Objective:To evaluate the efficacy and safety of endoscopic injection sclerotherapy (EIS) and endoscopic rubber band ligation (ERBL) for the treatment of grade Ⅰ-Ⅲ internal hemorrhoids.Methods:A prospective study was conducted on patients with grade Ⅰ-Ⅲ internal hemorrhoids who sought treatment at Renmin Hospital of Wuhan University or the NO.2 People's Hospital of Fuyang City from November 2021 to November 2022. Eligible patients were continuously enrolled based on inclusion and exclusion criteria and randomized into 2 groups using a central randomization system: the EIS group and the ERBL group. The primary outcomes included symptom improvement rate, recurrence rate, incidence of adverse events (bleeding, anal distension, pain, urinary retention, etc.), surgical costs, patient satisfaction, hemorrhoidal disease symptom score (HDSS), European quality of life 5-dimensions (EQ-5D) score, and self-rated health status score.Results:A total of 203 patients were enrolled (86 from Renmin Hospital of Wuhan University and 117 from the NO.2 People's Hospital of Fuyang City), with 103 in the EIS group and 100 in the ERBL group. Both groups successfully completed endoscopic treatment for internal hemorrhoids. The surgical cost in the EIS group was significantly lower than that in the ERBL group (1 044.77±522.77 yuan VS 2 538.44±465.63 yuan, t=-21.660, P<0.001). The incidence of perioperative pain and moderate-to-severe pain in the EIS group was significantly lower than that in the ERBL group [2.91% (3/103) VS 25.00% (25/100), χ2=20.817, P<0.001; 0.97% (1/103) VS 18.00% (18/100), χ2=17.344, P<0.001]. There were no significant differences in the incidence of perioperative bleeding, anal distension, or urinary retention between the two groups [0.97% (1/103) VS 1.00% (1/100), 11.65% (12/103) VS 19.00% (19/100), 0.00% (0/103) VS 2.00% (2/100), P>0.05]. During the 12-week follow-up, 4 patients were lost to follow-up (all from the EIS group). There were no significant differences in symptom improvement rate, recurrence rate, or patient satisfaction rate between the two groups [96.97% (96/99) VS 96.00% (96/100), 3.03% (3/99) VS 5.00% (5/100), 97.98% (97/99) VS 95.00% (95/100), P>0.05]. At 12 weeks postoperatively, the HDSS in the EIS group significantly decreased compared to preoperative levels [0.0 (0.0, 1.0) VS 5.0 (3.0, 7.0), Z=-18.270, P<0.010], the EQ-5D score in the ERBL group significantly increased compared to preoperative levels (1.00±0.01 VS 0.98±0.03, F=27.527, P<0.010), and self-rated health status score in the ERBL group significantly increased compared to preoperative levels (92.31±6.89 VS 82.62±10.98, F=115.025, P<0.010). At 12 weeks postoperatively, the HDSS in the ERBL group significantly decreased compared to preoperative levels [0.0 (0.0, 1.0) VS 5.0 (4.0, 8.0), Z=-16.110, P<0.010], the EQ-5D score in the ERBL group significantly increased compared to preoperative levels (1.00±0.00 VS 0.98±0.05, F=13.718, P<0.010), and self-rated health status score in the ERBL group significantly increased compared to preoperative levels (93.46±6.35 VS 84.15±10.71, F=123.695, P<0.010). Conclusion:Both EIS and ERBL are safe and effective treatments for grade Ⅰ-Ⅲ internal hemorrhoids, with high patient satisfaction. Comparatively, EIS demonstrates lower surgical costs and a reduced incidence and severity of perioperative pain.

