Gastric cancer (GC) occupies the first few places in the world among tumors in terms of incidence and mortality, causing serious harm to human health, and at the same time, its treatment greatly consumes the health care resources of all countries in the world. The diagnosis of GC is usually based on histopathologic examination, and it is very important to be able to detect and identify cancerous lesions at an early stage, but some endoscopists' lack of diagnostic experience and fatigue at work lead to a certain rate of under diagnosis. The rapid and striking development of Artificial intelligence (AI) has helped to enhance the ability to extract abnormal information from endoscopic images to some extent, and more and more researchers are applying AI technology to the diagnosis of GC. This initiative has not only improved the detection rate of early gastric cancer (EGC), but also significantly improved the survival rate of patients after treatment. This article reviews the results of various AI-assisted diagnoses of EGC in recent years, including the identification of EGC, the determination of differentiation type and invasion depth, and the identification of borders. Although AI has a better application prospect in the early diagnosis of ECG, there are still major challenges, and the prospects and limitations of AI application need to be further discussed.

As a global health concern, gastric cancer management has been systematized by individual countries and regions into regimented guidelines. To explore international differences, we examined the guidelines of Korea, Japan, Europe, and the United States. Guidelines are created by experts in the field, focusing on evidence-based recommendations to standardize and improve patient care, but the methodology for guideline creation, incorporation of new innovations, and review differs significantly. National and regional differences within the guidelines are apparent, stemming from various factors including local incidence, stage, presentation, patient preferences, and governmental influences. Differences include the use of neoadjuvant chemotherapy, criteria for endoscopic resection, and extent of lymphadenectomy. Nonetheless, fundamental treatment principles remain universal, and the goals of national guidelines are uniform: standardizing patient care, providing the highest quality treatments, incorporating cutting-edge clinical trial results, and consensus in guidelines to help formulate governmental policies. This review highlights how the guidelines are constructed, the unique elements of each guideline, how they differ, and why they differ.

Artificial intelligence is rapidly transforming quality assurance in healthcare, driving advancements in diagnostics, surgery, and patient care. This review presents a comprehensive analysis of artificial intelligence integration-particularly convolutional and recurrent neural networks-across key clinical domains, significantly enhancing diagnostic accuracy, surgical performance, and pathology evaluation. Artificial intelligence-based approaches have demonstrated clear superiority over conventional methods: convolutional neural networks achieved 91.56% accuracy in scanner fault detection, surpassing manual inspections; endoscopic lesion detection sensitivity rose from 2.3% to 6.1% with artificial intelligence assistance; and gastric cancer invasion depth classification reached 89.16% accuracy, outperforming human endoscopists by 17.25%. In pathology, artificial intelligence achieved 93.2% accuracy in identifying out-of-focus regions and an F1 score of 0.94 in lymphocyte quantification, promoting faster and more reliable diagnostics. Similarly, artificial intelligence improved surgical workflow recognition with over 81% accuracy and exceeded 95% accuracy in skill assessment classification. Beyond traditional diagnostics and surgical support, AI-powered wearable sensors, drug delivery systems, and biointegrated devices are advancing personalized treatment by optimizing physiological monitoring, automating care protocols, and enhancing therapeutic precision. Despite these achievements, challenges remain in areas such as data standardization, ethical governance, and model generalizability. Overall, the findings underscore artificial intelligence's potential to outperform traditional techniques across multiple parameters, emphasizing the need for continued development, rigorous clinical validation, and interdisciplinary collaboration to fully realize its role in precision medicine and patient safety.

This study estimated the participation rate and effectiveness of endoscopic screening of upper gastrointestinal cancer (UGIC) in China.From 2014 to 2015, we recruited 192805 adults from seven cities in China to build a prospective cohort for UGIC screening, including esophageal cancer and gastric cancer. Overall, 39991 participants were at high risk for UGIC according to an established risk score system and were recommended for endoscopic examination. Participation rates were reported, and their associated factors were explored. After inverse probability of treatment weighting (IPTW) based on propensity scores, Poisson regression was used to estimate the incidence rate ratio (IRR) and 95%CI for UGIC incidence and mortality between screened and non-screened groups from cohort entry until 31 December 2021.10442 participants underwent endoscopy, giving a participation rate of 26.1%. Higher participation was observed among individuals with higher education levels, history of upper gastrointestinal diseases, and family history of cancer. After a median follow-up of 6.8 years (interquartile range 6.7-6.9), UGIC incidences after IPTW were 94.6 per 100000 person-years in the screened group and 84.7 per 100000 person-years in the non-screened group. The weighted UGIC mortality rates were 13.1 and 33.4 per 100 000 person-years, respectively. The screened group had significantly lower UGIC mortality than the non-screened group, with a weighted IRR of 0.39 (95%CI 0.19-0.82).Participation in endoscopic screening among a high-risk UGIC population in China was low. We found that one-time endoscopic screening significantly reduced mortality caused by UGIC.

To explore the impact of magnifying endoscopy with narrow-band imaging (ME-NBI) combined with refined nursing management on the endoscopic diagnosis of early gastric cancer.

Patients who underwent painless gastroscopy at the Affiliated Hospital of Zunyi Medical University from January 1, 2021 to December 31, 2021 were randomly selected as study subjects. They were randomly divided into an experimental group and a control group. The experimental group received ME-NBI examination and refined nursing interventions included psychological support, environmental management, and structured patient preparation to optimize endoscopic conditions. The control group received routine endoscopic examination and nursing. The gastric cancer detection rates, patient compliance, and mucosal visibility were evaluated. The patient compliance scale used in this study evaluates adherence based on medication intake, positional changes, and examination cooperation.

