Background: To reduce the high incidence and mortality of gastric cancer (GC), we aimed to develop deep learning-based models to assist in predicting the diagnosis and overall survival (OS) of GC patients using pathological images. Methods: 2333 hematoxylin and eosin-stained pathological pictures of 1037 GC patients were collected from two cohorts to develop our algorithms, Renmin Hospital of Wuhan University (RHWU) and the Cancer Genome Atlas (TCGA). Additionally, we gained 175 digital pictures of 91 GC patients from National Human Genetic Resources Sharing Service Platform (NHGRP), served as the independent external validation set. Two models were developed using artificial intelligence (AI), one named GastroMIL for diagnosing GC, and the other named MIL-GC for predicting outcome of GC. Findings: The discriminatory power of GastroMIL achieved accuracy 0.920 in the external validation set, superior to that of the junior pathologist and comparable to that of expert pathologists. In the prognostic model, Cindices for survival prediction of internal and external validation sets were 0.671 and 0.657, respectively. Moreover, the risk score output by MIL-GC in the external validation set was proved to be a strong predictor of OS both in the univariate (HR = 2.414, P < 0.0001) and multivariable (HR = 1.803, P = 0.043) analyses. The predicting process is available at an online website (https://baigao.github.io/Pathologic-Prognostic-Analysis/). Interpretation: Our study developed AI models and contributed to predicting precise diagnosis and prognosis of GC patients, which will offer assistance to choose appropriate treatment to improve the survival status of GC patients. Funding: Not applicable.

Objective: To explore the gender differences in the psychological symptoms, sleep quality, and quality of life of patients with inflammatory bowel disease (IBD). Methods: A unified questionnaire was developed to collect clinical data on the psychology and quality of life of IBD patients from 42 hospitals in 22 provinces in China from September 2021 to May 2022. The general clinical characteristics, psychological symptoms, sleep quality, and quality of life of IBD patients of different genders were analyzed via a descriptive statistical analysis. A multivariate logistic regression analysis was conducted, and independent influencing factors were screened to construct a nomogram to predict the quality of life. The consistency index (C-index), receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), and calibration curve were used to evaluate the discrimination and accuracy of the nomogram model. Decision curve analysis (DCA) was used to evaluate the clinical utility. Results: A total of 2478 IBD patients (1371 patients with ulcerative colitis (UC) and 1107 patients with Crohn’s disease (CD)) were investigated, including 1547 males (62.4%) and 931 females (37.6%). The proportion of anxiety in females was significantly higher than in males (IBD: 30.5% vs. 22.4%, p < 0.001; UC: 32.4% vs. 25.1%, p = 0.003; CD: 26.8% vs. 19.9%, p = 0.013), and there were differences in the severity of anxiety between the genders (IBD: p < 0.001; UC: p < 0.001; CD: p = 0.050). The proportion of depression in females was higher than in males (IBD: 33.1% vs. 27.7%, p = 0.005; UC: 34.4% vs. 28.9%, p = 0.031; CD: 30.6% vs. 26.6%, p = 0.184), and there were differences in the severity of depression between the genders (IBD: p = 0.004; UC: p = 0.022; CD: p = 0.312). The proportion suffering from sleep disturbances among females was slightly higher than among males (IBD: 63.2% vs. 58.4%, p = 0.018; UC: 63.4% vs. 58.1%, p = 0.047; CD: 62.7% vs. 58.6%, p = 0.210), and the proportion of females with a poor quality of life was higher than that of males (IBD: 41.8% vs. 35.2%, p = 0.001; UC: 45.1% vs. 39.8%, p = 0.049; CD: 35.4% vs. 30.8%, p = 0.141). The AUC values of the female and male nomogram prediction models for predicting poor quality of life were 0.770 (95% CI: 0.7391–0.7998) and 0.771 (95% CI: 0.7466–0.7952), respectively. The calibration diagrams of the two models showed that the calibration curves fitted well with the ideal curve, and the DCA that showed nomogram models could bring clinical benefits. Conclusions: There were significant gender differences in the psychological symptoms, sleep quality, and quality of life of IBD patients, suggesting that females need more psychological support. In addition, a nomogram model with high accuracy and performance was constructed to predict the quality of life of IBD patients of different genders, which is helpful for the timely clinical formulation of personalized intervention plans that can improve the prognosis of patients and save medical costs.

BackgroundEndoplasmic reticulum stress (ERS) is a critical factor in the development of ulcerative colitis (UC); however, the underlying molecular mechanisms remain unclear. This study aims to identify pivotal molecular mechanisms related to ERS in UC pathogenesis and provide novel therapeutic targets for UC.MethodsColon tissue gene expression profiles and clinical information of UC patients and healthy controls were obtained from the Gene Expression Omnibus (GEO) database, and the ERS-related gene set was downloaded from GeneCards for analysis. Weighted gene co-expression network analysis (WGCNA) and differential expression analysis were utilized to identify pivotal modules and genes associated with UC. A consensus clustering algorithm was used to classify UC patients. The CIBERSORT algorithm was employed to evaluate the immune cell infiltration. Gene Set Variation Analysis (GSVA), Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) were used to explore potential biological mechanisms. The external sets were used to validate and identify the relationship of ERS-related genes with biologics. Small molecule compounds were predicted using the Connectivity Map (CMap) database. Molecular docking was performed to simulate the binding conformation of small molecule compounds and key targets.ResultsThe study identified 915 differentially expressed genes (DEGs) and 11 ERS-related genes (ERSRGs) from the colonic mucosa of UC patients and healthy controls, and these genes had good diagnostic value and were highly correlated. Five potential small-molecule drugs sharing tubulin inhibitors were identified, including albendazole, fenbendazole, flubendazole, griseofulvin, and noscapine, among which noscapine exhibited the highest correlation with a high binding affinity to the targets. Active UC and 10 ERSRGs were associated with a large number of immune cells, and ERS was also associated with colon mucosal invasion of active UC. Significant differences in gene expression patterns and immune cell infiltration abundance were observed among ERS-related subtypes.ConclusionThe results suggest that ERS plays a vital role in UC pathogenesis, and noscapine may be a promising therapeutic agent for UC by affecting ERS.