Objective:To develop a deep learning-based system for real-time recognition and classification of portal hypertensive gastropathy (PHG) and evaluate its ability to assist junior endoscopists.Methods:A total of 2 848 gastroscopy images from 832 patients with liver cirrhosis were selected from Digestive Endoscopy Center databases of Renmin Hospital of Wuhan University, Wuhan Hospital of Traditional Chinese and Western Medicine, and the Second Hospital of Jingzhou from January 2015 to October 2023. This system referred to 3 endoscopic features of Baveno Ⅱ scoring system. Three models were developed respectively for gastric antral vascular ectasia (GAVE), mosaic-like pattern (MLP), and red marks (RM). The specific classification references were as follows: (1) GAVE model: 0 no, 1 yes; (2) MLP model: 0 no, 1 mild, 2 severe; (3) RM model: 0 no, 1 isolated, 2 fused. The classification results for endoscopic characteristics of PHG of 3 endoscopy experts were taken as the gold standard. The yolov8-m model was used for training. The training dataset, validation dataset, and test dataset were allocated at a ratio of 8∶1∶1. The test dataset was used to evaluate the performance of models and their auxiliary effects on endoscopists. The accuracy, recall, precision, specificity and Kappa coefficient were calculated. Results:The accuracy, recall, specificity of GAVE model were 96.0% (48/50), 87.5% (7/8) and 97.6% (41/42). There was no significant difference between its accuracy and the gold standard ( χ2=316.226, P=1.000). The precision of GAVE1 and GAVE0 were 87.5% (7/8) and 97.6% (41/42) respectively. The accuracy of MLP model was 84.1% (132/157), and there was no significant difference compared with the gold standard ( χ2=3.286, P=0.193). The precision and recall of MLP2 were 88.2% (15/17) and 75.0% (15/20). The precision and recall of MLP1 were 77.9% (60/77) and 88.2% (60/68). The precision and recall of MLP0 were 90.5% (57/63) and 82.6% (57/69). The accuracy of RM model was 87.9% (123/140), and there was no significant difference compared with the gold standard ( χ2=2.891, P=0.409). The precision and recall of RM2 were 94.7% (18/19) and 78.3% (18/23). The precision and recall of RM1 were 72.2% (26/36) and 81.3% (26/32). The precision and recall of RM0 were 92.9% (79/85) and 92.9% (79/85). The mean accuracy of the three junior endoscopists, with and without the assistance of the GAVE model, MLP model, and RM model, respectively increased from 95.3% to 99.3%, from 83.9% to 91.9%, and from 81.9% to 83.1%. The overall consistency analysis of the 3 junior endoscopists with the gold standard indicated that the consistency of the GAVE model before and after assistance was extremely strong (both an overall Kappa of 1.000); the consistency before assistance of the MLP model was moderate (with an overall Kappa of 0.601), which increased to extremely strong after assistance (with an overall Kappa of 0.964); and the consistency of the RM model before and after assistance was also relatively strong (with an overall Kappa of 0.792 before and 0.798 after). Conclusion:The deep learning system accurately identifies and classifies PHG features and significantly enhances diagnostic performance of junior endoscopists.

Objective:To construct and validate an artificial intelligence diagnostic system based on multi-feature integration for diagnosing gastric whitish neoplastic lesions under white-light endoscopy.Methods:Gastroscopic images from Renmin Hospital of Wuhan University and the Seventh Medical Center of Chinese PLA General Hospital were collected from November 2012 to July 2021. A total of 823 images of gastric whitish lesions from 267 patients were finally selected. Five white-light endoscopic features associated with gastric whitish lesions were selected through a literature search, including lesion location, boundary clarity, surface texture, roundness, and depression status. Images with manually annotated features were used to train machine learning models, with the optimal model selected as the multi-feature fitting diagnostic system, which assigned diagnostic weights to each feature. A conventional deep learning model was trained with the same dataset. The diagnostic performance of the two models were compared, and eight endoscopists of varying expertise were invited to participate in human-machine comparisons.Results:Accuracy, sensitivity, and specificity of the multi-feature fitting diagnostic system were 82.11% (101/123), 78.43% (40/51), and 84.72% (61/72), respectively. Feature weights in descending order were depression (0.71), lesion location (0.11), surface roughness (0.08), boundary clarity (0.06), and subcircular shape (0.04). The diagnostic accuracy of the system was significantly higher than that of non-expert endoscopists (82.11% VS 74.31%, Z=-2.785, P=0.008) and comparable to that of expert endoscopists (82.11% VS 83.20%, Z=-0.696, P=0.700). There was no significant difference in accuracy between the multi-feature fitting diagnostic system and the traditional deep learning model [82.11% (101/123) VS 82.93% (102/123), P=1.000]. Conclusion:The feature-weighted artificial intelligence diagnostic system for gastric whitish neoplastic lesions demonstrates clinically relevant diagnostic accuracy under white-light endoscopy.

