Developing a Prognostic Model for Primary Biliary Cholangitis Based on a Random Survival Forest Model.

Background: Primary biliary cholangitis (PBC) is a rare autoimmune liver disease with few effective treatments and a poor prognosis, and its incidence is on the rise. There is an urgent need for more targeted treatment strategies to accurately identify high-risk patients. The use of stochastic survival forest models in machine learning is an innovative approach to constructing a prognostic model for PBC that can improve the prognosis by identifying high-risk patients for targeted treatment. Method: Based on the inclusion and exclusion criteria, the clinical data and follow-up data of patients diagnosed with PBC-associated cirrhosis between January 2011 and December 2021 at Taizhou Hospital of Zhejiang Province were retrospectively collected and analyzed. Data analyses and random survival forest model construction were based on the R language. Result: Through a Cox univariate regression analysis of 90 included samples and 46 variables, 17 variables with p-values <0.1 were selected for initial model construction. The out-of-bag (OOB) performance error was 0.2094, and K-fold cross-validation yielded an internal validation C-index of 0.8182. Through model selection, cholinesterase, bile acid, the white blood cell count, total bilirubin, and albumin were chosen for the final predictive model, with a final OOB performance error of 0.2002 and C-index of 0.7805. Using the final model, patients were stratified into high- and low-risk groups, which showed significant differences with a P value <0.0001. The area under the curve was used to evaluate the predictive ability for patients in the first, third, and fifth years, with respective results of 0.9595, 0.8898, and 0.9088. Conclusion: The present study constructed a prognostic model for PBC-associated cirrhosis patients using a random survival forest model, which accurately stratified patients into low- and high-risk groups. Treatment strategies can thus be more targeted, leading to improved outcomes for high-risk patients.

Development and validation of LightGBM algorithm for optimizing of Helicobacter pylori antibody during the minimum living guarantee crowd based gastric cancer screening program in Taizhou, China.

Gastric cancer continues to be a significant health concern in China, with a high incidence rate. To mitigate its impact, early detection and treatment is key. However, conducting large-scale endoscopic gastric cancer screening is not feasible in China. Instead, a more appropriate approach would be to initially screen high-risk groups and follow up with endoscopic testing as needed. We conducted a study on 25,622 asymptomatic participants aged 45-70 years from a free gastric cancer screening program in the Taizhou city government's Minimum Living Guarantee Crowd (MLGC) initiative. Participants completed questionnaires, blood tests, and underwent gastrin-17 (G-17), pepsinogen I and II (PGI and PGII), and H. pylori IgG antibody (IgG) assessments. Using the light gradient boosting machine (lightGBM) algorithm, we developed a predictive model for gastric cancer risk. In the full model, F1 score was 2.66%, precision was 1.36%, and recall was 58.14%. In the high-risk model, F1 score was 2.51%, precision was 1.27%, and recall was 94.55%. Excluding IgG, the F1 score was 2.73%, precision was 1.40%, and recall was 68.62%. We conclude that H. pylori IgG appears to be able to be excluded from the prediction model without significantly affecting its performance, which is important from a health economic point of view. It suggests that screening indicators can be optimized, and expenditures reduced. These findings can have important implications for policymakers, as we can focus resources on other important aspects of gastric cancer prevention and control.

Feasibility of endoscopic resection without laparoscopic assistance for giant gastric subepithelial tumors originating from the muscularis propria layer (with video).

BACKGROUND AND AIMS: Currently, published data of endoscopic resection (ER) for giant (≥ 6 cm) gastric subepithelial tumors originating from the muscularis propria layer (MP-SETs) are extremely rare and limited to only case reports. The aim of this study was thus to assess the feasibility of using ER for giant (≥ 6 cm) gastric MP-SETs in a case series. METHODS: Between July 2013 and December 2020, a total of 23 patients with giant (≥ 6 cm) gastric MP-SETs were treated with ER in the endoscopic center of Taizhou hospital. The study assessed outcomes of en bloc resection, complete resection, total complications, and local residual/recurrence of tumors. RESULTS: The mean procedure time was 112.2 min. En bloc resection was achieved in 22 tumors (95.7%). En bloc removal from the stomach and complete resection were achieved in 6 patients (26.1%). The rate of complete resection differed significantly depending on the minimum tumor diameter (P < 0.001). During hospitalization, 4 patients had complications, including localized peritonitis (3/23, 13.0%) and pulmonary infection (1/23, 4.3%). These 4 patients recovered successfully after conservative medical treatment. Histopathological examination revealed that 18 tumors were gastrointestinal stromal tumors (GISTs), and 5 tumors were leiomyoma. No patients were observed to have residual or recurrent tumors during the follow-up. CONCLUSIONS: Although ER for giant (≥ 6 cm) gastric MP-SETs was associated with several technical challenges and a relatively low complete resection rate, this technique was found to be a feasible therapeutic method for selected patients with a giant (≥ 6 cm) gastric MP-SETs when performed by an experienced endoscopic team.

