LightGBM is an Effective Predictive Model for Postoperative Complications in Gastric Cancer: A Study Integrating Radiomics with Ensemble Learning.

Postoperative complications of radical gastrectomy seriously affect postoperative recovery and require accurate risk prediction. Therefore, this study aimed to develop a prediction model specifically tailored to guide perioperative clinical decision-making for postoperative complications in patients with gastric cancer. A retrospective analysis was conducted on patients who underwent radical gastrectomy at the First Affiliated Hospital of Nanjing Medical University between April 2022 and June 2023. A total of 166 patients were enrolled. Patient demographic characteristics, laboratory examination results, and surgical pathological features were recorded. Preoperative abdominal CT scans were used to segment the visceral fat region of the patients through 3Dslicer, a 3D Convolutional Neural Network (3D-CNN) to extract image features and the LASSO regression model was employed for feature selection. Moreover, an ensemble learning strategy was adopted to train the features and predict postoperative complications of gastric cancer. The prediction performance of the LGBM (Light Gradient Boosting Machine), XGB (XGBoost), RF (Random Forest), and GBDT (Gradient Boosting Decision Tree) models was evaluated through fivefold cross-validation. This study successfully constructed a model for predicting early complications following radical gastrectomy based on the optimal algorithm, LGBM. The LGBM model yielded an AUC value of 0.9232 and an accuracy of 87.28% (95% CI, 75.61-98.95%), surpassing the performance of other models. Through ensemble learning and integration of perioperative clinical data and visceral fat radiomics, a predictive LGBM model was established. This model has the potential to facilitate individualized clinical decision-making and the early recovery of patients with gastric cancer post-surgery.

Lipid Parameters and the Development of Chronic Kidney Disease: A Prospective Cohort Study in Middle-Aged and Elderly Chinese Individuals.

Epidemiological evidence suggests that lipid parameters are related to the progression of chronic kidney disease (CKD). Nevertheless, prospective studies that comprehensively assess the effect of routinely available lipid measures on the development of CKD are lacking. The aim of this study was to longitudinally assess the influence of lipid metabolism indicators on the presence of CKD in a large community-based population. We conducted a prospective cohort study at Sun Yat-sen Memorial Hospital, China, with 5345 patients of 40 years or older. Cox regression models were conducted, and hazard ratios (HRs) and 95% confidence intervals (CIs) were calculated to assess lipid parameters and their relationship with the incidence of CKD. During the follow-up period, 340 (6.4%) subjects developed CKD. The incidence of CKD increased progressively with quartile values of triglyceride (TG), the ratio of non-high-density lipoprotein cholesterol to high-density lipoprotein cholesterol (non-HDL-C/HDL-C) and the ratio of TG to HDL-C, but decreased with HDL-C quartiles (p < 0.0001 for all trends). Pearson's correlation analysis and multiple regression analyses indicated that these parameters were also associated with various indicators of kidney function. Moreover, we found that among all the lipid parameters, TG/HDL-C emerged as the most effective predictor of CKD. In conclusion, our findings suggest that TG/HDL-C better predicts the incidence of CKD in middle-aged and elderly Chinese individuals than other lipid parameters tested in the study.

Facial-Meridional Isomerization and Reductive Elimination in [(R2P-o-C6H4)2N]PtMe3 (R = Ph, iPr).

Treatment of PtMe3I in tetrahydrofuran with either in situ prepared [R-PNP]Li ([R-PNP]- = [(R2P-o-C6H4)2N]-; R = Ph, iPr) or H[R-PNP] in the presence of triethylamine at room temperature affords quantitatively fac-[R-PNP]PtMe3. Thermolysis of fac-[R-PNP]PtMe3 in benzene solutions generates mer-[R-PNP]PtMe3 and ultimately [R-PNP]PtMe and ethane. Complexes mer-[R-PNP]PtMe3 represent the first meridional trialkylplatinum(IV) derivatives to date.

Impact of Factors of Online Deceptive Reviews on Customer Purchase Decision Based on Machine Learning.

Online deceptive reviews widely exist in the online shopping environment. Numerous studies have investigated the impact of online product reviews on customer behaviour and sales. However, the existing literature is mainly based on real product reviews; only a few studies have investigated deceptive reviews. Based on the results of deceptive reviews, this article explores the factors that affect customer purchase decision in online review systems, which is flooded by deceptive reviews. Therefore, a deceptive review influence model is proposed based on three influential factors of online review system, sentiment characteristics, review length, and online seller characteristics. Based on them, text mining is used to quantify the indicators of the three influential factors. Through principal component analysis and linear regression, the experimental results of electronic appliances on Tmall show that the three influential factors are positively related to customers' purchase intention and decision making.

Data on microbial community composition of sludge from high altitude wastewater treatment plants determined by 16S rRNA gene sequencing.

This work presented the sequences of activated sludge from two municipal wastewater treatment plants (WWTPs) located in a high altitude Plateau in Tibet, China (∼3650 m above the sea level). Sequencing data are the 16S rRNA gene amplicons of V4-V5 region that sequenced on an Illumina HiSeq PE250 platform. Data presented here include detail description and water quality parameters of the WWTPs as well as results of 16S rRNA gene sequences from their active sludges. The core microbial communities in the WWTPs were shown at the taxonomic level of phylum, class, order, family, genus and species. The sequencing data have been deposited in NCBI BioProject PRJNA477990 with the Biosample accessions SAMN09488330-SAMN09488338. The annotation of OTU table at the genus level was assessable on Zenodo (https://zenodo.org/record/2105899#.XA0vQPZuJyw).