Search

Abstract Hematoma expansion (HE) is a high risky symptom with high rate of occurrence for patients who have undergone spontaneous intracerebral hemorrhage (ICH) after a major accident or illness. Correct prediction of the occurrence of HE in advance is critical to help the doctors to determine the next step medical treatment. Most existing studies focus only on the occurrence of HE within 6 h after the occurrence of ICH, while in reality a considerable number of patients have HE after the first 6 h but within 24 h. In this study, based on the medical doctors recommendation, we focus on prediction of the occurrence of HE within 24 h, as well as the occurrence of HE every 6 h within 24 h. Based on the demographics and computer tomography (CT) image extraction information, we used the XGBoost method to predict the occurrence of HE within 24 h. In this study, to solve the issue of highly imbalanced data set, which is a frequent case in medical data analysis, we used the SMOTE algorithm for data augmentation. To evaluate our method, we used a data set consisting of 582 patients records, and compared the results of proposed method as well as few machine learning methods. Our experiments show that XGBoost achieved the best prediction performance on the balanced dataset processed by the SMOTE algorithm with an accuracy of 0.82 and F1-score of 0.82. Moreover, our proposed method predicts the occurrence of HE within 6, 12, 18 and 24 h at the accuracy of 0.89, 0.82, 0.87 and 0.94, indicating that the HE occurrence within 24 h can be predicted accurately by the proposed method.

BackgroundThe global impact of the COVID-19 pandemic had significantly altered the daily routines of people worldwide. This study aimed to compare how sleeptime and depression among Chinese residents had differed between periods during and outside the epidemic. Furthermore, it delved into the interactive effect of age in this relationship.MethodUtilizing data from the China Health and Retirement Longitudinal Study (CHARLS) study in 2015 and the recently released data from 2020, which covered the pandemic period. Depression was assessed using Center for Epidemiologic Studies Depression Scale (CESD-10), considering a score of 10 or higher as indicative of depression. Participants were categorized based on age, specifically those aged 60 years and older. multivariate logistic regression and interaction analyses were employed to assess the interplay of age, supported by subgroup and sensitivity analyses to reinforce our findings.ResultsThe 2020 database comprised 19,331 participants, while the 2015 database had 10,507 participants. Our findings demonstrated a significant correlation between sleeptime and depression in both unadjusted models and models adjusted for all variables in both datasets (p

Abstract Background Postoperative delayed hyponatremia (PDH) is a major cause of readmission after endoscopic transsphenoidal surgery (eTSS) for pituitary adenomas (PAs). However, the risk factors associated with PDH have not been well established, and the development of a dynamic online nomogram for predicting PDH is yet to be realized. We aimed to investigate the predictive factors for PDH and construct a dynamic online nomogram to aid in its prediction. Methods We analyzed the data of 226 consecutive patients who underwent eTSS for PAs at the Department of Neurosurgery in Jinling Hospital between January 2018 and October 2020. An additional 97 external patients were included for external validation. PDH was defined as a serum sodium level below 137 mmol/L, occurring on the third postoperative day (POD) or later. Results Hyponatremia on POD 1–2 (OR = 2.64, P = 0.033), prothrombin time (PT) (OR = 1.78, P = 0.008), and percentage of monocytes (OR = 1.22, P = 0.047) were identified as predictive factors for PDH via multivariable logistic regression analysis. Based on these predictors, a nomogram was constructed with great discrimination in internal validation (adjusted AUC: 0.613–0.688) and external validation (AUC: 0.594–0.617). Furthermore, the nomogram demonstrated good performance in calibration plot, Brier Score, and decision curve analysis. Subgroup analysis revealed robust predictive performance in patients with various clinical subtypes and mild to moderate PDH. Conclusions Preoperative PT and the percentage of monocytes were, for the first time, identified as predictive factors for PDH. The dynamic nomogram proved to be a valuable tool for predicting PDH after eTSS for PAs and demonstrated good generalizability. Patients could benefit from early identification of PDH and optimized treatment decisions.

Vehicle trajectory prediction is a key technology in autonomous driving, one of the aims of which is to ensure the safety of vehicle travelling and lane changing. Especially in complex traffic scenarios, it is critical to accurately predict the vehicle trajectory so that the automated driving system can make appropriate response actions to help the vehicle driver avoid accidents to the greatest extent possible. Some studies on vehicle trajectory prediction have used recurrent networks (LSTMs) to extract temporal correlations and additional convolutional neural networks (CNNs) to capture spatial correlations. This hybrid model can be added more operations, so we propose a new CNN-LSTM hybrid model containing multi-module, interaction regions and spatial-temporal attention mechanisms (IA-CSTM). In this paper, the traffic scene is divided into multiple interaction regions, and vehicles in different regions have different impacts on the predicted vehicles. The model has multiple modules that deal with vehicle information in different interaction regions. The model will cross-fuse vehicle information in important interaction regions to enhance the model’s perception of vehicle information. Multiple modules are linked through a spatial-temporal attention mechanism and capture the relevance of the vehicle in the interaction region to predicted vehicle.