Feasibility of transgastric endoscopic gallbladder-preserving surgery for benign gallbladder diseases (with video).

BACKGROUND: With the increasing realization of the importance of gallbladder function, choledochoscopic gallbladder-preserving surgery has been advocated for benign gallbladder diseases. However, limited information is available regarding the use of endoscopic gallbladder-preserving surgery (EGPS) for patients with benign gallbladder diseases. The aim of this study was to evaluate the feasibility of EGPS for benign gallbladder diseases. METHODS: Between June 2020 and January 2021, 22 patients with gallbladder stones and/or gallbladder polyps were treated with EGPS. The main outcome measures included the rate of complications, residual gallbladder stones, and gallbladder stone recurrence. RESULTS: In this study, transgastric EGPS was successfully performed in 22 patients (13 female, 9 male) with benign gallbladder diseases, and included 8 cases of multiple gallstones, 4 cases of gallbladder polyps with gallstones, 6 cases of multiple gallbladder polyps, 2 cases of single gallstone, and 2 case of singe gallbladder polyp. The median time of transgastric EGPS was 118 min. During hospitalization, 4 patients suffered localized peritonitis (4/22, 18.2%), and these patients successfully recovered after conservative medical treatment. None of the patients experienced massive bleeding, delayed bleeding, diffuse peritonitis, or any other serious complications. During the median follow-up of 4 months, 1 patient suffered residual gallstone, while no gallstone recurrence or deaths related to transgastric EGPS occurred in any patients. CONCLUSIONS: Transgastric EGPS appears to be a feasible treatment method in selected patients with benign gallbladder diseases. However, as it is a new technique, further studies are needed to explore the long-term effectiveness of transgastric EGPS.

Hydrogen-rich water protects against liver injury in nonalcoholic steatohepatitis through HO-1 enhancement via IL-10 and Sirt 1 signaling.

Nonalcoholic steatohepatitis (NASH) could progress to hepatic fibrosis in the absence of effective control. The purpose of our experiment was to investigate the protective effect of drinking water with a high concentration of hydrogen, namely, hydrogen-rich water (HRW), on mice with nonalcoholic fatty liver disease to elucidate the mechanism underlying the therapeutic action of molecular hydrogen. The choline-supplemented, l-amino acid-defined (CSAA) or the choline-deficient, l-amino acid-defined (CDAA) diet for 20 wk was used to induce NASH and fibrosis in the mice model and simultaneously treated with the high-concentration 7-ppm HRW for different periods (4 wk, 8 wk, and 20 wk). Primary hepatocytes were stimulated by palmitate to mimic liver lipid metabolism during fatty liver formation. Primary hepatocytes were cultured in a closed vessel filled with 21% O2 + 5% CO2 + 3.8% H2 and N2 as the base gas to verify the response of primary hepatocytes in a high concentration of hydrogen gas in vitro. Mice in the CSAA + HRW group had lower serum levels of alanine aminotransferase (ALT) and aspartate aminotransferase (AST) and milder histological damage. The inflammatory cytokines were expressed at lower levels in the HRW group than in the CSAA group. Importantly, HRW reversed hepatocyte fatty acid oxidation and lipogenesis as well as hepatic inflammation and fibrosis in preexisting hepatic fibrosis specimens. Molecular hydrogen inhibits the lipopolysaccharide-induced production of inflammation cytokines through increasing heme oxygenase-1 (HO-1) expression. Furthermore, HRW improved hepatic steatosis in the CSAA + HRW group. Sirtuin 1 (Sirt1) induction by molecular hydrogen via the HO-1/adenosine monophosphate activated protein kinase (AMPK)/peroxisome proliferator-activated receptor α (PPARα)/peroxisome proliferator-activated receptor γ (PPAR-γ) pathway suppresses palmitate-mediated abnormal fat metabolism. Orally administered HRW suppressed steatosis induced by CSAA and attenuated fibrosis induced by CDAA, possibly by reducing oxidative stress and the inflammation response.NEW & NOTEWORTHY The mRNA expression of inflammatory cytokines in the HRW group was lower than in the CSAA group. HRW reversed hepatocyte apoptosis as well as hepatic inflammation and fibrosis in NASH specimens. Molecular hydrogen inhibits LPS-induced inflammation via an HO-1/interleukin 10 (IL-10)-independent pathway. HRW improved hepatic steatosis in the CSAA + HRW group. Sirt1 induction by molecular hydrogen via the HO-1/AMPK/PPARα/PPARγ pathway suppresses palmitate-mediated abnormal fat metabolism.