A total of 998 patients were included, with 499 in each group. The gastric cancer detection rate was significantly higher in the experimental group (4.2%) compared to the control group (0.6%) (χ2 = 13.721, p < 0.0001). Patients were randomly assigned to an experimental group (n = 499) receiving ME-NBI with refined nursing, and a control group (n = 499) receiving routine care. There were no statistically significant differences in general data such as gender, age, family history of gastric cancer, and Helicobacter pylori infection between the two groups (all p > 0.05), indicating comparability. In the experimental group, 334 cases (66.93%) had good compliance scores (9-10 points) and 165 cases (33.07%) had general compliance scores (6-8 points), while in the control group, 31 cases (6.21%) had good compliance scores and 468 cases (93.79%) had general compliance scores. Patient compliance was significantly higher in the experimental group compared to the control group (χ2 = 396.569, p < 0.0001), indicating that refined nursing can improve patient compliance. In addition, the comparison of gastric mucosal visibility scores during endoscopic examination showed that in the experimental group, 384 cases (76.95%) scored 1 point, 115 cases (23.05%) scored 2 points, and 0 cases (0.00%) scored 3 points; while in the control group, 27 cases (5.41%) scored 1 point, 228 cases (45.69%) scored 2 points, and 244 cases (48.90%) scored 3 points. The mucosal visibility was significantly higher in the experimental group compared to the control group (χ2 = 591.322, p < 0.0001), indicating that refined nursing can improve gastric mucosal visibility. The gastric cancer detection rate was significantly higher in the experimental group (4.2%) compared to the control group (0.6%) (χ2 = 13.721, p < 0.0001), indicating that refined care can improve the gastric cancer detection rate.

The application of refined nursing management combined with ME-NBI technology for the diagnosis of early gastric cancer can significantly improve patient compliance, gastric mucosal visibility, and gastric cancer detection rate, which is worthy of clinical promotion and application.

Cancer cachexia is a pathological state characterized by severe weight loss, skeletal muscle depletion, and adipose tissue reduction. Cancer cachexia is observed in gastric cancer (GC) with a higher incidence over 80%. Approximately 80% patients with advanced GC including scirrhous gastric cancer (SGC), which has the worst prognosis among all GC, are affected with cachexia. The exact pathophysiology in SGC cancer cachexia remains elusive, and therapeutic approaches for the cancer cachexia have not been established. Patient-derived cancer cachexia models are promising for elucidating the underlying mechanisms of disease progression and developing novel treatments, none of which originate from SGC. Therefore, we established a novel cancer cachexia-inducing cell line, designated Aku60GC, through stepwise selection of a patient-derived SGC cell line, HSC-60. Subcutaneous implantation of the Aku60GC cells into nude mice resulted in weight loss, muscle atrophy, and adipose tissue depletion with high reproducibility, accompanied by elevation of the circulating cytokines IL-8 and IL-18. Compared to parental HSC-60 cells, Aku60GC cells exhibited additional genomic changes, such as AKT2 and CCNE1 gains, a somatic mutation of RUNX1, and accelerated growth. Thus, our results demonstrate that the Aku60GC cell line is a valuable resource for research on cancer cachexia in SGC.

Magnifying endoscopy combined with narrow-band imaging endoscopy is an emerging method for early gastric cancer screening and diagnosis However, its effectiveness is closely related to the cleaning quality of the gastric mucosal preparation. H. pylori infection is a major risk factor for inadequate gastric mucosa cleaning quality preparation. Multiple medications are useful in helping patients with gastric mucosal cleansing preparations. This randomized controlled trial study protocol aims to investigate the effect of different combinations of medications on the quality of gastric mucosal cleansing in an H. pylori-infected population.

This study is a prospective, randomized, single-blind, single-center trial. The subjects are patients who require magnifying endoscopy combined with narrow-band imaging and have evidence of H. pylori infection (a non-invasive diagnostic 13C urea breath test was used to examine the study subjects). These patients will be randomly assigned to the control group (Group A) and the experimental groups (Groups B, C, D, E, and F). Each group will consist of 44 patients, with a total of 264 patients expected to be enrolled. The core content of the drug preparation regimen for each group is as follows: Group A (control group) will take 10 ml of simethicone before the examination; Group B (experimental group) will take 20,000 units of pronase before the examination; Group C (experimental group) will take 600 mg of N-acetylcysteine before the examination; Group D (experimental group) will take 10 ml of simethicone +20,000 units of pronase before the examination; Group E (experimental group) will take 10 ml of simethicone + 600 mg of N-acetylcysteine before the examination; Group F (experimental group) will take 10 ml of simethicone + 20,000 units of pronase + 1 g of sodium bicarbonate before the examination. All group medications will be dissolved in 50 ml of warm water at 20-40°C. All patients will fast for ≥6 h and abstain from drinking for 2 h before the examination. The primary endpoint is the gastric mucosa cleanliness score. Secondary endpoints include the early detection rate of gastric cancer, polyp detection rate, adenoma detection rate, procedure time, number of irrigations, patient medication compliance, preoperative anxiety, incidence of adverse reactions, overall patient satisfaction, and willingness to undergo the examination again.

The results of this research project are aimed at improving the quality of gastric mucosal cleansing preparations in the H. pylori population to meet the demand for early diagnosis and treatment prevention screening for early gastric cancer screening. The implementation of the results of the study and their inclusion in the guidelines may reduce economic expenditures by reflecting a reduced need for social and health care services.

Chinese Clinical Trial Registry (ChiCTR). Number of identification: (ChiCTR2400087510).

Laser endoscopy has a linked color imaging (LCI) mode which has been reported to be superior to white light imaging (WLI) in detecting early gastric cancer (EGC). In this study, we retrospectively investigated the characteristics of superficial gastric neoplasms detected not by WLI but by LCI.

From April 2018 to May 2023, EGC or gastric adenoma identified by EGD was observed using LCI after WLI. The size, location, macroscopic type, color, skill level of the endoscopists, and treatment were examined for lesions detected by WLI (WLI group) and lesions detected not by WLI but by LCI (LCI group).

Eighty-eight lesions of EGCs were differentiated adenocarcinomas, 13 undifferentiated adenocarcinomas, and 28 gastric adenomas. There were 117 lesions (90.7%) in the WLI group and 12 (9.2%) in the LCI group. The mean diameter was 22.9 mm in the WLI group and 9.3 mm in the LCI group, with the latter being significantly smaller (p = 0.003). The numbers of protruding, depressed, and flat lesions were 58, 59, and 0 in the WLI group, and 7, 4, and 1 in the LCI group, respectively, indicating that more protruding lesions were detected in the LCI group (p = 0.005). After multivariate analysis, there was a significant difference in diameter only in the LCI group compared to the WLI group (odds ratio, 0.834; 95% CI, 0.728-0.956).

LCI is more useful than WLI for detecting smaller superficial gastric neoplasms.