Objective:To analyze interobserver variability in endoscopic diagnostic accuracy of chronic atrophic gastritis (CAG) among endoscopists with varying levels of experience.Methods:Endoscopic examination data from 247 patients who underwent endoscopy from January 2021 to June 2024 at Department of Gastroenterology, the First Affiliated Hospital of Army Medical University ( n=154), Renmin Hospital of Wuhan University ( n=35) and Shanxi Provincial Coal Central Hospital ( n=58) were retrospectively collected. The collected images were reviewed by an expert panel of three individuals with the title of deputy chief physician or above. The final endoscopic Kimura-Takemoto classification diagnosis of the expert panel was regarded as the golden standard. Fourteen endoscopists from the above three centers provided their Kimura-Takemoto classification diagnosis. These endoscopists were divided into the junior group ( n=7, with experience of <2 000 procedures) and the senior group ( n=7, with experience of >10 000 procedures). The difference in the accuracy of endoscopic Kimura-Takemoto classification diagnosis between the groups were analyzed. Results:Diagnostic accuracy for Kimura-Takemoto classification ranged from 65.99% (163/247) to 86.64% (214/247) in the senior group with the overall accuracy of 77.27% (1 336/1 729). The junior group exhibited diagnostic accuracy ranging from 36.44% (90/247) to 72.47% (179/247) with the overall accuracy of 62.12% (1 074/1 729). The senior group demonstrated higher overall diagnostic accuracy than that of the junior group ( χ 2=93.27, P<0.001). The diagnostic accuracy of non-CAG in the senior group was higher than that in the junior group [83.73% (463/553) VS 72.33% (400/553), χ 2=20.27, P<0.001]. The diagnostic accuracy of C-type atrophy in the senior group was higher than that in the junior group [90.10% (801/889) VS 82.79% (736/889), χ 2=19.66, P<0.001] .The diagnostic accuracy of O-type atrophy in the senior group was higher than that in the junior group [83.97% (241/287) VS 68.29% (196/287), χ 2=18.56, P<0.001]. Conclusion:Interobserver variability is observed in the diagnostic accuracy of endoscopic Kimura-Takemoto classification for CAG among endoscopists with different experience levels. Experienced endoscopists exhibit higher diagnostic accuracy for CAG compared with their less experienced counterparts.

Objective:To analyze interobserver variability in endoscopic diagnostic accuracy of chronic atrophic gastritis (CAG) among endoscopists with varying levels of experience.Methods:Endoscopic examination data from 247 patients who underwent endoscopy from January 2021 to June 2024 at Department of Gastroenterology, the First Affiliated Hospital of Army Medical University ( n=154), Renmin Hospital of Wuhan University ( n=35) and Shanxi Provincial Coal Central Hospital ( n=58) were retrospectively collected. The collected images were reviewed by an expert panel of three individuals with the title of deputy chief physician or above. The final endoscopic Kimura-Takemoto classification diagnosis of the expert panel was regarded as the golden standard. Fourteen endoscopists from the above three centers provided their Kimura-Takemoto classification diagnosis. These endoscopists were divided into the junior group ( n=7, with experience of <2 000 procedures) and the senior group ( n=7, with experience of >10 000 procedures). The difference in the accuracy of endoscopic Kimura-Takemoto classification diagnosis between the groups were analyzed. Results:Diagnostic accuracy for Kimura-Takemoto classification ranged from 65.99% (163/247) to 86.64% (214/247) in the senior group with the overall accuracy of 77.27% (1 336/1 729). The junior group exhibited diagnostic accuracy ranging from 36.44% (90/247) to 72.47% (179/247) with the overall accuracy of 62.12% (1 074/1 729). The senior group demonstrated higher overall diagnostic accuracy than that of the junior group ( χ 2=93.27, P<0.001). The diagnostic accuracy of non-CAG in the senior group was higher than that in the junior group [83.73% (463/553) VS 72.33% (400/553), χ 2=20.27, P<0.001]. The diagnostic accuracy of C-type atrophy in the senior group was higher than that in the junior group [90.10% (801/889) VS 82.79% (736/889), χ 2=19.66, P<0.001] .The diagnostic accuracy of O-type atrophy in the senior group was higher than that in the junior group [83.97% (241/287) VS 68.29% (196/287), χ 2=18.56, P<0.001]. Conclusion:Interobserver variability is observed in the diagnostic accuracy of endoscopic Kimura-Takemoto classification for CAG among endoscopists with different experience levels. Experienced endoscopists exhibit higher diagnostic accuracy for CAG compared with their less experienced counterparts.

