Artificial intelligence in detection of small bowel lesions and their bleeding risk: A new step forward.

The present letter to the editor is related to the study with the title "Automatic detection of small bowel (SB) lesions with different bleeding risk based on deep learning models". Capsule endoscopy (CE) is the main tool to assess SB diseases but it is a time-consuming procedure with a significant error rate. The development of artificial intelligence (AI) in CE could simplify physicians' tasks. The novel deep learning model by Zhang et al seems to be able to identify various SB lesions and their bleeding risk, and it could pave the way to next perspective studies to better enhance the diagnostic support of AI in the detection of different types of SB lesions in clinical practice.

Double balloon enteroscopy versus single balloon enteroscopy: A comparative study.

Device assisted enteroscopy (DAE) like the double balloon enteroscopy (DBE) and single balloon enteroscopy (SBE) are postulated to ease small bowel examination and performance of therapy. However, studies comparing the effectiveness of these 2 modalities have yielded varying results. The aim of this study is to compare the efficacy and safety of SBE and DBE. We retrospectively reviewed records of patients who underwent DBE (n = 82) or SBE (n = 45) for small bowel exam in our unit from January 2014 to January 2022. Our primary outcomes were to compare the technical success and diagnostic success rates between DBE and SBE. Our secondary outcomes were to compare the therapeutic success, and complication rates. The main indications were suspected GI bleeding (DBE 41.5% vs SBE 48.9%), iron deficiency anemia (DBE 9.8% vs SBE 4.4%) and small bowel lesions (DBE 28.0% vs SBE 44.4%) detected either from prior capsule endoscopy or radiological imaging. Majority of the enteroscopy exam was by antegrade approach (DBE 67.1% vs SBE 77.8%). We found no significant difference in the technical success (DBE 95.1% vs SBE 97.8%, P = .46), diagnostic success (DBE 69.5% vs SBE 77.8%, P = .36) and the therapeutic success rate (DBE 63.2% vs SBE 54.3%, P = .09) between the groups. Complications occurred in 1 case from each group (mucosal tear). None of the complications were major. In patients who underwent enteroscopy, the diagnostic and therapeutic performance of SBE is similar to DBE. Both procedures were safe with low complication rates.

Beta-blockers or Placebo for Primary Prophylaxis (BOPPP) of oesophageal varices: study protocol for a randomised controlled trial.

BACKGROUND: Liver disease is within the top five causes of premature death in adults. Deaths caused by complications of cirrhosis continue to rise, whilst deaths related to other non-liver disease areas are declining. Portal hypertension is the primary sequelae of cirrhosis and is associated with the development of variceal haemorrhage, ascites, hepatic encephalopathy and infection, collectively termed hepatic decompensation, which leads to hospitalisation and mortality. It remains uncertain whether administering a non-selective beta-blocker (NSBB), specifically carvedilol, at an earlier stage, i.e. when oesophageal varices are small, can prevent VH and reduce all-cause decompensation (ACD). METHODS/DESIGN: The BOPPP trial is a pragmatic, multicentre, placebo-controlled, triple-blinded, randomised controlled trial (RCT) in England, Scotland, Wales and Northern Ireland. Patients aged 18 years or older with cirrhosis and small oesophageal varices that have never bled will be recruited, subject to exclusion criteria. The trial aims to enrol 740 patients across 55 hospitals in the UK. Patients are allocated randomly on a 1:1 ratio to receive either carvedilol 6.25 mg (a NSBB) or a matched placebo, once or twice daily, for 36 months, to attain adequate power to determine the effectiveness of carvedilol in preventing or reducing ACD. The primary outcome is the time to first decompensating event. It is a composite primary outcome made up of variceal haemorrhage (VH, new or worsening ascites, new or worsening hepatic encephalopathy (HE), spontaneous bacterial peritonitis (SBP), hepatorenal syndrome, an increase in Child-Pugh grade by 1 grade or MELD score by 5 points, and liver-related mortality. Secondary outcomes include progression to medium or large oesophageal varices, development of gastric, duodenal, or ectopic varices, participant quality of life, healthcare costs and transplant-free survival. DISCUSSION: The BOPPP trial aims to investigate the clinical and cost-effectiveness of carvedilol in patients with cirrhosis and small oesophageal varices to determine whether this non-selective beta-blocker can prevent or reduce hepatic decompensation. There is clinical equipoise on whether intervening in cirrhosis, at an earlier stage of portal hypertension, with NSBB therapy is beneficial. Should the trial yield a positive result, we anticipate that the administration and use of carvedilol will become widespread with pathways developed to standardise the administration of the medication in primary care. ETHICS AND DISSEMINATION: The trial has been approved by the National Health Service (NHS) Research Ethics Committee (REC) (reference number: 19/YH/0015). The results of the trial will be submitted for publication in a peer-reviewed scientific journal. Participants will be informed of the results via the BOPPP website ( www.boppp-trial.org ) and partners in the British Liver Trust (BLT) organisation. TRIAL REGISTRATION: EUDRACT reference number: 2018-002509-78. ISRCTN reference number: ISRCTN10324656. Registered on April 24 2019.

