Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis
Bang CS, Lee JJ, Baik GH
Journal of medical Internet research. 2021;23(12):e33267
BACKGROUND Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models. OBJECTIVE To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images. METHODS We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed. RESULTS Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected. CONCLUSIONS CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.
Incidence of gastrointestinal bleeding after transesophageal echocardiography in patients with gastroesophageal varices: A systematic review and meta-analysis
Hui RW, Leung CM
Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography. 2021
BACKGROUND Transesophageal echocardiography (TEE) is useful for cardiac assessment and intraoperative monitoring. However, the safety of TEE in cirrhotic patients with gastroesophageal varices has remained uncertain. This meta-analysis aims to determine the incidence of gastrointestinal bleeding after TEE in patients with varices. The secondary objectives are to compare the bleeding risks between patients with and without varices; and to determine the incidences of TEE-related esophageal perforation and mortality. METHODS Systematic literature search was conducted on MEDLINE, EMBASE and Cochrane Database using the terms "Transesophageal echocardiography", "Varices", "Bleeding", and related terms. Articles describing the incidence of post-TEE bleeding in patients with varices were included. Non-English articles were excluded. Risk of bias and level of evidence were assessed through validated scales. Pooled weighted incidence of gastrointestinal bleeding and risk difference in bleeding were calculated with a random effects model. RESULTS 569 articles were identified initially, and 10 articles (comprising of 908 patients) were included. The incidence of post-TEE bleeding in patients with varices was 0.84% (95% CI 0.34%-1.56%). When stratified by TEE indication, the pooled incidence of bleeding was 0.68% (95% CI 0.11%-1.63%) in intraoperative TEE; and 1.03% (95% CI 0.23%-2.29%) in diagnostic TEE. No cases of esophageal perforation or mortality were reported. Six studies included a comparator group of patients without varices, and the bleeding risk was comparable between patients with and without varices (risk difference 0.26%; 95% CI -0.80%-1.32%; I2=0%, p=0.88). Eight studies had moderate or high risk of bias, and overall level of evidence was low. CONCLUSION TEE appears to be associated with low gastrointestinal bleeding incidence in patients with gastroesophageal varices. Nonetheless, results should be treated with caution due to bias and low level of evidence. Large-scale high-quality studies will be required to confirm the safety of TEE in patients with gastroesophageal varices.
The role of refined nursing combined with targeted nursing in patients with digestive tract hemorrhages complicated by liver cirrhosis
Wang Y, Wang Y, Han J
American journal of translational research. 2021;13(5):5336-5342
OBJECTIVE To explore the effect of refined nursing combined with targeted nursing on patients with gastrointestinal bleeding complicated by liver cirrhosis. METHODS 128 patients with gastrointestinal bleeding and liver cirrhosis admitted to our hospital from April 2018 to April 2019 were recruited as the study cohort and were randomly divided into a control group and an experimental group with 64 patients in each group. The patients in the control group underwent conventional nursing, and the experimental group underwent refined nursing combined with targeted nursing. The two groups' clinical efficacy, complication rates, psychological states, prognoses, quality of life, and nursing satisfaction were statistically analyzed. RESULTS The clinical curative effect, prognosis complication rate, psychological state scores, quality of life scores, and nursing satisfaction in the experimental group were significantly better than they were in the control group (P<0.05). CONCLUSION Refined nursing combined with targeted nursing has a more significant clinical effect than the conventional nursing mode due to its strengths in improving patients' prognoses, psychological states, and quality of life, and reducing the incidence of complications, improving the patients' nursing satisfaction, and establishing good doctor-patient relationships.