Tryptophan (Trp) is an essential amino acid that must be acquired exclusively through dietary intake. The metabolism of tryptophan plays a critical role in maintaining immune homeostasis and tolerance, as well as in preventing excessive inflammatory responses. Tryptophan-2,3-dioxygenase (TDO2) is a tetrameric heme protein and serves as one of the pivotal rate-limiting enzymes in the first step of tryptophan metabolism. Dysregulation of TDO2 expression has been observed in various digestive system diseases, encompassing those related to the oral cavity, esophagus, liver, stomach, pancreas, and colon and rectum. Digestive system diseases are the most common clinical diseases, with complex clinical manifestations and interrelated symptoms, and have become a research hotspot in the field of medicine. Studies have demonstrated that aberrant TDO2 expression is closely associated with various clinical manifestations and disease outcomes in patients with digestive system disorders. Consequently, TDO2 has garnered increasing recognition as a promising therapeutic target for digestive system diseases in recent years, attracting growing attention. This article provides a brief overview of the role of TDO2 in the tryptophan pathway, emphasizing its significant involvement in diseases of the digestive system. Strategies targeting TDO2 through specific inhibitors suggest considerable promise in enhancing therapeutic outcomes for digestive diseases. Thus, this review concludes by discussing recent advancements in the development of TDO2 inhibitors. We believe that targeted inhibition of TDO2 combined with immunotherapy, the screening of a large number of natural products, and the assistance of artificial intelligence in drug design will be important directions for developing more effective TDO2 inhibitors and improving treatment outcomes in the future.

The treatment of early gastric cancer (EGC) is contingent upon the status of lymph node metastasis (LNM). Accurate preoperative prediction of LNM is critical for reducing unnecessary surgeries. This study seeks to evaluate the risk factors for LNM in submucosal EGC and develop a predictive model to optimize therapeutic decision-making.

A retrospective analysis was performed on clinical data from 389 patients with T1b-stage EGC who underwent radical gastrectomy. Univariate and multivariate analyses were conducted to identify independent risk factors, followed by the development of a nomogram to predict LNM. The model's efficacy was validated through receiver operating characteristic curves, calibration curves, and decision curve analysis.

Of the 389 patients, 77 had LNM. Logistic regression analysis identified gender, CA199 levels, tumor location, degree of differentiation, presence of ulcers, and lymph node enlargement on CT as independent risk factors for LNM. A nomogram was constructed to assess the risk of LNM, demonstrating strong predictive accuracy with an area under the curve of 0.82 in the training set and 0.74 in the validation set, along with good sensitivity and positive predictive value.

This study presents a reliable preoperative nomogram to estimate the likelihood of LNM in submucosal EGC, providing valuable guidance for determining the most effective treatment strategies for patients.

The clinical value of incorporating lipid and inflammatory factors to predict long-term survival in patients with gastric cancer (GC) is unreported. This study aimed to investigate the clinical value of nomograms integrating the Circulating Lipid and Inflammation Risk Score (CLIRS) for predicting the long-term outcome of patients with GC.

A retrospective analysis included patients with GC who underwent radical resection at four tertiary medical centers. Patients were divided into training and validation cohorts, with least absolute shrinkage and selection operator regression selecting optimal lipid and inflammatory indicators related to GC prognosis. The CLIRS was developed from six indicators: lymphocyte, triglycerides, total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and apolipoprotein B.

Overall, 2534 patients were studied, including 1910 in the training cohort and 624 in the validation cohort. The CLIRS was an independent risk factor for overall survival (OS; hazard ratio [HR] 1.529, 95% confidence interval [CI] 1.271-1.839; p < 0.001) and disease-free survival (DFS; HR 1.511, 95% CI 1.267-1.801; p < 0.001) in GC patients. The OS nomogram (area under the receiver operating characteristic curve 0.823 vs. 0.785; p < 0.05) and DFS nomogram (AUC 0.804 vs. 0.770; p < 0.05) based on the CLIRS outperformed pTNM stage. High-risk patients had earlier and more sustained recurrence, with higher rates of local, peritoneal, and distant recurrences (p < 0.05).

The CLIRS, combining circulating lipid and inflammatory factors, is an independent prognostic factor for patients with GC. Nomograms incorporating the CLIRS are superior to pTNM stage in predicting postoperative survival and recurrence in patients with GC.

To identify high-risk gastric carcinoma patients with concurrent vascular and neural invasion ("double invasion") who are at heightened risk of progression-free survival (PFS) decline, enabling personalized clinical management.

In this multi-center retrospective study, 559 patients with double invasion who underwent curative gastrectomy between May 2002 and December 2020 were analyzed. Prognostic factors for PFS were identified using Lasso-Cox regression. Model validation included internal bootstrapping, calibration plots, and comparison against the American Joint Committee on Cancer(AJCC) 8th edition TNM staging system via Harrell's C-index, decision curve analysis (DCA), and time-dependent receiver operating characteristic (ROC) curves.

The nomogram integrated gender, positive lymph node count, surgical gastrectomy method, PTEN/FHIT expression levels, and maximum tumor diameter. It demonstrated superior predictive accuracy to AJCC staging, with a C-index of 0.651 (95% CI: 0.612-0.691) versus 0.543 (95% CI: 0.517-0.569). Calibration plots showed strong agreement between predicted and observed outcomes. The area under the curve(AUC) for 3- and 5-year PFS predictions were 0.719 (95% CI: 0.655-0.771) and 0.767 (95% CI: 0.670-0.841), respectively. DCA confirmed clinical utility across decision thresholds, and risk stratification effectively differentiated low- and high-risk groups. In the training cohort, the model significantly outperformed AJCC staging (NRI: 0.218, p < 0.01; IDI: 0.085, p < 0.01). However, this superiority was not statistically significant in the validation cohort (NRI: 0.141, p = 0.08; IDI: 0.031, p = 0.239).

We developed a Lasso-Cox regression-based nomogram to stratify PFS risk in gastric carcinoma patients with double invasion. While the model outperformed AJCC staging in training, validation cohort results highlight the need for further refinement. This tool holds potential for guiding tailored therapeutic strategies, though broader validation is warranted to confirm clinical applicability.

This study aimed to investigate the efficacy of radical resection and postoperative adjuvant chemotherapy on the survival benefit in patients with pancreatic ductal adenocarcinoma (PDAC), stratified by age, frailty, and other factors in actual clinical practice.

We retrospectively analyzed the clinicopathological and follow-up data of 414 patients with PDAC who underwent surgical resection at nine institutions under the Yamaguchi Pancreat/Biliary Disease Study Group, between January 1997 and December 2016. Recurrence-free survival (RFS) and overall survival (OS) were calculated using the Kaplan-Meier method. Associations between survival and prognostic factors were evaluated by univariate and multivariate analyses.