Objective:To evaluate the efficacy and safety of endoscopic injection sclerotherapy (EIS) and endoscopic rubber band ligation (ERBL) for the treatment of grade Ⅰ-Ⅲ internal hemorrhoids.Methods:A prospective study was conducted on patients with grade Ⅰ-Ⅲ internal hemorrhoids who sought treatment at Renmin Hospital of Wuhan University or the NO.2 People's Hospital of Fuyang City from November 2021 to November 2022. Eligible patients were continuously enrolled based on inclusion and exclusion criteria and randomized into 2 groups using a central randomization system: the EIS group and the ERBL group. The primary outcomes included symptom improvement rate, recurrence rate, incidence of adverse events (bleeding, anal distension, pain, urinary retention, etc.), surgical costs, patient satisfaction, hemorrhoidal disease symptom score (HDSS), European quality of life 5-dimensions (EQ-5D) score, and self-rated health status score.Results:A total of 203 patients were enrolled (86 from Renmin Hospital of Wuhan University and 117 from the NO.2 People's Hospital of Fuyang City), with 103 in the EIS group and 100 in the ERBL group. Both groups successfully completed endoscopic treatment for internal hemorrhoids. The surgical cost in the EIS group was significantly lower than that in the ERBL group (1 044.77±522.77 yuan VS 2 538.44±465.63 yuan, t=-21.660, P<0.001). The incidence of perioperative pain and moderate-to-severe pain in the EIS group was significantly lower than that in the ERBL group [2.91% (3/103) VS 25.00% (25/100), χ2=20.817, P<0.001; 0.97% (1/103) VS 18.00% (18/100), χ2=17.344, P<0.001]. There were no significant differences in the incidence of perioperative bleeding, anal distension, or urinary retention between the two groups [0.97% (1/103) VS 1.00% (1/100), 11.65% (12/103) VS 19.00% (19/100), 0.00% (0/103) VS 2.00% (2/100), P>0.05]. During the 12-week follow-up, 4 patients were lost to follow-up (all from the EIS group). There were no significant differences in symptom improvement rate, recurrence rate, or patient satisfaction rate between the two groups [96.97% (96/99) VS 96.00% (96/100), 3.03% (3/99) VS 5.00% (5/100), 97.98% (97/99) VS 95.00% (95/100), P>0.05]. At 12 weeks postoperatively, the HDSS in the EIS group significantly decreased compared to preoperative levels [0.0 (0.0, 1.0) VS 5.0 (3.0, 7.0), Z=-18.270, P<0.010], the EQ-5D score in the ERBL group significantly increased compared to preoperative levels (1.00±0.01 VS 0.98±0.03, F=27.527, P<0.010), and self-rated health status score in the ERBL group significantly increased compared to preoperative levels (92.31±6.89 VS 82.62±10.98, F=115.025, P<0.010). At 12 weeks postoperatively, the HDSS in the ERBL group significantly decreased compared to preoperative levels [0.0 (0.0, 1.0) VS 5.0 (4.0, 8.0), Z=-16.110, P<0.010], the EQ-5D score in the ERBL group significantly increased compared to preoperative levels (1.00±0.00 VS 0.98±0.05, F=13.718, P<0.010), and self-rated health status score in the ERBL group significantly increased compared to preoperative levels (93.46±6.35 VS 84.15±10.71, F=123.695, P<0.010). Conclusion:Both EIS and ERBL are safe and effective treatments for grade Ⅰ-Ⅲ internal hemorrhoids, with high patient satisfaction. Comparatively, EIS demonstrates lower surgical costs and a reduced incidence and severity of perioperative pain.