Red Blood Cell Distribution Width as a Risk Factor for 30/90-Day Mortality in Patients with Gastrointestinal Bleeding: Analysis of the MIMIC-IV Database.

PURPOSE: The purpose of this research was to assess the relationship between red blood cell distribution width (RDW) and mortality in patients with gastrointestinal (GIB) bleeding in the intensive care unit (ICU). METHODS: The information of the participants was obtained from the Medical Information Mart for Intensive Care IV database. The main outcome of this research was 30/90-day mortality, with ICU mortality and in-hospital mortality as secondary outcomes. RESULTS: This research included 2924 patients with gastrointestinal bleeding in total. Patients with higher RDW had considerably higher 30/90-day and in-hospital mortality rates, as well as longer hospital stays and ICU stays. According to the Kaplan-Meier analysis, the 30/90-day mortality rate was remarkably higher among participants in the higher RDW group (P < 0.0001). In the adjusted multivariate Cox regression analysis, for 30-day mortality, the HR (95% CI) was 1.75 (1.37, 2.24) in comparison to Q1 in the reference group (P < 0.001). Analyses of 90-day mortality and in-hospital mortality both showed the same results. In the subgroup analysis, gender, myocardial infarction, chronic pulmonary disease, cerebrovascular disease and renal disease had no significant effect on the correlation between RDW values and mortality (all P > 0.05). The area under the ROC curve for RDW was 0.599 (95% CI 0.581-0.617) and 0.606 (95% CI 0.588-0.624) in 30/90-day ICU mortality. CONCLUSION: The current research showed that RDW could be utilized as an independent indicator of short-term mortality in critically ill GIB patients at 30 and 90 days of hospital admission.

Gastroenterology/Hepatology: What You May Have Missed in 2023.

This article summarizes clinically important gastroenterology developments from 2023 for internal medicine specialists. In colorectal cancer screening, a new RNA fecal screening test is on the horizon, as well as a new analysis on the benefits of using artificial intelligence in screening colonoscopy to detect more polyps. There is new evidence for management of gastrointestinal bleeding, a new drug for treatment of recurrent small-intestinal angiodysplasia, and a new endoscopic treatment method in patients with gastrointestinal tumor bleeding. The authors feature a randomized trial about amitriptyline as treatment for patients with irritable bowel syndrome by primary care providers and bring you news about new biologic agents for inflammatory bowel disease and eosinophilic esophagitis. Finally, they review 2 important articles on new terminology and management of metabolic dysfunction-associated fatty liver disease.

Heyde's syndrome: a challenging case of severe aortic stenosis and gastrointestinal bleeding.

We present the case of an elderly man with a history of diastolic congestive heart failure, severe aortic stenosis and atrial fibrillation, who presented with fatigue, weakness, coffee ground emesis and black tarry stool. Haemoglobin was 68 g/L. Lactate dehydrogenase was elevated at 1038. Evaluation by cardiology and gastroenterology specialists revealed reflux oesophagitis and a mild hiatal hernia on oesophagogastroduodenoscopy, normal colonoscopy and small bowel series without obstruction. Capsule endoscopy identified angiodysplasia in the small intestine.The patient was diagnosed with Heyde's syndrome based on the triad of severe aortic stenosis, gastrointestinal bleeding from angiodysplasia and acquired von Willebrand syndrome. The patient underwent transcatheter aortic valve replacement, resulting in the resolution of symptoms.Heyde's syndrome represents a challenging clinical entity requiring a multidisciplinary approach for accurate diagnosis and management. Early recognition, prompt intervention and interdisciplinary collaboration are crucial in optimising patient outcomes.

Congenital Gastric Teratoma Presenting with Gastrointestinal Bleeding: Case Report and Review of Literature.

BACKGROUND: Gastric teratoma is an extremely rare tumor, representing <1% of all pediatric teratomas, and commonly manifests as a palpable abdominal mass. Upper gastrointestinal tract bleeding in newborns and infants is rare and is mostly caused by a benign lesion. CASE REPORT: We present a 3-month-old boy who presented with recurrent attacks of hematemesis, vomiting, and melena which on work up revealed a gastric teratoma. DISCUSSION/CONCLUSION: Owing to the unique characteristics and the extreme rarity of this entity, accurate preoperative diagnosis has remained elusive.