Endoscopic resection of large (≥ 4 cm) upper gastrointestinal subepithelial tumors originating from the muscularis propria layer: a single-center study of 101 cases (with video).

BACKGROUND AND AIMS: Although endoscopic resection (ER) is already established as a minimally invasive technique for small (< 4.0 cm) upper gastrointestinal subepithelial tumors originating from the muscularis propria layer (MP-SETs), published data of ER for large (≥ 4.0 cm) upper gastrointestinal MP-SETs are extremely rare and limited to case reports. This retrospective study aimed to evaluate the feasibility and safety of ER for large (≥ 4.0 cm) upper gastrointestinal MP-SETs in a large case series. METHODS: Between June 2012 and December 2018, 101 patients with large (≥ 4 cm) upper gastrointestinal MP-SETs were enrolled in this study. The main outcome measures included complete resection, total complications, and local residual or recurrent tumor. RESULTS: The rate of complete resection was 86.1%. Thirteen patients (12.9%) experienced complications including gas-related complications (6/101, 5.9%), localized peritonitis (4/101, 4.0%), esophageal/cardiac mucosal laceration (2/101, 2.0%), and delayed bleeding (1/101, 1.0%). These 13 patients recovered after endoscopic and conservative treatment. The independent risk factor for incomplete resection was tumor size (P = 0.005), and the independent risk factors for total complications were tumor size (P = 0.011) and tumor extraluminal growth (P = 0.037). During the median follow-up of 36 months, local residual tumor was detected in 1 patient. No local recurrence occurred in any patient. CONCLUSIONS: Despite being associated with a relatively low complete resection rate, ER is an alternative therapeutic method for large (≥ 4.0 cm) upper gastrointestinal MP-SETs when performed by an experienced endoscopist. This method is especially valuable for patients who are unwilling to undergo surgery.

Endoscopic retrograde appendicitis techniques for the treatment of patients with acute appendicitis.

OBJECTIVE: The purpose of this study was to demonstrate the feasibility of endoscopic retrograde appendicitis therapy (ERAT) in treating patients with acute appendicitis. MATERIALS AND METHODS: Between January 2014 and December 2014, 22 patients with acute appendicitis underwent ERAT. Patient demographics, colonoscopy findings, endoscopic retrograde appendiceal radiography (ERAR) findings, and treatment outcomes of the ERAT and adverse events associated with ERAT were analyzed. RESULTS: In this study, 22 patients with acute appendicitis underwent ERAT. The median age of the patients was 39.5 years. Colonoscopy findings included mucosal hyperemia and swelling of the appendiceal orifice and/or its surrounding mucosa (86.4 %, 19/22) and pus at the appendiceal orifice (40.9 %, 9/22). ERAR findings included irregular contour (76.2 %, 16/21), appendiceal lumen dilation (28.6 %, 6/21), appendiceal lumen stenosis (42.9 %, 9/21), and filling defect of the appendiceal lumen (23.8 %, 5/21). Deep intubation was successfully performed in 21 of the 22 patients (95.5 %). Sixteen patients underwent endoscopic appendiceal stent placement after endoscopic appendiceal irrigation (EAI) due to lumen stenosis of the appendiceal, excessive pus, or appendiceal fecalith, and the remaining 6 patients only underwent EAI. Among the 22 patients who underwent ERAT, their abdominal pain was noticeably relieved following the procedure. The main adverse events associated with ERAT were spontaneous discharge of the stent, recurrent abdominal pain, and recurrent appendicitis. During the follow-up (median 33 months), 2 patients underwent laparoscopic appendectomy. CONCLUSIONS: ERAT provide a new alternative therapeutic method for patients with acute appendicitis, particularly for certain patients who are unwilling to undergo an appendectomy.