There were 30.5% of patients with PDAC who were aged < 65 years, 37.9% aged 65-74 years, 17.6% aged 75-79 years, and 14.0% aged ≥ 80 years. Notably, RFS declined with increasing age (median RFS: 12.9, 10.2, 9.4, and 7.4 months, respectively), although the differences were not significant (p = 0.223). OS significantly decreased with age (median OS: 21.6, 21.2, 17.0, and 13.9 months, respectively; p = 0.005). In patients aged < 75 years, independent prognostic factors identified by univariate and multivariate analyses included lymph node metastasis (hazard ratio [HR], 1.598; p = 0.007), tumor size (HR, 1.489; p = 0.043), R status (HR, 1.536; p = 0.011), and serum albumin levels (HR, 1.526; p = 0.031). In patients aged ≥ 75 years, a high modified frailty index (HR, 2.446; p = 0.012) emerged as an independent prognostic factor, along with lymph node metastasis, CA19-9 level (HR, 1.897; p = 0.017), and R status (HR, 2.087; p = 0.007).

The prognosis for older patients with PDAC was shorter than that of younger patients. Frailty may contribute to their poorer prognosis in older age.

Patients diagnosed with pathologic T1N0 esophageal squamous cell carcinoma and treated with surgery alone have a good prognosis and are generally followed up without adjuvant therapy. However, recurrence has been observed in this patient group. Therefore, this study aimed to identify recurrence and prognostic factors in patients with pathologic T1N0 esophageal squamous cell carcinoma who were treated with surgery alone.

Of the 532 patients who underwent esophagectomy with R0 resection at Hiroshima University Hospital between August 2003 and November 2018, 124 who underwent only esophagectomy and had pathological T1N0 esophageal squamous cell carcinoma were included in the study. Recurrence and prognostic factors were analyzed and details of recurrence were evaluated.

The 5-year recurrence-free survival and 5-year overall survival rates were 84.7% and 87.2%, respectively. Recurrence was observed in 12 (9.7%) patients. Univariate and multivariate analyses showed that the histologic type (poorly differentiated compared with others) and lymphatic and/or vascular invasion (positive compared with negative) were statistically significant for recurrence-free survival. Kaplan-Meier curves for recurrence-free survival and overall survival showed that prognosis was significantly stratified according to these factors. All patients with poorly differentiated and positive lymphatic and/or vascular invasion experienced recurrence and recurrence pattern is all distant metastases.

Poorly differentiated and lymphatic and/or vascular invasion are important recurrence and prognostic predictors in pathologic T1N0 esophageal squamous cell carcinoma treated with surgery alone. Patients with these prognostic factors experienced increased recurrence rates, often with distant metastasis. Therefore, adjuvant therapy may be beneficial for such patients and follow-ups should be performed at closer intervals.

Background/Objectives: Gastric cancer (GC) is the leading cause of cancer-related deaths worldwide. C118P, a microtubule inhibitor with anti-angiogenic and vascular-disrupting activities, was proven to be cytotoxic to various cancer cell lines. This study aimed to explore the anti-tumor effect of C118P against gastric cancer and identify its potential target. Methods: The MTT assay, colony formation assay, and EdU incorporation assay were used to evaluate the effect of C118P on GC cell proliferation. Cell cycle and cell apoptosis were measured using flow cytometry. Molecular docking, a microscale thermophoresis (MST) analysis, and the cellular thermal shift assay (CETSA) were used to investigate the binding of C118P to RAB1A. Autophagy-related effects were evaluated by using the MDC staining assay, immunofluorescence assay, and immunoblotting assay. The SGC-7901 cell line xenograft mouse model was used to confirm the anti-tumor efficacy of C118P. Results: C118P dramatically inhibited proliferation, induced G2/M cell cycle arrest, and triggered apoptosis in GC cell lines HGC-27 and SGC-7901. Mechanistically, C118P was demonstrated to bind with RAB1A and reduce the RAB1A protein level, accompanied by the inhibition of mTORC1 signaling. Moreover, C118P induced autophagosome formation and promoted RAB1A protein degradation in an autophagy-lysosomal-dependent manner. The in vivo study verified that C118P inhibits GC growth by inhibiting the RAB1A-mTOR axis. Conclusions: Our findings suggested that C118P inhibits GC growth by promoting the autophagy-lysosomal-dependent degradation of RAB1A and modulating mTOR C1 signaling. C118P shows potential as being a small molecule drug effective in the treatment of gastric cancer via targeting RAB1A.

Gastric cancer represents a significant global health challenge with elevated incidence and mortality rates, highlighting the need for advancements in diagnostic and therapeutic strategies. This review paper addresses the critical need for a thorough synthesis of the role of artificial intelligence (AI) in the management of gastric cancer. It provides an in-depth analysis of current AI applications, focusing on their contributions to early diagnosis, treatment planning, and outcome prediction. The review identifies key gaps and limitations in the existing literature by examining recent studies and technological developments. It aims to clarify the evolution of AI-driven methods and their impact on enhancing diagnostic accuracy, personalizing treatment strategies, and improving patient outcomes. The paper emphasizes the transformative potential of AI in overcoming the challenges associated with gastric cancer management and proposes future research directions to further harness AI's capabilities. Through this synthesis, the review underscores the importance of integrating AI technologies into clinical practice to revolutionize gastric cancer management.

The risk of gastric cancer can be predicted by gastroscopic manifestation recognition and the Kyoto Gastritis Score. This study aims to validate the applicability of AI approaches for recognizing gastroscopic manifestations according to the definition of Kyoto Gastritis Score, with the goal of improving early gastric cancer detection and reducing gastric cancer mortality.

In this retrospective study, 29013 gastric endoscopy images were collected and carefully annotated into five categories according to the Kyoto Gastritis Score, i.e. atrophy (A), diffuse redness (DR), enlarged folds (H), intestinal metaplasia (IM), and nodularity (N). As a multi-label recognition task, we propose a deep learning approach composed of five GAM-EfficientNet models, each performing a multiple classification to quantify gastroscopic manifestations, i.e. no presentation or the severity score 0-2. This approach was compared with endoscopists of varying years of experience in terms of accuracy, specificity, precision, recall, and F1 score.