Digestive bleeding due to jejunal diverticula: diagnosis and management.

A jejunal diverticular haemorrhage is the second most common complication of jejunum diverticula. It can manifest clinically as acute upper gastrointestinal bleeding and is common to imitate acute rectal bleeding. Bleeding is usually associated with or without haemodynamic stability. Its diagnosis is challenging, requiring imaging examinations. Treatment is conservative management or surgery.

Proton Pump Inhibitor Associated Multiple Gastric Hyperplastic Polyps With Uncontrollable Bleeding: A Case Report.

BACKGROUND/AIM: The long-term use of proton pump inhibitors (PPIs) has been reported to be strongly associated with the development of fundic gland polyps (FGPs). Conversely, a few cases of gastric hyperplastic polyps (GHPs) associated with PPI use have been reported. We experienced a case of PPI-associated multiple GHPs with uncontrollable bleeding. CASE REPORT: A 64 year old man with a history of rheumatoid arthritis presented to the hospital with complaints of vertigo and black stools. Blood tests revealed anemia and hypoproteinemia. Esophagogastroduodenoscopy (EGD) showed blood and black residue accumulated in the stomach. The source of the bleeding was multiple hyperplastic polyps. Bleeding could be stopped even with fasting, and total blood transfusions amounted to 28 units of RBCs were required in 18 days. After the cessation of PPI, EGD showed that the polyps had almost disappeared. Pathological diagnosis of resected polyp was hyperplastic polyp, which was characterized by capillary hyperplasia and edema. Gastrin receptors were over-expressed in the foveolar epithelium and not in the capillaries. Methotrexate (MTX)-induced portal hypertensive gastroenteropathy was revealed during follow-up. We consider that the effect of portal hypertension may have caused the capillary hyperplasia. CONCLUSION: Although PPI-related polyps are usually fundic gland polyps and do not cause life-threatening adverse events, we experienced PPI-related GHPs in which hemostasis was difficult to control.

Assessment of nomogram model for the prediction of esophageal variceal hemorrhage in hepatitis B-induced hepatic cirrhosis.

BACKGROUND: Esophageal variceal (EV) hemorrhage is a life-threatening consequence of portal hypertension in hepatitis B virus (HBV) -induced cirrhotic patients. Screening upper endoscopy and endoscopic variceal ligation to find EVs for treatment have complications, contraindications, and high costs. We sought to identify the nomogram models (NMs) as alternative predictions for the risk of EV hemorrhage. METHODS: In this case-control study, we retrospectively analyzed 241 HBV-induced liver cirrhotic patients treated for EVs at the Second People's Hospital of Fuyang City, China from January 2021 to April 2023. We applied univariate analysis and multivariate logistic regression to assess the accuracy of various NMs in EV hemorrhage. The area under the curve (AUC) and calibration curves of the receiver's operating characteristics were used to evaluate the predictive accuracy of the nomogram. Decision curve analysis (DCA) was used to determine the clinically relevant of nomograms. RESULTS: In the prediction group, multivariate logistic regression analysis identified platelet distribution and spleen length as independent risk factors for EVs. We applied NMs as the independent risk factors to predict EVs risk. The NMs fit well with the calibration curve and have good discrimination ability. The AUC and DCA demonstrated that NMs with a good net benefit. The above results were validated in the validation cohort. CONCLUSION: Our non-invasive NMs based on the platelet distribution width and spleen length may be used to predict EV hemorrhage in HBV-induced cirrhotic patients. NMs can help clinicians to increase diagnostic performance leading to improved treatment measures.

Outcomes of endoscopic sclerotherapy for jejunal varices at the site of choledochojejunostomy (with video): Three case reports.

