Background: Gestational diabetes mellitus (GDM) is a common endocrine metabolic disease, involving a carbohydrate intolerance of variable severity during pregnancy. The incidence of GDM-related complications and adverse pregnancy outcomes has declined, in part, due to early screening. Machine learning (ML) models are increasingly used to identify risk factors and enable the early prediction of GDM. Objective: The aim of this study was to perform a meta-analysis and comparison of published prognostic models for predicting the risk of GDM and identify predictors applicable to the models. Methods: Four reliable electronic databases were searched for studies that developed ML prediction models for GDM in the general population instead of among high-risk groups only. The novel Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias of the ML models. The Meta-DiSc software program (version 1.4) was used to perform the meta-analysis and determination of heterogeneity. To limit the influence of heterogeneity, we also performed sensitivity analyses, a meta-regression, and subgroup analysis. Results: A total of 25 studies that included women older than 18 years without a history of vital disease were analyzed. The pooled area under the receiver operating characteristic curve (AUROC) for ML models predicting GDM was 0.8492; the pooled sensitivity was 0.69 (95% CI 0.68-0.69; P<.001; I2=99.6%) and the pooled specificity was 0.75 (95% CI 0.75-0.75; P<.001; I2=100%). As one of the most commonly employed ML methods, logistic regression achieved an overall pooled AUROC of 0.8151, while non–logistic regression models performed better, with an overall pooled AUROC of 0.8891. Additionally, maternal age, family history of diabetes, BMI, and fasting blood glucose were the four most commonly used features of models established by the various feature selection methods. Conclusions: Compared to current screening strategies, ML methods are attractive for predicting GDM. To expand their use, the importance of quality assessments and unified diagnostic criteria should be further emphasized.

Since December 2019, the seriousness of coronavirus disease 2019 (COVID‐19) pandemic has been on escalation (Lu, et al 2020). Coagulopathy is common in critically ill patients with COVID‐19 (Tang, et al 2020b). Systemic microvascular thrombosismay occur in most deaths, which was further identified by a recent autopsy (Luo 2020). However, less has been known about the coagulation parameter D‐dimer in the progression of COVID‐19. In this study, we describe 279 COVID‐19 patients recruited from three hospitals in Hubei Province, China, and then investigate the dynamic relationship between D‐dimer level and the progression of COVID‐19.

Selenium (Se) is an essential trace element in human. Recent studies of Se supplementation on the effect of Hashimoto’s thyroiditis (HT) have been reported, but the exact benefit is unclear as well as the underlying immunologic mechanism. We aimed to evaluate the clinical effect of Se supplement in patients with HT, and explore the potential mechanism against thyroid autoimmunity. A prospective, randomized‑controlled study was performed in patients with HT assigned to two groups. Se‐treated group (n = 43) received selenious yeast tablet (SYT) for 6 months, whereas no treatment in control group (n = 47). The primary outcome is the change of thyroid peroxidase antibody (TPOAb) or thyroglobulin antibody (TGAb). Second, thyroid function, urinary iodine, Se, Glutathione peroxidase3 (GPx3), and Selenoprotein P1 (SePP1) levels were measured during the SYT treatment. Meanwhile, regulatory T cells (Tregs) and their subsets activated Tregs (aTregs), resting Tregs, and secreting Tregs, as well as Helios and PD‐1 expression on these cells were also detected. The results showed that SYT treatment significantly decreased TPOAb, TGAb, and thyroid stimulating hormone (TSH) levels, accompanied with the increased Se, GPx3, and SePP1, compared with the control group. Subgroup analysis revealed that subclinical HT may benefit more from this treatment in the decrease of TSH levels by interaction test. Moreover, the percentage of aTregs, Helios/Tregs, and Helios/aTregs were significantly higher in the Se‐treated group than control. In conclusion, Se supplementation may have a beneficial effect on thyroid autoantibodies and thyroid function by increasing the antioxidant activity and upregulating the activated Treg cells.

Drug combination therapies are promising clinical treatments for curing patients. However, efficiently identifying valid drug combinations remains challenging because the number of available drugs has increased rapidly. In this study, we proposed a deep learning model called the Dual Feature Fusion Network for Drug–Drug Synergy prediction (DFFNDDS) that utilizes a fine-tuned pretrained language model and dual feature fusion mechanism to predict synergistic drug combinations. The dual feature fusion mechanism fuses the drug features and cell line features at the bit-wise level and the vector-wise level. We demonstrated that DFFNDDS outperforms competitive methods and can serve as a reliable tool for identifying synergistic drug combinations.

Background: The relationship between pancreatic cancer (PC) and type 2 diabetes mellitus (T2DM) has long been widely recognized, but the interaction mechanisms are still unknown. This study was aimed to investigate the shared gene signatures and molecular processes between PC and T2DM.Methods: The Gene Expression Omnibus (GEO) database was used to retrieve the RNA sequence and patient information of PC and T2DM. Weighted gene co-expression network analysis (WGCNA) was performed to discover a co-expression network associated with PC and T2DM. Enrichment analysis of shared genes present in PC and T2DM was performed by ClueGO software. These results were validated in the other four cohorts based on differential gene analysis. The predictive significance of S100A6 in PC was evaluated using univariate and multivariate Cox analyses, as well as Kaplan–Meier plots. The biological process of S100A6 enrichment in PC was detected using Gene Set Enrichment Analysis (GSEA). The involvement of S100A6 in the tumor immune microenvironment (TIME) was assessed by CIBERSORT. In vitro assays were used to further confirm the function of S100A6 in PC.Results: WGCNA recognized three major modules for T2DM and two major modules for PC. There were 44 shared genes identified for PC and T2DM, and Gene Ontology (GO) analysis showed that regulation of endodermal cell fate specification was primarily enriched. In addition, a key shared gene S100A6 was derived in the validation tests. S100A6 was shown to be highly expressed in PC compared to non-tumor tissues. PC patients with high S100A6 expression had worse overall survival (OS) than those with low expression. GSEA revealed that S100A6 is involved in cancer-related pathways and glycometabolism-related pathways. There is a strong relationship between S100A6 and TIME. In vitro functional assays showed that S100A6 helped to induce the PC cells’ proliferation and migration. We also proposed a diagram of common mechanisms of PC and T2DM.Conclusions: This study firstly revealed that the regulation of endodermal cell fate specification may be common pathogenesis of PC and T2DM and identified S100A6 as a possible biomarker and therapeutic target for PC and T2DM patients.