional magnetic resonance imaging scans at two time points: one at rested wakefulness and the other after sleep deprivation (SD) accompanied with one night of shift work. Global FCD, local FCD, and long-range FCD (lrFCD) were used to evaluate spontaneous brain activity in the whole brain. In the meantime, peripheral blood samples were collected for measurement of serum 5-HT and NE levels. All these data were acquired between 7:00 and 8:00 am to limit the influence of biological rhythms. The correlations between the FCD values and HAMD scores and serum levels of neurotransmitters were analyzed concurrently.ResultsFunctional connectivity density mapping manifested that global FCD was decreased in the right medial frontal gyrus and the anterior cingulate gyrus, whereas lrFCD was decreased mainly in the right medial frontal gyrus. Most of these brain areas with FCD differences were components of the default mode network and overlapped with the medial prefrontal cortex. The lrFCD in the medial frontal gyrus showed a negative correlation with HAMD scores after SD. Compared with rested wakefulness, serum levels of 5-HT and NE decreased significantly, whereas HAMD scores were higher after SD within subjects.ConclusionsOur study suggested that sleep deprivation after night shift work can induce depressive tendency in ICU medical staffs, which might be related to alterative medial prefrontal cortex, raised HAMD scores, and varying monoamine neurotransmitters.
This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.