BACKGROUND: Hemorrhage associated with varices at the site of choledochojejunostomy is an unusual, difficult to treat, and often fatal manifestation of portal hypertension. So far, no treatment guidelines have been established. CASE SUMMARY: We reported three patients with jejunal varices at the site of choledochojejunostomy managed by endoscopic sclerotherapy with lauromacrogol/α-butyl cyanoacrylate injection at our institution between June 2021 and August 2023. We reviewed all patient records, clinical presentation, endoscopic findings and treatment, outcomes and follow-up. Three patients who underwent pancreaticoduodenectomy with a Whipple anastomosis were examined using conventional upper gastrointestinal endoscopy for suspected hemorrhage from the afferent jejunal loop. Varices with stigmata of recent hemorrhage or active hemorrhage were observed around the choledochojejunostomy site in all three patients. Endoscopic injection of lauromacrogol/α-butyl cyanoacrylate was carried out at jejunal varices for all three patients. The bleeding ceased and patency was observed for 26 and 2 months in two patients. In one patient with multiorgan failure and internal environment disturbance, rebleeding occurred 1 month after endoscopic sclerotherapy, and despite a second endoscopic sclerotherapy, repeated episodes of bleeding and multiorgan failure resulted in eventual death. CONCLUSION: We conclude that endoscopic sclerotherapy with lauromacrogol/α-butyl cyanoacrylate injection can be an easy, effective, safe and low-cost treatment option for jejunal varicose bleeding at the site of choledochojejunostomy.

Advancements in hemostatic strategies for managing upper gastrointestinal bleeding: A comprehensive review.

Upper gastrointestinal (GI) hemorrhage presents a substantial clinical challenge. Initial management typically involves resuscitation and endoscopy within 24 h, although the benefit of very early endoscopy (< 12 h) for high-risk patients is debated. Treatment goals include stopping acute bleeding, preventing rebleeding, and using a multimodal approach encompassing endoscopic, pharmacological, angiographic, and surgical methods. Pharmacological agents such as vasopressin, prostaglandins, and proton pump inhibitors are effective, but the increase in antithrombotic use has increased GI bleeding morbidity. Endoscopic hemostasis, particularly for nonvariceal bleeding, employs techniques such as electrocoagulation and heater probes, with concerns over tissue injury from monopolar electrocoagulation. Novel methods such as Hemospray and Endoclot show promise in creating mechanical tamponades but have limitations. Currently, the first-line therapy includes thermal probes and hemoclips, with over-the-scope clips emerging for larger ulcer bleeding. The gold probe, combining bipolar electrocoagulation and injection, offers targeted coagulation but has faced device-related issues. Future advancements involve combining techniques and improving endoscopic imaging, with studies exploring combined approaches showing promise. Ongoing research is crucial for developing standardized and effective hemorrhage management strategies.

Capsule endoscopy and panendoscopy: A journey to the future of gastrointestinal endoscopy.

In 2000, the small bowel capsule revolutionized the management of patients with small bowel disorders. Currently, the technological development achieved by the new models of double-headed endoscopic capsules, as miniaturized devices to evaluate the small bowel and colon [pan-intestinal capsule endoscopy (PCE)], makes this non-invasive procedure a disruptive concept for the management of patients with digestive disorders. This technology is expected to identify which patients will require conventional invasive endoscopic procedures (colonoscopy or balloon-assisted enteroscopy), based on the lesions detected by the capsule, i.e., those with an indication for biopsies or endoscopic treatment. The use of PCE in patients with inflammatory bowel diseases, namely Crohn's disease, as well as in patients with iron deficiency anaemia and/or overt gastrointestinal (GI) bleeding, after a non-diagnostic upper endoscopy (esophagogastroduodenoscopy), enables an effective, safe and comfortable way to identify patients with relevant lesions, who should undergo subsequent invasive endoscopic procedures. The recent development of magnetically controlled capsule endoscopy to evaluate the upper GI tract, is a further step towards the possibility of an entirely non-invasive assessment of all the segments of the digestive tract, from mouth-to-anus, meeting the expectations of the early developers of capsule endoscopy.

AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study.

BACKGROUND: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. METHODS: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without melena or haematochezia, and negative bidirectional endoscopy) were prospectively enrolled at 14 European centres. Patients underwent small bowel capsule endoscopy with the Navicam SB system (Ankon, China), which is provided with a deep neural network-based AI system (ProScan) for automatic detection of lesions. Initial reading was performed in standard reading mode. Second blinded reading was performed with AI assistance (the AI operated a first-automated reading, and only AI-selected images were assessed by human readers). The primary endpoint was to assess the non-inferiority of AI-assisted reading versus standard reading in the detection (diagnostic yield) of potentially small bowel bleeding P1 and P2 lesions in a per-patient analysis. This study is registered with ClinicalTrials.gov, NCT04821349. FINDINGS: From Feb 17, 2021 to Dec 29, 2021, 137 patients were prospectively enrolled. 133 patients were included in the final analysis (73 [55%] female, mean age 66·5 years [SD 14·4]; 112 [84%] completed capsule endoscopy). At per-patient analysis, the diagnostic yield of P1 and P2 lesions in AI-assisted reading (98 [73·7%] of 133 lesions) was non-inferior (p<0·0001) and superior (p=0·0213) to standard reading (82 [62·4%] of 133; 95% CI 3·6-19·0). Mean small bowel reading time was 33·7 min (SD 22·9) in standard reading and 3·8 min (3·3) in AI-assisted reading (p<0·0001). INTERPRETATION: AI-assisted reading might provide more accurate and faster detection of clinically relevant small bowel bleeding lesions than standard reading. FUNDING: ANKON Technologies, China and AnX Robotica, USA provided the NaviCam SB system.