Safety of endoscopic resection for duodenal subepithelial lesions with wound closure using clips and an endoloop: an analysis of 68 cases.

BACKGROUND: Endoscopic removal of a duodenal lesion is still considered to be a challenging procedure that can be fraught with potentially serious complications, specifically perforation or delayed bleeding. This study was to assess the safety of endoscopic resection for duodenal subepithelial lesions (SELs) with wound closure using clips and an endoloop. METHODS: From October 2010 to July 2015, a total of 68 consecutive patients with duodenal SELs were treated with endoscopic resection with wound closure using clips and an endoloop. The main outcome measures considered were the incidence of complete resection, perioperative perforation, delayed perforation, delayed bleeding, residual lesions, and lesion recurrence. RESULTS: Complete resection was successfully achieved for all 68 patients. The median lesion size was 1.7 cm. The median procedure time was 62 min. The mean hospital stay was 5.5 days. During the procedure, five patients developed perioperative perforations (7.4 %) and no patients developed delayed bleeding, delayed perforation, or other serious complications. The five patients with perioperative perforations recovered after conservative treatment. The perioperative perforation rate was significantly higher for lesions originating in the muscularis propria layer (18.2 %) than in the submucosal layer (2.2 %; p < 0.05). No residual or recurrent lesions were detected during the follow-up period (median: 27 months). CONCLUSIONS: Endoscopic resection with wound closure using clips and an endoloop is an effective and reasonably safe therapeutic method for treating/removing duodenal SELs when managed by an experienced endoscopic team, and it can provide an alternative treatment option for patients with duodenal SELs.

Submucosal tunneling endoscopic resection using methylene-blue guidance for cardial subepithelial tumors originating from the muscularis propria layer.

Submucosal tunneling endoscopic resection (STER) of subepithelial tumors (SETs) originating from the muscularis propria (MP) layer in the cardia is rarely performed due to the difficulty of creating a submucosal tunnel for resection. The aim of this study was to evaluate the feasibility of STER using methylene-blue guidance for SETs originating from the MP layer in the cardia. From January 2012 to December 2014, 56 patients with SETs originating from the MP layer in the cardia were treated with STER using methylene-blue guidance. The complete resection rate and adverse event rate were the main outcome measurements. Successful complete resection by STER was achieved in all 56 cases (100%). The median size of the tumor was 1.8 cm. Nine patients (15.3%) had adverse events including subcutaneous emphysema, pneumoperitoneum, pneumothorax, and pleural effusion. These nine patients recovered successfully after conservative treatment without endoscopic or surgical intervention. No residual or recurrent tumors were detected in any patient during the follow-up period (median, 25 months). The adverse event rate was significantly higher for tumors originating in the deeper MP layers (46.7%) than in the superficial MP layers (4.9%) (P < 0.05), differed significantly according to tumor size (5.4% for tumors < 2.0 cm vs. 36.8% for tumors ≥ 2.0 cm; P < 0.05), and also differed significantly in relation to the tumor growth pattern (4.1% for the intraluminal growth vs. 100% for the extraluminal growth; P < 0.001). STER using methylene-blue guidance appears to be a feasible method for removing SETs originating from the MP layer in the cardia.

Safety of Endoscopic Resection for Upper Gastrointestinal Subepithelial Tumors Originating from the Muscularis Propria Layer: An Analysis of 733 Tumors.

OBJECTIVES: Although endoscopic resection is an accepted technique for upper gastrointestinal subepithelial tumors (SETs) originating from the muscularis propria (MP) layer, published data regarding its complications are highly variable and limited to small data series. This study aimed to analyze the safety of endoscopic resection in a large case series. METHODS: A total of 726 consecutive patients with 733 upper gastrointestinal SETs originating from the MP layer underwent endoscopic resection from June 2005 to December 2014. The complete resection rate, perioperative perforation rate, and perioperative bleeding rate were the main outcome measurements. RESULTS: The complete resection rate was 97.1%. Ninety-four patients had complications (12.9%), including 88 with perioperative perforations (12.1%), 13 with perioperative bleeding (1.8%), 5 with localized peritonitis (0.7%), and one with delayed bleeding (0.1%). Eleven patients required surgery; the others were treated endoscopically. Risk factors for incomplete resection were extensive connection of the tumor to the MP layer (P=0.007) and extraluminal growth (P=0.048). Risk factors for perioperative perforation were larger tumor size (≤2.0 cm vs. 2.1-3.0 cm vs. >3.0 cm, P=0.021), extraluminal growth (P=0.046), and extensive connection (P<0.001). A risk factor for perioperative bleeding was larger tumor size (P=0.045). No residual or recurrent lesions were detected during the follow-up period (median: 28 months). CONCLUSIONS: Endoscopic resection is an effective and reasonably safe therapeutic method for treating/removing upper gastrointestinal SETs originating from the MP layer when managed by an experienced endoscopic team.