The approach demonstrated good performance in identifying the five manifestations of the Kyoto Gastritis Score, with an average accuracy, specificity, precision, recall, and F1 score of 78.70%, 91.92%, 80.23%, 78.70%, and 0.78, respectively. The average performance of five experienced endoscopists was 72.63%, 90.00%, 77.68%, 72.63%, and 0.73, while that of five less experienced endoscopists was 66.60%, 87.44%, 70.88%, 66.60%, and 0.66, respectively. The sample t-test indicates that the approach's average accuracy, specificity, precision, recall, and F1 score for identifying the five manifestations were significantly higher than those of less experienced endoscopists, experienced endoscopists, and all endoscopists on average (p < 0.05).

Our study demonstrates the potential of deep learning approaches on gastric manifestation recognition over junior, even senior endoscopists. Thus, the deep learning approach holds potential as an auxiliary tool, although prospective validation is still needed to assess its clinical applicability.

Gastric cancer (GC) is highly heterogeneous, and accurate preoperative assessment of lymph node status remains challenging. We aimed to develop a multiparametric MRI-based model for predicting lymph node metastasis (LNM) in GC and to explore its prognostic implications.

In this dual-center retrospective study, 479 GC patients undergoing preoperative multiparametric MRI before radical gastrectomy were enrolled. 1595 imaging features were extracted from T2-weighted imaging, apparent diffusion coefficient maps, and contrast-enhanced T1-weighted imaging (cT1WI), respectively. Feature selection steps, including the Boruta and Simulated Annealing algorithms, were conducted to identify key features. Different radiomics models (RMs) based on the single- and multiple-sequence were constructed. The performance of various RMs in predicting LNM was assessed in terms of discrimination, calibration, and clinical usefulness. Additionally, Kaplan-Meier survival curves were employed to estimate differences in disease-free survival (DFS) and overall survival (OS).

The multi-sequence radiomics model (MRM) achieved area under the curves (AUCs) of 0.774 [95 % confidence interval (CI), 0.703-0.845], 0.721 (95 % CI, 0.593-0.850), and 0.720 (95 % CI, 0.639-0.801) in the training and two validation cohorts, respectively, outperforming the single-sequence RMs. Notably, the RM derived from cT1WI demonstrated superior performance compared to the other two single-sequence models. Furthermore, the proposed MRM exhibited a significant association with DFS and OS in GC patients (both P < 0.05).

The multiparametric MRI-based radiomics model, derived from primary lesions, demonstrated moderate performance in predicting LNM and survival outcomes in patients with GC, which could provide valuable insights for personalized treatment strategies.

Gastric cancer ranks fifth for incidence and fourth in the leading causes of mortality worldwide. In this study, we aimed to validate previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm, called ALPHAON® in detecting gastric neoplasm.

We used the retrospective data of 500 still images, including 5 benign gastric ulcers, 95 with gastric cancer, and 400 normal images. Thereby we validated the CADe algorithm measuring accuracy, sensitivity, and specificity with the result of receiver operating characteristic curves (ROC) and area under curve (AUC) in addition to comparing the diagnostic performance status of four expert endoscopists, four trainees, and four beginners from two university-affiliated hospitals with CADe algorithm. After a washing-out period of over 2 weeks, endoscopists performed gastric detection on the same dataset of the 500 endoscopic images again marked by ALPHAON®.

The CADe algorithm presented high validity in detecting gastric neoplasm with accuracy (0.88, 95% CI: 0.85 to 0.91), sensitivity (0.93, 95% CI: 0.88 to 0.98), specificity (0.87, 95% CI: 0.84 to 0.90), and AUC (0.962). After a washing-out period of over 2 weeks, overall validity improved in the trainee and beginner groups with the assistance of ALPHAON®. Significant improvement was present, especially in the beginner group (accuracy 0.94 (0.93 to 0.96) p < 0.001, sensitivity 0.87 (0.82 to 0.92) p < 0.001, specificity 0.96 (0.95 to 0.97) p < 0.001).

The high validation performance state of the CADe algorithm system was verified. Also, ALPHAON® has demonstrated its potential to serve as an endoscopic educator for beginners improving and making progress in sensitivity and specificity.

The benefit of adjuvant therapy for patients with IB gastric cancer (GC) is a topic of debate. This study aimed to evaluate the benefit of adjuvant therapy for patients with IB GC.

Overall, the study selected 510 IB GC patients after gastrectomy at the First Medical Center of the Chinese PLA General Hospital, Beijing, China between 2005 and 2018. Overall survival (OS) and disease-free survival (DFS) were analyzed using the Kaplan-Meier method and the log-rank test. Cox regression analyses were used to confirm the independent prognostic factors.

Patients who received postoperative adjuvant therapy had a longer 5-year OS (92.9 %) than those who received surgery alone (86.7 %; P < 0.05), but the 5-year DFS did not differ significantly between the two groups (92.6 vs. 95.0 %; P > 0.05). Moreover, DFS did not differ between monotherapy, and combination therapy. Uni- and multivariate analyses showed that older age was a significant risk factor for tumor recurrence. Subgroup analyses also failed to identify suitable candidates for chemotherapy.

Because adjuvant therapy did not demonstrate any benefits in terms of tumor recurrence or DFS, these treatment strategies may be unnecessary for IB GC patients after gastrectomy. Further studies are required to identify subgroups of IB GC patients who may benefit from adjuvant treatments.

Gastric cancer with macroscopic peritoneal metastases represents a major therapeutic challenge and is associated with a poor prognosis. This review aims to evaluate the efficacy and safety of new treatment modalities. A systematic search of PubMed was conducted to identify studies published between January 2014 and April 2024. Inclusion criteria were trials investigating novel therapies for gastric cancer with peritoneal metastases. Data on treatment efficacy, survival outcomes, and side effects were extracted.

The inflammatory response plays a crucial role in tumor development. Inflammatory markers are recognized prognostic factors in many types of cancer, including gastric cancer. However, the correlation between inflammatory markers and prognosis in remnant gastric cancer (RGC) remains unclear. The aim of this study was to evaluate the importance of inflammatory markers as a prognostic factor in patients who underwent gastrectomy for RGC.

This multicenter retrospective study involved 107 patients with RGC who underwent curative gastrectomy at 10 institutions in Japan between January 2000 and December 2016. Both overall survival (OS) and relapse-free survival (RFS) were analyzed.