Objective:To develop a deep learning-based system for real-time recognition and classification of portal hypertensive gastropathy (PHG) and evaluate its ability to assist junior endoscopists.Methods:A total of 2 848 gastroscopy images from 832 patients with liver cirrhosis were selected from Digestive Endoscopy Center databases of Renmin Hospital of Wuhan University, Wuhan Hospital of Traditional Chinese and Western Medicine, and the Second Hospital of Jingzhou from January 2015 to October 2023. This system referred to 3 endoscopic features of Baveno Ⅱ scoring system. Three models were developed respectively for gastric antral vascular ectasia (GAVE), mosaic-like pattern (MLP), and red marks (RM). The specific classification references were as follows: (1) GAVE model: 0 no, 1 yes; (2) MLP model: 0 no, 1 mild, 2 severe; (3) RM model: 0 no, 1 isolated, 2 fused. The classification results for endoscopic characteristics of PHG of 3 endoscopy experts were taken as the gold standard. The yolov8-m model was used for training. The training dataset, validation dataset, and test dataset were allocated at a ratio of 8∶1∶1. The test dataset was used to evaluate the performance of models and their auxiliary effects on endoscopists. The accuracy, recall, precision, specificity and Kappa coefficient were calculated. Results:The accuracy, recall, specificity of GAVE model were 96.0% (48/50), 87.5% (7/8) and 97.6% (41/42). There was no significant difference between its accuracy and the gold standard ( χ2=316.226, P=1.000). The precision of GAVE1 and GAVE0 were 87.5% (7/8) and 97.6% (41/42) respectively. The accuracy of MLP model was 84.1% (132/157), and there was no significant difference compared with the gold standard ( χ2=3.286, P=0.193). The precision and recall of MLP2 were 88.2% (15/17) and 75.0% (15/20). The precision and recall of MLP1 were 77.9% (60/77) and 88.2% (60/68). The precision and recall of MLP0 were 90.5% (57/63) and 82.6% (57/69). The accuracy of RM model was 87.9% (123/140), and there was no significant difference compared with the gold standard ( χ2=2.891, P=0.409). The precision and recall of RM2 were 94.7% (18/19) and 78.3% (18/23). The precision and recall of RM1 were 72.2% (26/36) and 81.3% (26/32). The precision and recall of RM0 were 92.9% (79/85) and 92.9% (79/85). The mean accuracy of the three junior endoscopists, with and without the assistance of the GAVE model, MLP model, and RM model, respectively increased from 95.3% to 99.3%, from 83.9% to 91.9%, and from 81.9% to 83.1%. The overall consistency analysis of the 3 junior endoscopists with the gold standard indicated that the consistency of the GAVE model before and after assistance was extremely strong (both an overall Kappa of 1.000); the consistency before assistance of the MLP model was moderate (with an overall Kappa of 0.601), which increased to extremely strong after assistance (with an overall Kappa of 0.964); and the consistency of the RM model before and after assistance was also relatively strong (with an overall Kappa of 0.792 before and 0.798 after). Conclusion:The deep learning system accurately identifies and classifies PHG features and significantly enhances diagnostic performance of junior endoscopists.

Objective:To construct and validate an artificial intelligence diagnostic system based on multi-feature integration for diagnosing gastric whitish neoplastic lesions under white-light endoscopy.Methods:Gastroscopic images from Renmin Hospital of Wuhan University and the Seventh Medical Center of Chinese PLA General Hospital were collected from November 2012 to July 2021. A total of 823 images of gastric whitish lesions from 267 patients were finally selected. Five white-light endoscopic features associated with gastric whitish lesions were selected through a literature search, including lesion location, boundary clarity, surface texture, roundness, and depression status. Images with manually annotated features were used to train machine learning models, with the optimal model selected as the multi-feature fitting diagnostic system, which assigned diagnostic weights to each feature. A conventional deep learning model was trained with the same dataset. The diagnostic performance of the two models were compared, and eight endoscopists of varying expertise were invited to participate in human-machine comparisons.Results:Accuracy, sensitivity, and specificity of the multi-feature fitting diagnostic system were 82.11% (101/123), 78.43% (40/51), and 84.72% (61/72), respectively. Feature weights in descending order were depression (0.71), lesion location (0.11), surface roughness (0.08), boundary clarity (0.06), and subcircular shape (0.04). The diagnostic accuracy of the system was significantly higher than that of non-expert endoscopists (82.11% VS 74.31%, Z=-2.785, P=0.008) and comparable to that of expert endoscopists (82.11% VS 83.20%, Z=-0.696, P=0.700). There was no significant difference in accuracy between the multi-feature fitting diagnostic system and the traditional deep learning model [82.11% (101/123) VS 82.93% (102/123), P=1.000]. Conclusion:The feature-weighted artificial intelligence diagnostic system for gastric whitish neoplastic lesions demonstrates clinically relevant diagnostic accuracy under white-light endoscopy.