Complete circular endoscopic resection using submucosal tunnel technique combined with esophageal stent placement for circumferential superficial esophageal lesions.

BACKGROUND AND AIMS: At present, removing a circumferential superficial esophageal lesion (SEL) via en bloc resection is still a great challenge. Based on the previous success of submucosal tunneling endoscopic resection, this study aimed to evaluate the safety and effectiveness of complete circular endoscopic resection (CER) using a submucosal tunnel technique combined with esophageal stent placement for patients with circumferential SELs. METHODS: From August 2012 to June 2014, 23 patients with circumferential SELs were treated by CER using a submucosal tunnel technique combined with esophageal stent placement. The following steps were performed: (1) circular mucosa incisions were made at the anal and oral side of the lesion after marking the margin, (2) two submucosal tunnels were created from the oral to anal side using a hybrid knife, which was followed by submucosal dissection, and (3) following the completion of CER, a retrievable esophageal stent was placed to prevent postoperative stricture. RESULTS: CER using the submucosal tunnel technique combined with esophageal stent placement was successfully performed for all 23 cases. The complete resection and success rate were 100%, while the mean longitudinal diameter of the lesions was 65 mm. Mediastinal emphysema, pneumothorax, and postoperative stenosis were detected in 8.7% (2/23), 4.3% (1/23), and 17.4% (4/23) of the cases, respectively. Pathological diagnoses of the lesions included carcinomas (13/23) and high-grade intraepithelial neoplasias (10/23). No residual or recurrent tumors were detected in any patient during the follow-up period. CONCLUSIONS: CER using the submucosal tunnel technique combined with esophageal stent placement seems to be a safe and effective procedure for treating patients with SELs that result in a higher en bloc resection rate with fewer or minor complications.

Endoscopic excavation for the treatment of small esophageal subepithelial tumors originating from the muscularis propria.

BACKGROUND/AIMS: This study was designed to evaluate the safety and efficacy of endoscopic excavation for esophageal subepithelial tumors originating from the muscularis propria. METHODOLOGY: Forty-five patients with esophageal subepithelial tumors originating from the muscularis propria were treated with endoscopic excavation between January 2010 and June 2012. The key steps were: (1) making several dots around the tumor; (2) incising the mucosa along with the marker dots, and then seperating the tumor from the muscularis propria by using a hook knife or an insulated-tip knife; (3) closing the artificial ulcer with clips after the tumor was removed. RESULTS: The mean tumor diameter was 1.1 ± 0.6 cm. Endoscopic excavation was successfully performed in 43 out of 45 cases (95.6%), the other 2 cases were ligated with nylon rope. During the procedure perforation occurred in 4 (8.9%) patients, who recovered after conservative treatment. No massive bleeding or delayed bleeding occurred. Histologic diagnosis was obtained from 43 (95.6%) patients. Pathological diagnoses of these tumors were leiomyomas (38/43) and gastrointestinal stromal tumors (5/43). CONCLUSIONS: Endoscopic excavation is a safe and effective method for the treatment of small esophageal subepithelial tumors originating from the muscularis propria.

Endoscopic full-thickness resection with defect closure using clips and an endoloop for gastric subepithelial tumors arising from the muscularis propria.