Receiver operating characteristic analyses indicated that the lymphocyte/monocyte ratio (LMR) had a higher area under the curve compared with other potential prognostic factors. Patients were categorized into high- and low LMR groups by the optimal LMR cutoff value. Preoperative LMR was significantly correlated with reconstruction way after the primary surgery (p=0.032) and lymphatic invasion (p=0.046). OS and RFS were significantly worse in the low- vs high LMR groups. Low LMR, T3 or deeper tumor invasion, and low body mass index were independent prognostic factors for OS and RFS.

Preoperative low LMR is associated with poor OS and RFS in patients who undergo gastrectomy for RGC.

Clinical findings and postoperative follow-up data on remnant gastric cancer (RGC) are limited due to its rarity. Additionally, the preoperative staging, radical surgery, and managing recurrence in RGC present significant clinical challenges.

We analyzed the clinicopathological findings, adjuvant chemotherapy, and patterns of postoperative recurrence of 313 consecutive patients who underwent curative surgery for RGC at 17 Japanese institutions. This study investigated the optimal management of RGC and the impact of adjuvant chemotherapy (AC) on recurrence-free survival (RFS).

Pathological stages I, II, and III were observed in 55.9% (N = 175), 24.9% (N = 78), and 19.2% (N = 60) of the patients, respectively. The overall concordance rate between clinical and pathological T staging was 58.3%, with a clinical T4 sensitivity of 41.4% for diagnosing pathological T4. During the median follow-up period of 4.6 years, disease recurrence occurred in 24.3% of patients. Most recurrences (over 80%) occurred within 2.5 years, and 96.1% within 5 years after RGC surgery. Peritoneal recurrence was the most common in patients with advanced RGC, accounting for 14.1% in stage II and 28.3% in stage III. Multivariable regression analysis showed that AC was significantly associated with a longer RFS, with a hazard ratio of 0.45 (95% confidence interval: 0.26-0.76).

Our study underscores the importance of early detection, accurate preoperative staging, and postoperative surveillance in managing advanced RGC cases. Despite some limitations, our findings indicate that AC may provide survival benefits comparable to those seen in primary gastric cancer.

Previous studies have proved the effectiveness of endoscopic screening in rural areas; however, long-term, high-quality evidence regarding the effectiveness of risk-adapted upper gastrointestinal cancer (UGC) sequential screening strategies in resource-rich regions is currently lacking.

The objectives were to validate the effectiveness of risk-adapted sequential screening strategies in UGC prevention and control and assess the potential of sequential screening to lower mortality rates.

Based on the Cancer Screening Program in Urban China, a prospective, large-scale cohort study based on population was conducted to recruit individuals from 4 cities in China from 2013-2019. Those identified as having a high risk of UGC according to a validated risk-score model were advised to undergo endoscopy tests. Follow-up outcomes were tracked until June 2021. Incidence of UGC, UGC-related mortality, and all-cause mortality were evaluated between the screened and nonscreened cohorts.

The study included 153,079 participants at baseline. In total, 113,916 (74.42%) of the participants were designated as low risk of UGC. The remaining 39,163 (25.68%) participants were deemed to be at high risk of UGC and were offered gastroscopy tests. Among the high-risk participants, 9627 (compliance rate 24.6%) adhered to the gastroscopy tests. Over a median follow-up of 6.05 (IQR 3.06-7.06) years, 622 UGC cases, 180 UGC deaths, and 1958 all-cause death cases were traced. The screened cohort exhibited the highest cumulative incidence of UGC (119.2 per 100,000 person-years), followed by the nonscreened and low-risk cohorts. Obvious reductions in both all-cause mortality and UGC mortality were observed between those who undertook screening (153.7 and 4.7 per 100,000 person-years, respectively) and the nonscreened group (245.3 and 27 per 100,000 person-years, respectively). The screening population showed a significant 36% and 82% reduction in both all-cause mortality (hazard ratio [HR] 0.64, 95% CI 0.49-0.83, P<.001) and UGC mortality (HR 0.18, 95% CI 0.04-0.74, P=.02), respectively, compared to the nonscreened group. Reductions of 35% in all-cause mortality (HR 0.65, 95% CI 0.49-0.86, P=.003) and 81% in UGC mortality (HR 0.19, 95% CI 0.05-0.80, P=.02) were observed in participants aged older than 55 years in the screened group compared to the nonscreened group. The reductions in all-cause mortality and UGC mortality were statistically significant in males (all-cause mortality: HR 0.64, 95% CI 0.47-0.88, P=.005; UGC mortality: HR 0.10, 95% CI 0.01-0.72, P=.02), but significant reductions were not observed in females (all P values were >.05).

Our study suggests the significance of one-off risk-adapted UGC screening in reducing both all-cause mortality and UGC mortality, particularly among high-risk individuals, indicating its effectiveness in UGC prevention and management.

Although the dissected lymph node number in remnant gastric cancer (RGC) may be smaller than in primary proximal gastric cancer (PGC), altered lymphatic flow provides different metastatic patterns in lymph nodes, which could potentially give rise to prognostic differences between RGC and PGC with nodal metastasis.

Between 1993 and 2020, 2546 consecutive patients with gastric cancer underwent gastrectomy. Of these, 53 patients with RGC and 381 patients with PGC with pathologic TNM stage I-III gastric cancer underwent curative gastrectomy. We reviewed their hospital records retrospectively.

The number of dissected lymph nodes was significantly smaller in patients with RGC than in patients with PGC (P < .001; RGC, 13.0 vs PGC, 34.5). Although the 5-year overall survival (OS) rate did not differ between RGC and PGC in all patients, the prognosis in each pathologic N (pN) stage of RGC was worse than that of PGC, suggesting that each lymph node metastasis has a greater prognostic effect in RGC. In particular, even with patients with pN1 (20.0%) or pN2 RGC (40.0%), their 5-year OS rates were poor and similar to those of patients with pN3 PGC (35.7%). The presence of lymph node metastasis in RGC (hazard ratio [HR], 4.41; 95% CI, 1.02-18.9; P = .045) was an independent and a similar prognostic impact in pN3 PGC (HR, 2.82; 95% CI, 1.57-5.07; P < .001). Lymph node metastasis in RGC more strongly affected peritoneal or lymph node recurrence rather than hematogenous recurrence.

The presence of lymph node metastasis yielded a poorer prognosis in patients with RGC than patients with primary PGC. Patients with RGC with lymph node metastasis should be specifically targeted in an effort to improve their prognosis.

