Background: The application of machine learning (ML) for identifying early gastric cancer (EGC) has drawn increasing attention. However, there lacks evidence-based support for its specific diagnostic performance. Hence, this systematic review and meta-analysis was implemented to assess the performance of image-based ML in EGC diagnosis. Methods: We performed a comprehensive electronic search in PubMed, Embase, Cochrane Library, and Web of Science up to September 25, 2022. QUADAS-2 was selected to judge the risk of bias of included articles. We did the meta-analysis using a bivariant mixed-effect model. Sensitivity analysis and heterogeneity test were performed. Results: Twenty-one articles were enrolled. The sensitivity (SEN), specificity (SPE), and SROC of ML-based models were 0.91 (95% CI: 0.87–0.94), 0.85 (95% CI: 0.81–0.89), and 0.94 (95% CI: 0.39–1.00) in the training set and 0.90 (95% CI: 0.86–0.93), 0.90 (95% CI: 0.86–0.92), and 0.96 (95% CI: 0.19–1.00) in the validation set. The SEN, SPE, and SROC of EGC diagnosis by non-specialist clinicians were 0.64 (95% CI: 0.56–0.71), 0.84 (95% CI: 0.77–0.89), and 0.80 (95% CI: 0.29–0.97), and those by specialist clinicians were 0.80 (95% CI: 0.74–0.85), 0.88 (95% CI: 0.85–0.91), and 0.91 (95% CI: 0.37–0.99). With the assistance of ML models, the SEN of non-specialist physicians in the diagnosis of EGC was significantly improved (0.76 vs 0.64). Conclusion: ML-based diagnostic models have greater performance in the identification of EGC. The diagnostic accuracy of non-specialist clinicians can be improved to the level of the specialists with the assistance of ML models. The results suggest that ML models can better assist less experienced clinicians in diagnosing EGC under endoscopy and have broad clinical application value.

Expression of the 3 subunit of Na /K -ATPase is increased in gastric cancer and regulates gastric cancer cell progression and prognosis via the PI3/AKT pathway Expression of the β3 subunit of Na+/K+-ATPase is increased in gastric cancer and regulates gastric cancer cell progression and prognosis via the PI3/AKT pathway

Background: Aberrant DNA methylation has emerged as a class of promising biomarkers for early colorectal cancer (CRC) detection, but the performance of methylated C9orf50 and methylated KCNQ5 in stool DNA has never been evaluated.Methods: Methylation specific quantitative PCR (qPCR) assays for methylated C9orf50 and methylated KCNQ5 were developed. The methylation levels of C9orf50 and KCNQ5 in 198 CRC patients, 20 advanced adenoma (AA) patients, 101 small polyp (SP) patients, and 141 no evidence of disease (NED) subjects were analyzed.Results: The methylation levels of both KCNQ5 and C9orf50 genes were significantly higher in CRC and AA groups than those in SP and NED groups, but showed no significant difference among different stages of CRC. The sensitivities of methylated KCNQ5 and methylated C9orf50 for CRC detection were 77.3% (95% CI: 70.7–82.8%) and 85.9% (95% CI: 80.0–90.2%) with specificities of 91.5% (95% CI: 85.3–95.3%) and 95.0% (95% CI: 89.7–97.8%), respectively. When C9orf50 and methylated KCNQ5 were combined, the clinical performance for CRC detection was similar to that of methylated C9orf50 alone.Conclusions: Stool DNA based methylated C9orf50 test has the potential to become an alternative approach for CRC screening and prevention.

Background: A number of plasma methylated DNA biomarkers related to colorectal cancer (CRC) have been identified. However, the effect of methylation level in leukocytes on plasma-based methylation test was rarely reported.

Objective: Acute necrotic collection (ANC), acute peripancreatic fluid collection (APFC), pleural effusion, and ascites are common early complications of acute pancreatitis. This study aimed to investigate the relationship between 12 serum cytokines and the early complications and severity of acute pancreatitis (AP).Methods: We retrospectively analyzed the clinical data of 307 patients with AP, and divided them into severe group and mild‐to‐moderate group according to the revised Atlanta classification. Propensity score matching was used to control for confounding factors. Binary logistic regression analysis was used to explore the relationship between cytokine levels and early complications of AP.Results: Serum levels of interleukin (IL)‐1β, IL‐5, IL‐6, IL‐8, IL‐10, IL‐17, and tumor necrosis factor‐α were significantly higher in the severe acute pancreatitis (SAP) group than in the non‐SAP group (p < .05). After adjusting for confounding factors, the upper quartiles of IL‐6, IL‐8, and IL‐10 were associated with an increased risk of ANC compared with those in the lowest quartile (IL‐6: quartile 3, odds ratio [OR] = 3.99, 95% confidence interval [CI] = 1.95–8.16; IL‐8: quartile 4, OR = 2.47, 95% CI = 1.27–4.84; IL‐10: quartile 2, OR = 2.22, 95% CI = 1.09–4.56). APFC was associated with high serum levels of IL‐6 (quartile 3, OR = 1.32, 95% CI = 1.02–1.72), pleural effusions were associated with high serum levels of IL‐1β, IL‐6, IL‐8, and IL‐10 (IL‐1β: quartile 4, OR = 2.36, 95% CI = 1.21–4.58; IL‐6: quartile 3, OR = 4.67, 95% CI = 2.27–9.61; IL‐8: quartile 3, OR = 2.95, 95% CI = 1.51–5.79; IL‐10: quartile 4, OR = 3.20, 95% CI = 1.61–6.36), and high serum levels of IL‐6 and IL‐10 were associated with an increased risk of ascites (IL‐6: quartile 3, OR = 3.01, 95% CI = 1.42–6.37; IL‐10: quartile 3, OR = 2.57, 95% CI = 1.23–5.37).Conclusion: Serum cytokine levels, including IL‐1β, IL‐6, IL‐8, and IL‐10 may be associated with the occurrence of early complications of AP. In daily clinical practice, IL‐6 may be the most worthwhile cytokine to be detected.