Aim: Lower grade gliomas [LGGs; World Health Organization (WHO) grades 2 and 3], owing to the heterogeneity of their clinical behavior, present a therapeutic challenge to neurosurgeons. The aim of this study was to explore the N6-methyladenosine (m6A) modification landscape in the LGGs and to develop an m6A-related microRNA (miRNA) risk model to provide new perspectives for the treatment and prognostic assessment of LGGs. Methods: Messenger RNA (mRNA) and miRNA expression data of LGGs were extracted from The Cancer Genome Atlas (TCGA) and Chinese Glioma Genome Atlas (CGGA) databases. An m6A-related miRNA risk model was constructed via least absolute shrinkage and selection operator (LASSO), univariate, and multivariate Cox regression analysis. Next, Kaplan-Meier analysis, principal-component analysis (PCA), functional enrichment analysis, immune infiltrate analysis, dynamic nomogram, and drug sensitivity prediction were used to evaluate this risk model. Results: Firstly, six m6A-related miRNAs with independent prognostic value were selected based on clinical information and used to construct a risk model. Subsequently, compared with low-risk group, LGGs in the high-risk group had a higher m6A writer and reader scores, but a lower eraser score. Moreover, LGGs in the high-risk group had a significantly worse clinical prognosis than those in the low-risk group. Simultaneously, this risk model outperformed other clinicopathological variables in the prognosis prediction of LGGs. Immune infiltrate analysis revealed that the proportion of M2 macrophages, regulatory T (Treg) cells, and the expression levels of exhausted immune response markers were significantly higher in the high-risk group than in the low-risk group. Finally, this study constructed an easy-to-use and free dynamic nomogram to help clinicians use this risk model to aid in diagnosis and prognosis assessment. Conclusions: This study developed a m6A-related risk model and uncovered two different m6A modification landscapes in LGGs. Moreover, this risk model may provide guidance and help in clinical prognosis assessment and immunotherapy response prediction for LGGs.

PurposeGlioblastoma multiforme (GBM) is a common and aggressive form of brain tumor. The N6-methyladenosine (m6A) mRNA modification plays multiple roles in many biological processes and disease states. However, the relationship between m6A modifications and the tumor microenvironment in GBM remains unclear, especially at the single-cell level.Experimental DesignSingle-cell and bulk RNA-sequencing data were acquired from the GEO and TCGA databases, respectively. We used bioinformatics and statistical tools to analyze associations between m6A regulators and multiple factors.ResultsHNRNPA2B1 and HNRNPC were extensively expressed in the GBM microenvironment. m6A regulators promoted the stemness state in GBM cancer cells. Immune-related BP terms were enriched in modules of m6A-related genes. Cell communication analysis identified genes in the GALECTIN signaling network in GBM samples, and expression of these genes (LGALS9, CD44, CD45, and HAVCR2) correlated with that of m6A regulators. Validation experiments revealed that MDK in MK signaling network promoted migration and immunosuppressive polarization of macrophage. Expression of m6A regulators correlated with ICPs in GBM cancer cells, M2 macrophages and T/NK cells. Bulk RNA-seq analysis identified two expression patterns (low m6A/high ICP and high m6A/low ICP) with different predicted immune infiltration and responses to ICP inhibitors. A predictive nomogram model to distinguish these 2 clusters was constructed and validated with excellent performance.ConclusionAt the single-cell level, m6A modification facilitates the stemness state in GBM cancer cells and promotes an immunosuppressive microenvironment through ICPs and the GALECTIN signaling pathway network. And we also identified two m6A-ICP expression patterns. These findings could lead to novel treatment strategies for GBM patients.

Background: The global impact of the COVID-19 pandemic had significantly altered the daily routines of people worldwide. This study aimed to compare how sleeptime and depression among Chinese residents had differed between periods during and outside the epidemic. Furthermore, it delved into the interactive effect of age in this relationship. Method: Utilizing data from the China Health and Retirement Longitudinal Study (CHARLS) study in 2015 and the recently released data from 2020, which covered the pandemic period. Depression was assessed using Center for Epidemiologic Studies Depression Scale (CESD-10), considering a score of 10 or higher as indicative of depression. Participants were categorized based on age, specifically those aged 60 years and older. multivariate logistic regression and interaction analyses were employed to assess the interplay of age, supported by subgroup and sensitivity analyses to reinforce our findings. Results: The 2020 database comprised 19,331 participants, while the 2015 database had 10,507 participants. Our findings demonstrated a significant correlation between sleeptime and depression in both unadjusted models and models adjusted for all variables in both datasets (p<0.001). Upon stratifying by age and adjusting for relevant factors, we identified an interaction effect among age, sleeptime, and depression (p=0.004 for the interaction in the 2020 database, compared to 0.004 in 2015). The restricted cubic spline analysis in both datasets showcased a nonlinear relationship between sleeptime and depression. Conclusions: During both epidemic and non-epidemic periods in China, there existed a correlation between sleep duration and depression, which interacts with age. [ABSTRACT FROM AUTHOR]

To improve the poor dispersion and insufficient interfacial adhesion of reinforced graphene (GN) in copper matrices, the graphene surface is irradiated with a Cu ion beam. To study the mechanism of surface modification of irradiated Cu ^+2 sample on the surface of graphene, the Raman spectroscopy, x-ray photoelectron spectroscopy (XPS), atomic force microscope (AFM), and transmission electron microscope (TEM) are employed. The results of Raman spectroscopy showed that the value of relative intensity ratio I _D / I _G of the characteristic peaks of unirradiated graphene was 1.2530 where it became 0.8693 after the irradiation process. It showed an 30.6% reduction in the ratio of I _D / I _G indicating that the ion beam irradiation reduces the surface defects of graphene and causes obvious modification effects. XPS results showed that the irradiated Cu deoxidizes with the epoxy, hydroxyl, or carboxyl group on the surface of the GN, resulting in Cu compounds attached to the surface of the GN. In addition, irradiation introduces stress on the graphene surface to promote the formation of a wrinkled structure to cause the surface morphology to change, as witnessed by the rougher surface morphology, as compared to the unirradiated area. The TEM results showed a recrystallization on the surface of the GN after the irradiation process. Moreover, it showed that the GN lattice was significantly qualified. Ion beam irradiation improves the quality of the surface of GN lattice, reduces the surface defects of graphene, and displays obvious modification effects.