Cysteine desulfurase (NFS1) is highly expressed in a variety of tumors, which is closely related to ferroptosis of tumor cells and affects prognosis. The relationship between NFS1 and the development of gastric cancer (GC) remains unknown. Here we showed that NFS1 expression was significantly higher in GC tissues compared to adjacent normal tissues. Patients with high expression of NFS1 in GC tissues had a lower overall survival rate than those with low expression. NFS1 was highly expressed in cultured GC cells compared to normal gastric cells. Knockdown of NFS1 expression reduced the viability, migration and invasion of GC cells. In cultured GC cells, NFS1 deficiency promoted ferroptosis. Mechanistically, NFS1 inhibited ferroptosis by upregulating the signal transduction and activator of transcription 3 (STAT3) signaling pathway in cultured GC cells. NFS1 knockdown using siRNA inhibited the STAT3 pathway, reduced the expression of glutathione peroxidase 4 (GPX4) and solute carrier family 7 member 11 (SLC7A11), and elevated intracellular levels of reactive oxygen species (ROS), ferrous ion (Fe2+), and malondialdehyde (MDA) in cultured GC cells. A specific STAT3 activator significantly reversed the inhibitory effect of NFS1 deficiency on ferroptosis in cultured GC cells. These in vitro results were further confirmed by experiments in vivo using a mouse xenograft tumor model. Collectively, THESE RESULTS INDICATE THAT NFS1 is overexpressed in human GC tissues and correlated with prognosis. NFS1 inhibits ferroptosis by activating the STAT3 pathway in GC cells. These results suggest that NFS1 may be a potential prognostic biomarker and therapeutic target to treat GC.

Colorectal cancer is the third most common cancer worldwide, accounting for 10% of cancer deaths. Therefore, this study was performed with the aim of spatial analysis of risk factors for colorectal cancer in Iran.

This study was conducted ecologically using STEPS information (The WHO Stepwise Approach to NCD Risk Factor Surveillance) in Iran. To analyze the data, the researcher used cluster analysis and Geographically Weighted Regression methods with the help of ArcGIS version 10.

The results of OLS analysis showed that there was a significant relationship between tobacco consumption (B = 0.571, p-value = 0.044) and smoking (B = 0.772, p-value = 0.010) and the incidence of colon cancer (CC). There was also a significant relationship between abdominal obesity and the incidence of rectal cancer (RC) (B = 0.061, p-value = 0.027).

This study showed that (CC) high-risk areas are located in central and northern parts of Iran, and the significant risk factors related to CC and RC were found to be tobacco use, cigarette smoking, and abdominal obesity. These findings are helpful to inform policymakers to plan screening services to reduce CC and RC, especially in high-risk populations.

Cysteine desulfurase (NFS1) is closely associated with the occurrence and development of human tumors, but its relationship with the prognosis and immunity of gastric cancer (GC) patients remains unclear.

To study the relationship between NFS1 and GC, GC-related data of TCGA were downloaded and analyzed. At the same time, Tumor Immune Estimation Resource (TIMER) and Kaplan‒Meier Plotter were used for relevant online analysis. Clinical samples were collected for immunohistochemical testing to validate the results.

The mRNA and protein levels of NFS1 in GC tissues were significantly higher than those in normal tissues. In terms of the operating characteristic curve (ROC), the area under the curve (AUC) was 0.793, indicating that NFS1 had a high diagnostic value for GC. Further analysis showed that NFS1 expression was highly correlated with the depth of tumor invasion, lymph node metastasis, and tumor stage. Survival analysis showed that patients with high expression of NFS1 had a poorer prognosis, and NFS1 was an independent risk factor. Enrichment analysis by GO, KEGG, and GSEA showed that NFS1 was enriched in immune-related pathways. The expression of NFS1 was significantly positively correlated with the proportion of macrophages M0 and plasma cells but negatively correlated with the proportion of B cells memory, monocytes, and mast cells resting. In addition, NFS1 expression was significantly correlated with TMB levels and responses to immunotherapy.

Our results suggest that NFS1 may be a potential biomarker for the diagnosis and prediction of prognosis and immunotherapy efficacy in GC.

The extracellular matrix (ECM) has been demonstrated to be dysregulated and crucial for malignant progression in gastric cancer (GC), but the mechanism is not well understood. Here, that discoidin domain receptor 1 (DDR1), a principal ECM receptor, is recognized as a key driver of GC progression is reported. Mechanistically, DDR1 directly interacts with the PAS domain of hypoxia-inducible factor-1α (HIF-1α), suppresses its ubiquitination and subsequently strengthens its transcriptional regulation of angiogenesis. Additionally, DDR1 upregulation in GC cells promotes actin cytoskeleton reorganization by activating HIF-1α/ Ras Homolog Family Member A (RhoA)/Rho-associated protein kinase 1 (ROCK1) signaling, which in turn enhances the metastatic capacity. Pharmacological inhibition of DDR1 suppresses GC progression and angiogenesis in patient-derived xenograft (PDX) and organoid models. Taken together, this work first indicates the effects of the DDR1-HIF-1α axis on GC progression and reveals the related mechanisms, providing experimental evidence for DDR1 as a therapeutic target for GC.

Minute gastric cancers (MGCs) have a favorable prognosis, but they are too small to be detected by endoscopy, with a maximum diameter ≤ 5 mm.

To explore endoscopic detection and diagnostic strategies for MGCs.

This was a real-world observational study. The endoscopic and clinicopathological parameters of 191 MGCs between January 2015 and December 2022 were retrospectively analyzed. Endoscopic discoverable opportunity and typical neoplastic features were emphatically reviewed.

All MGCs in our study were of a single pathological type, 97.38% (186/191) of which were differentiated-type tumors. White light endoscopy (WLE) detected 84.29% (161/191) of MGCs, and the most common morphology of MGCs found by WLE was protruding. Narrow-band imaging (NBI) secondary observation detected 14.14% (27/191) of MGCs, and the most common morphology of MGCs found by NBI was flat. Another three MGCs were detected by indigo carmine third observation. If a well-demarcated border lesion exhibited a typical neoplastic color, such as yellowish-red or whitish under WLE and brownish under NBI, MGCs should be diagnosed. The proportion with high diagnostic confidence by magnifying endoscopy with NBI (ME-NBI) was significantly higher than the proportion with low diagnostic confidence and the only visible groups (94.19% > 56.92% > 32.50%, P < 0.001).