Perforated and bleeding peptic ulcer: WSES guidelines
Tarasconi A, Coccolini F, Biffl WL, Tomasoni M, Ansaloni L, Picetti E, Molfino S, Shelat V, Cimbanassi S, Weber DG, et al
World journal of emergency surgery : WJES. 2020;15:3
Background: Peptic ulcer disease is common with a lifetime prevalence in the general population of 5-10% and an incidence of 0.1-0.3% per year. Despite a sharp reduction in incidence and rates of hospital admission and mortality over the past 30 years, complications are still encountered in 10-20% of these patients. Peptic ulcer disease remains a significant healthcare problem, which can consume considerable financial resources. Management may involve various subspecialties including surgeons, gastroenterologists, and radiologists. Successful management of patients with complicated peptic ulcer (CPU) involves prompt recognition, resuscitation when required, appropriate antibiotic therapy, and timely surgical/radiological treatment. Methods: The present guidelines have been developed according to the GRADE methodology. To create these guidelines, a panel of experts was designed and charged by the board of the WSES to perform a systematic review of the available literature and to provide evidence-based statements with immediate practical application. All the statements were presented and discussed during the 5th WSES Congress, and for each statement, a consensus among the WSES panel of experts was reached. Conclusions: The population considered in these guidelines is adult patients with suspected complicated peptic ulcer disease. These guidelines present evidence-based international consensus statements on the management of complicated peptic ulcer from a collaboration of a panel of experts and are intended to improve the knowledge and the awareness of physicians around the world on this specific topic. We divided our work into the two main topics, bleeding and perforated peptic ulcer, and structured it into six main topics that cover the entire management process of patients with complicated peptic ulcer, from diagnosis at ED arrival to post-discharge antimicrobial therapy, to provide an up-to-date, easy-to-use tool that can help physicians and surgeons during the decision-making process.
Comparison in the diagnostic yield between "Pillcam SB3" capsule endoscopy and "OMOM Smart Capsule 2" in small bowel bleeding. A randomized head-to-head study
Blanco-Velasco G, Zamarripa-Mottú RA, Solórzano-Pineda OM, Mascarenhas-Saraiva M, Blancas-Valencia JM, Hernández-Mondragón OV
Digestive diseases (Basel, Switzerland). 2020
Introduction Capsule endoscopy is the first-line tool for diagnosis of small bowel bleeding. There are some studies that have compared different types of capsule endoscopy. OMOM capsule endoscopy is one of the newest in the market, and has not been compared to other types of capsule endoscopy. The objective of this study was to compare the diagnostic yield of the Pillcam SB3 and OMOM capsule endoscopy in small bowel bleeding. Material and methods This is a prospective, comparative, randomized and blinded study. Patients with suspected small bowel bleeding were included. All the patients were given both types of capsules endoscopy in random order. Diagnostic yield and functionality between the two types of capsule endoscopy were analyzed. Results We included 44 patients, 54.5% female with a median of 63.5 years old. Battery time was significantly longer with SB3 (816.5 vs. 700.5 minutes, p<0.001) and the download time was shorter with the OMOM (33 vs. 132 minutes, p<0.001). Both capsule endoscopies presented one failure. The cause of the bleeding was identified in 39 SB3 (88.6%) and in 34 OMOM CE (77.3%) (p=0.256). P2 lesions were observed in 32 SB3 (72.7%) and in 29 OMOM (65.9%) (p=0.784). The agreement between both capsule endoscopies for P2 lesions was moderate (κ=0.628). Conclusions Pillcam SB3 and OMOM devices are safe procedures and have a similar diagnostic yield. Significant differences were observed in the battery life and download time with both capsule endoscopies.