BACKGROUND AND AIMS: This retrospective study evaluated the safety and efficacy of endoscopic full-thickness resection (eFTR) with defect closure using clips and an endoloop for the treatment of gastric subepithelial tumors (SETs) arising from the muscularis propria (MP). METHODS: From January 2009 to December 2012, 51 patients with gastric SETs arising from the MP underwent eFTR with defect closure using clips and an endoloop. The key steps were (1) several milliliters of mixture solution was injected into the submucosa after dots were marked around the tumor; (2) a cross incision was made in the mucosa to reveal the tumor; (3) subsequently, circumferential excavation was performed as deep as the muscularis propria, and full-thickness resection of the tumor was performed with an insulated-tip knife, including its underlying MP and serosa; (4) the gastric wall defect was closed with clips and an endoloop was then placed to fix and tighten all of the clips together. RESULTS: Successful complete resection by eFTR was achieved in 50 cases (98.0%). One case failed and was converted into a laparoscopic resection due to the tumor falling into the peritoneal cavity during the procedure. The mean procedure time was 52 min. No patients had severe complications, such as massive bleeding, delayed bleeding, peritonitis, or gastrointestinal tract leakage. The mean tumor length was 2.4 cm. Pathological diagnoses of the tumors were leiomyomas (21/51) and gastrointestinal stromal tumors (30/51). The median follow-up period after the procedure was 22.4 months (range 1-48 months), and no residual tumor or tumor recurrence was detected during the follow-up period. CONCLUSIONS: eFTR with defect closure with clips and an endoloop appears to be a safe and effective technique for the treatment of patients with gastric SETs originating from the MP, especially for those with extraluminal growth or adhesions to the MP.

Submucosal tunneling endoscopic resection for small upper gastrointestinal subepithelial tumors originating from the muscularis propria layer.

BACKGROUND: This prospective study was designed to evaluate the safety and efficacy of submucosal tunneling endoscopic resection (STER) for small (≤3 cm) upper gastrointestinal (GI) subepithelial tumors (SETs) originating from the muscularis propria (MP) layer. METHODS: Between August 2011 and February 2013, a total of 85 patients with upper GI SETs originating from the MP layer were treated with STER. The key steps were as follows: (1) locating the tumor by injection of methylene blue or indigo carmine and then creating a submucosal tunnel from 5 cm above the tumor between the submucosal and muscular layers; (2) resecting the tumor by endoscopic resection techniques; (3) closing the mucosal incision site with several clips after the tumor is removed. RESULTS: Of the 85 SETs, 60 were located in the esophagus, 16 in the cardia, and 9 in the stomach. STER was successfully performed in all cases (success rate: 100 %). The mean tumor size was 19.2 mm. The mean procedure time was 57.2 min. The average hospital stay after the procedure was 5.9 days. Pathological diagnosis of the tumors were leiomyoma (65/85), gastrointestinal stromal tumor (GIST) (19/85), and calcifying fibrous tumor (1/85). During the procedure, eight patients developed pneumothorax, subcutaneous emphysema, and/or pneumoperitoneum. These patients recovered after conservative treatment. The rate of all complications was significantly higher for lesions originating in the deeper MP layer (70 %) than in the superficial MP layer (1.3 %; p < 0.001). The total complication rate for different histological diagnoses was also significantly different (26.3 % for GISTs, 4.6 % for leiomyomas, 0 % for calcifying fibrous tumors, p < 0.05). No residual or recurrent tumors were detected during the follow-up period (median: 8 months). CONCLUSIONS: Submucosal tunneling endoscopic resection appears to be a feasible, safe, and effective procedure for treatment of small (≤3 cm) upper GI SETs originating from the MP layer.

[Recent progress in the development of atherosclerosis: role of heat shock protein].

Recent studies have shown a close relationship between heat shock proteins (HSPs) and atherosclerosis. HSP60 may promote the development of atherosclerosis by inducing autoimmune response, enhancing inflammatory response, promoting proliferation and migration of vascular smooth muscle cells. While HSP27 may protect the blood vessels from oxidative stress, reduce inflammatory response, inhibit proliferation, migration and apoptosis of vascular smooth muscle cells, and stabilize the atherosclerotic plaque. These new understanding of the role of HSPs provides useful clues for the diagnosis and treatment of atherosclerosis.

Deep learning assists detection of esophageal cancer and precursor lesions in a prospective, randomized controlled study.