WLE combined with NBI and indigo carmine are helpful for detection of MGCs. A clear demarcation line combined with a typical neoplastic color using nonmagnifying observation is sufficient for diagnosis of MGCs. ME-NBI improves the endoscopic diagnostic confidence of MGCs.

Esophagogastroduodenoscopy is the most important tool to detect gastric cancer (GC). In this study, we developed a computer-aided detection (CADe) system to detect GC with white light imaging (WLI) and linked color imaging (LCI) modes and aimed to compare the performance of CADe with that of endoscopists.

The system was developed based on the deep learning framework from 9,021 images in 385 patients between 2017 and 2020. A total of 116 LCI and WLI videos from 110 patients between 2017 and 2023 were used to evaluate per-case sensitivity and per-frame specificity.

The per-case sensitivity and per-frame specificity of CADe with a confidence level of 0.5 in detecting GC were 78.6% and 93.4% for WLI and 94.0% and 93.3% for LCI, respectively (p < 0.001). The per-case sensitivities of nonexpert endoscopists for WLI and LCI were 45.8% and 80.4%, whereas those of expert endoscopists were 66.7% and 90.6%, respectively. Regarding detectability between CADe and endoscopists, the per-case sensitivities for WLI and LCI were 78.6% and 94.0% in CADe, respectively, which were significantly higher than those for LCI in experts (90.6%, p = 0.004) and those for WLI and LCI in nonexperts (45.8% and 80.4%, respectively, p < 0.001); however, no significant difference for WLI was observed between CADe and experts (p = 0.134).

Our CADe system showed significantly better sensitivity in detecting GC when used in LCI compared with WLI mode. Moreover, the sensitivity of CADe using LCI is significantly higher than those of expert endoscopists using LCI to detect GC.

The current pathologic N (pN) classification exhibits limitations in the prognostic stratification of patients with pT3-4N0-2M0 gastric cancer (GC). Therefore, this study aimed to develop and validate a new lymph nodal staging method based on the number of examined lymph nodes (ELNs) and lymph node ratio (LNR).

Data from 7883 patients with pT3-4N0-2M0 GC were collected from the Surveillance, Epidemiology, and End Results (SEER) database and Zhejiang Cancer Provincial Hospital. Optimal cutoff values for ELNs and LNR were determined using X-tile software. Kaplan-Meier methods, Log-rank tests, and Cox regression analyses were employed in this study. Patients were categorized into 3 new pN stages: new pN0 (pN0 with ELNs of >16), new pN1 (pN0 with ELNs of ≤16 or pN1-2 with LNR of ≤0.15), and new pN2 (pN1-2 with LNR of >0.15). The prognostic predictive power of both current and new pN staging was evaluated using the Akaike information criterion (AIC), Bayesian information criterion, concordance index (C-index), and receiver operating characteristic curve.

The new pN classification exhibited excellent performance in Kaplan-Meier survival analysis. After adjusting for confounding factors, the new pN staging emerged as an independent prognostic indicator in patients with GC. In the SEER cohort, the new pN staging demonstrated enhanced prognostic prediction accuracy over the American Joint Committee on Cancer pN staging (AIC: 75578.85 vs 75755.06; C-index: 0.642 vs 0.630; P < .001). Similar findings were validated in the Chinese cohort.

This study developed and validated an improved pN classification for patients with pT3-4N0-2M0 GC. Surgeons should consider ELNs and LNR when assessing postoperative prognosis in patients with GC.

Gastric cancer (GC) is one of the most common clinical malignant tumors worldwide, with high morbidity and mortality. Presently, the overall response rate to immunotherapy is low, and current methods for predicting the prognosis of GC are not optimal. Therefore, novel biomarkers with accuracy, efficiency, stability, performance ratio, and wide clinical application are needed. Based on public data sets, the chemotherapy cohort and immunotherapy cohort from Sun Yat-sen University Cancer Center, a series of bioinformatics analyses, such as differential expression analysis, survival analysis, drug sensitivity prediction, enrichment analysis, tumor immune dysfunction and exclusion analysis, single-sample gene set enrichment analysis, stemness index calculation, and immune cell infiltration analysis, were performed for screening and preliminary exploration. Immunohistochemical staining and in vitro experiments were performed for further verification. Overexpression of COX7A1 promoted the resistance of GC cells to Oxaliplatin. COX7A1 may induce immune escape by regulating the number of fibroblasts and their cellular communication with immune cells. In summary, measuring the expression levels of COX7A1 in the clinic may be useful in predicting the prognosis of GC patients, the degree of chemotherapy resistance, and the efficacy of immunotherapy.

Artificial intelligence (AI) using deep learning systems has recently been utilized in various medical fields. In the field of gastroenterology, AI is primarily implemented in image recognition and utilized in the realm of gastrointestinal (GI) endoscopy. In GI endoscopy, computer-aided detection/diagnosis (CAD) systems assist endoscopists in GI neoplasm detection or differentiation of cancerous or noncancerous lesions. Several AI systems for colorectal polyps have already been applied in colonoscopy clinical practices. In esophagogastroduodenoscopy, a few CAD systems for upper GI neoplasms have been launched in Asian countries. The usefulness of these CAD systems in GI endoscopy has been gradually elucidated.

In this review, we outline recent articles on several studies of endoscopic AI systems for GI neoplasms, focusing on esophageal squamous cell carcinoma (ESCC), esophageal adenocarcinoma (EAC), gastric cancer (GC), and colorectal polyps. In ESCC and EAC, computer-aided detection (CADe) systems were mainly developed, and a recent meta-analysis study showed sensitivities of 91.2% and 93.1% and specificities of 80% and 86.9%, respectively. In GC, a recent meta-analysis study on CADe systems demonstrated that their sensitivity and specificity were as high as 90%. A randomized controlled trial (RCT) also showed that the use of the CADe system reduced the miss rate. Regarding computer-aided diagnosis (CADx) systems for GC, although RCTs have not yet been conducted, most studies have demonstrated expert-level performance. In colorectal polyps, multiple RCTs have shown the usefulness of the CADe system for improving the polyp detection rate, and several CADx systems have been shown to have high accuracy in colorectal polyp differentiation.

Most analyses of endoscopic AI systems suggested that their performance was better than that of nonexpert endoscopists and equivalent to that of expert endoscopists. Thus, endoscopic AI systems may be useful for reducing the risk of overlooking lesions and improving the diagnostic ability of endoscopists.