Comparison of scoring systems for predicting clinical outcomes of acute lower gastrointestinal bleeding: A prospective cohort study.

BACKGROUND: This study aimed to determine the performance of the Oakland, Glasgow-Blatchford, and AIMS65 scores in predicting the clinical outcomes of acute lower gastrointestinal bleeding (LGIB). METHODS: This prospective cohort study was conducted from July 2020 to July 2021. Patients admitted with acute lower gastrointestinal bleeding were enrolled. The Oakland, Glasgow-Blatchford, and AIMS65 scores were calculated. The primary outcome was validating the performance of the scores in predicting severe LGIB; secondary outcomes were comparing the performance of the scores in predicting the need for blood transfusion, hemostatic interventions, in-hospital rebleeding, and mortality. Receiver operating characteristic curves were calculated for all outcomes. The associations between all three scores and the primary outcomes were calculated using multivariate logistic regression analysis. RESULTS: Patients with acute LGIB (n = 150) were enrolled (88 [58.7%] men and mean age: 63.6 ± 17.3 years). The rates of severe LGIB, need for blood transfusion, hemostatic intervention, in-hospital rebleeding, and in-hospital mortality were 54.7%, 79.3%, 10.7%, and 3.3%, respectively. The Oakland and Glasgow-Blatchford scores had comparable performance in predicting severe LGIB, need for blood transfusion, and mortality, outperforming the AIMS65 score. All scores were suboptimal for predicting hemostatic interventions and rebleeding. CONCLUSIONS: Our results demonstrate the predictive performances of the Oakland score and the GBS are excellent and comparable for severe LGIB, the need for blood transfusion, and in-hospital mortality in patients with acute LGIB. Thus, GBS could be considered as an alternative predictive score for stratification of the patients with acute LGIB.

Gastrointestinal bleeding due to obstruction of the superior mesenteric vein.

ABSTRACT: Gastrointestinal bleeding is a common clinical symptom. Finding the underlying cause is the first step for treatment. In a few patients, this can be difficult. The present work reports on the unusual case of a 53-year-old man who presented gastrointestinal bleeding. No bleeding site was found by gastrocolonoscopy or interventional examination, but after multidisciplinary consultation, we discovered that the cause of gastrointestinal bleeding was the obstruction of the upper mesenteric vein.

A Novel Nomogram for Predicting Early Rebleeding After Endoscopic Treatment of Esophagogastric Variceal Hemorrhage.

BACKGROUND: Early rebleeding is a significant complication of endoscopic treatment for esophagogastric variceal hemorrhage (EGVH). However, a reliable predictive model is currently lacking. AIMS: To identify risk factors for rebleeding within 6 weeks and establish a nomogram for predicting early rebleeding after endoscopic treatment of EVGH. METHODS: Demographic information, comorbidities, preoperative evaluation, endoscopic features, and laboratory tests were collected from 119 patients who were first endoscopic treatment for EGVH. Independent risk factors for early rebleeding were determined through least absolute shrinkage and selection operator logistic regression. The discrimination, calibration, and clinical utility of the nomogram were assessed and compared with the model for end-stage liver disease (MELD), Child-Pugh, and albumin-bilirubin (ALBI) scores using receiver-operating characteristic (ROC) curves, calibration plots, and decision curve analyses (DCA). RESULTS: Early rebleeding occurred in 39 patients (32.8%) within 6 weeks after endoscopic treatment. Independent early rebleeding factors included gastric variceal hemorrhage (GVH), concomitant hepatocellular carcinoma (HCC), international normalized ratio (INR), and creatinine. The nomogram demonstrated exceptional calibration and discrimination capability. The area under the curve for the nomogram was 0.758 (95% CI 0.668-0.848), and it was validated at 0.71 through cross-validation and bootstrapping validation. The DCA and ROC curves demonstrated that the nomogram outperformed the MELD, Child-Pugh, and ALBI scores. CONCLUSIONS: Compared with existing prediction scores, the nomogram demonstrated superior discrimination, calibration, and clinical applicability for predicting rebleeding in patients with EGVH after endoscopic treatment. Therefore, it may assist clinicians in the early implementation of aggressive treatment and follow-up.