Endoscopy is the primary modality for detecting asymptomatic esophageal squamous cell carcinoma (ESCC) and precancerous lesions. Improving detection rate remains challenging. We developed a system based on deep convolutional neural networks (CNNs) for detecting esophageal cancer and precancerous lesions [high-risk esophageal lesions (HrELs)] and validated its efficacy in improving HrEL detection rate in clinical practice (trial registration ChiCTR2100044126 at www.chictr.org.cn). Between April 2021 and March 2022, 3117 patients ≥50 years old were consecutively recruited from Taizhou Hospital, Zhejiang Province, and randomly assigned 1:1 to an experimental group (CNN-assisted endoscopy) or a control group (unassisted endoscopy) based on block randomization. The primary endpoint was the HrEL detection rate. In the intention-to-treat population, the HrEL detection rate [28 of 1556 (1.8%)] was significantly higher in the experimental group than in the control group [14 of 1561 (0.9%), P = 0.029], and the experimental group detection rate was twice that of the control group. Similar findings were observed between the experimental and control groups [28 of 1524 (1.9%) versus 13 of 1534 (0.9%), respectively; P = 0.021]. The system's sensitivity, specificity, and accuracy for detecting HrELs were 89.7, 98.5, and 98.2%, respectively. No adverse events occurred. The proposed system thus improved HrEL detection rate during endoscopy and was safe. Deep learning assistance may enhance early diagnosis and treatment of esophageal cancer and may become a useful tool for esophageal cancer screening.

Safety and efficacy of endoscopic excavation for gastric subepithelial tumors originating from the muscularis propria layer: results from a large study in China.

BACKGROUND AND AIM: In this retrospective study, we investigated the safety and efficacy of endoscopic excavation of gastric subepithelial tumors (SETs) originating from the muscularis propria (MP) layer. MATERIALS AND METHODS: Between November 2007 and June 2012, 212 patients with gastric SETs originating from the MP layer were treated via endoscopic excavation. The key procedures were: (1) injecting a mixture solution (100 mL saline+2 mL indigo carmine+1 mL epinephrine) into the submucosa around the tumor; (2) making a cross-incision of the mucosa and then excavating the tumor by the technique of endoscopic excavation. After the tumor was completely excavated from the MP layer, it was removed using a snare; (3) closing the artificial ulcer with clips. RESULTS: The mean diameter of the 212 tumors was 16.5 mm. Complete resection by endoscopic excavation was achieved in 204 cases (96.2%). The rate of complete resection was significantly higher for tumors <2 cm (98.0%) than for tumors >2 cm (91.9%) (P=0.035). Perforation occurred in 32 cases (15.1%), and massive bleeding occurred in 9 cases (4.2%) during the procedure. The rate of perforation was significantly higher for the fundus and the body than for antrum (21.5%, 11.5%, 0%, respectively; P=0.036), and also differed significantly in relation to histologic diagnosis (23.7% for gastrointestinal stromal tumors vs. 7.8% for leiomyoma; P=0.001). Histologic diagnosis showed that the density of gastrointestinal stromal tumors located in the fundus and the body of the stomach was significantly higher than in the antrum (44.1%, 51.9%, 13.3%, respectively; P=0.036). CONCLUSIONS: Endoscopic excavation is a safe and efficient method for resecting small (>3.5 cm) gastric SETs originating from the MP layer.

Endoscopic muscularis excavation for subepithelial tumors of the esophagogastric junction originating from the muscularis propria layer.

BACKGROUND: Because of complicating anatomic factors, endoscopic submucosal dissection is seldom performed in subepithelial tumors of the esophagogastric junction originating from the muscularis propria layer. AIM: This study was designed to evaluate the feasibility of endoscopic muscularis excavation for treating subepithelial tumors of the esophagogastric junction originating from the muscularis propria layer. METHODS: Between December 2008 and December 2011, 68 patients with subepithelial tumors of the esophagogastric junction originating from the muscularis propria layer were treated with endoscopic muscularis excavation. Key steps of the procedure included the following: (1) injecting a mixture solution into the submucosal layer after making several dots around the tumor; (2) making a cross incision of the overlying mucosa, and excavating the tumor from the muscularis propria layer; (3) closing the artificial ulcer with clips after tumor removal. RESULTS: The mean tumor size was 16.2 mm (range 7-35 mm). Endoscopic muscularis excavation was successfully performed in 65 out of 68 cases (success rate 95.6 %). Pathological diagnosis of these tumors included leiomyoma (39 out of 68) and gastrointestinal stromal tumor (29 out of 68). Perforation occurred in seven patients (10.3 %). No massive bleeding or delayed bleeding occurred. The median follow-up period after the procedure was 23 months (range 6-42 months). No residual or recurrent tumor was detected and no stricture occurred in patients during the follow-up period. CONCLUSIONS: Endoscopic muscularis excavation is a safe, effective and feasible procedure for providing accurate histopathologic evaluation and curative treatment for subepithelial tumors of the esophagogastric junction originating from the muscularis propria layer.