Objective To explore the risk factors for myocardial injury in esophagogastric variceal bleeding(EGVB)patients with liver cirrhosis during hospitalization.Methods A case-control trial was conducted on 235 EGVB patients admitted to our hospital between May 2021 and July 2022.Their basic information,laboratory results and relevant data during hospitalization were collected.According to their myocardial enzyme profiles during hospitalization,they were divided into myocardial injury group(n=46)and non-myocardial injury group(n=189).Univariate regression analysis and clinical correlation analysis were used to preliminarily screen the risk factors for myocardial injury secondary to EGVB caused by liver cirrhosis.Then,multivariate logistic regression analysis was used to further screen the risk factors.A nomogram was constructed based on the selected risk factors and the occurrence of myocardial injury.Receiver operating characteristic(ROC)curve was plotted to analyze the independent predictive value of these factors alone or combined together.Calibration curve analysis and internal verification were utilized to evaluate the predictive performance of the nomogram model.Subgroup verification was performed in the myocardial infarction group.Results Univariate analysis revealed that statistical differences were observed in age,sex,hypertension,renal disease,underlying diseases,vomiting,leukocytosis,increased alanine aminotransferase(ALT)or aspartate aminotransferase(AST),albumin,red blood cell hematocrit(HCT),international normalized ratio(INR),endoscopy within 6 h after admission,and Child-Pugh(CP)class between the myocardial injury group and the non-myocardial injury group(P＜0.01).Multivariate logistic regression analysis showed that age(P=0.014,OR=1.153,95％CI:1.030～1.291),underlying diseases(P=0.005,OR=1.122,95％CI:1.032～2.437),and albumin(P=0.012,OR=0.449,95％CI:0.241～0.837)were independent risk factors for inhospital myocardial injury in EGVB patients with liver cirrhosis.The AUC value of the above indicators combined together for predicting myocardial injury was 0.902.Hosmer-Lemeshow test and calibration curve analysis indicated that the nomogram had good prediction consistency(Chi-square=12.88,P=0.615).Internal verification correctly distinguished 86.4％of verification objects.Subgroup analysis of myocardial injury patients showed that albumin was also an independent risk factor for in-hospital myocardial injury in this population(AUC=0.80).Conclusion Age,underlying diseases,and albumin level are independent risk factors for in-hospital myocardial injury in EGVB patients with liver cirrhosis.Albumin level can be used as an independent risk factor for predicting myocardial infarction.Combination of the above 3 indicators has a high diagnostic value in early identification and prevention of myocardial injury in this patient population.

Gastric cancer is a common malignant tumor with complex pathological mechanisms， a low early diagnosis rate， and a high mortality rate. However， surgical treatment， targeted therapy， and chemotherapy have their treatment limitations and toxic side effects. Therefore， exploring the pathogenesis and mechanism of gastric cancer and finding effective treatment methods are important. At present， researches has found that tumor epithelial cells exhibit individual differences in molecular characteristics and exhibit metabolic heterogeneity that affects cell phenotype and function. The interaction between metabolites and cytokines can inhibit the formation of the tumor immune microenvironment and promote malignant progression. Therefore， metabolic reprogramming is regarded as a key feature of tumors and plays an important role in the process of tumor occurrence and development. However， the continuous deterioration of gastric cancer may be closely related to changes in the energy metabolism of cancer cells. Gastric cancer cells may regulate the dysregulation of synthesis or decomposition pathways such as glucose metabolism， amino acid metabolism， lipid metabolism， and nucleotide metabolism and activate associated signaling pathways， key proteins， and genes， leading to proliferation， invasion， and metastasis of cancer cells. In recent years， there has been a close relationship between the effective intervention by traditional Chinese medicine in gastric cancer and the regulation of metabolic reprogramming. There has been some progress in the intervention research on effective ingredients and formulas of traditional Chinese medicine for cancer. This article summarized existing Chinese and foreign literature on how gastric cancer cells affect disease progression by regulating their related metabolic networks， such as glucose metabolism， amino acid metabolism， lipid metabolism， and nucleotide metabolism， as well as how effective ingredients and formulas of traditional Chinese medicine enhance anti-tumor effects through targeted metabolism. It reviewed metabolic reprogramming intervention in gastric cancer， providing a reference for research on metabolic reprogramming regulation by traditional Chinese medicine and new targets and strategies for the treatment and prognosis of gastric cancer.