Genetic polymorphisms associated with upper gastrointestinal bleeding: a systematic review
Forgerini M, Lucchetta RC, Urbano G, de Nadai TR, de Carvalho Mastroianni P
The pharmacogenomics journal. 2020
Non-variceal upper gastrointestinal bleeding (non-variceal UGIB) is a frequent and severe adverse drug reaction. Idiosyncratic responses due to genetic susceptibility to non-variceal UGIB has been suggested. A systematic review was conducted to assess the association between genetic polymorphisms and non-variceal UGIB. Twenty-one publications and 7134 participants were included. Thirteen studies evaluated genetic polymorphism in patients exposed to non-steroidal anti-inflammatory drugs, low-dose aspirin, and warfarin. Eight studies present at least one methodological problem. Only six studies clearly defined that the outcome evaluated was non-variceal UGIB. Genetic polymorphisms involved in platelet activation and aggregation, angiogenesis, inflammatory process, and drug metabolism were associated with risk of non-variceal UGIB (NOS3, COX-1; COX-2; PLA2G7; GP1BA; GRS; IL1RN; F13A1; CDKN2B-AS1; DPP6; TBXA2R; TNF-alpha; VKORC1; CYP2C9; and AGT). Further well-designed studies are needed (e.g., clear restriction to non-variceal UGIB; proper selection of participants; and adjustment of confounding factors) to provide strong evidence for pharmacogenetic and personalized medicine.
Diagnostic accuracy of computerized tomography (CT) angiography in detecting non-variceal gastrointestinal bleeding (NVGIB): a sistematic review
Ciarambino T, Giannico OV, Menna G, Sansone G, Para O, Giordano M, Corrente A, Adinolfi LE
Minerva gastroenterologica e dietologica. 2020
INTRODUCTION The American Society for Gastrointestinal Endoscopy (ASGE) has produced numerous algorithms for the management of gastrointestinal bleeding (GIB) in which endoscopy plays a major role. The aim of this Systematic Review was to evaluate the diagnostic accuracy of computerized tomography (CT) angiography in detecting non-variceal gastrointestinal bleeding (NVGIB). METHODS Studies were identified on PubMed, Web of Science and Scopus databases from 2009 to 2019. The search performed included the following terms: "digestive" and "bleeding" as well as "acute bleeding gastrointestinal" or "acute bleeding digestive". Studies were included if enrolled adult patients and included measures of diagnostic accuracy (sensibility and specificity) of CT angiography in detecting GIB. Studies on variceal bleeding were excluded. First, a bivariate diagnostic randomeffects meta-analysis was fitted through REML (Restricted maximum likelihood approach) method, with the estimation of pooled sensitivity, specificity and SROC curve. Then, an univariate model was fitted for the 11 studies, with the estimation of pooled Diagnostic Odds Ratio and Cochrane's Q for heterogeneity. RESULTS Eleven studies were eligible for inclusion criteria and so included in the analysis. The pooled sensitivity is 85% [75%, 92%], the pooled specificity 93% [89%, 96%]. The pooled DOR is 94.35 [37.91, 234.82]. Q for heterogeneity is not significant (p=0.377). CONCLUSIONS CT angiography showed a good sensibility and specificity in detecting NVGIB. Therefore, it would be useful to consider CT angiography use also in the suspicion of NVGIB, especially when endoscopy is not immediately available and there are signs and symptoms of bleeding in progress.
Machine Learning to Predict Outcomes in Patients with Acute Gastrointestinal Bleeding: A Systematic Review
Shung D, Simonov M, Gentry M, Au B, Laine L
Digestive diseases and sciences. 2019
Risk stratification of patients with gastrointestinal bleeding (GIB) is recommended, but current risk assessment tools have variable performance. Machine learning (ML) has promise to improve risk assessment. We performed a systematic review to evaluate studies utilizing ML techniques for GIB. Bibliographic databases and conference abstracts were searched for studies with a population of overt GIB that used an ML algorithm with outcomes of mortality, rebleeding, hemostatic intervention, and/or hospital stay. Two independent reviewers screened titles and abstracts, reviewed full-text studies, and extracted data from included studies. Risk of bias was assessed with an adapted Quality in Prognosis Studies tool. Area under receiver operating characteristic curves (AUCs) were the primary assessment of performance with AUC ≥ 0.80 predefined as an acceptable threshold of good performance. Fourteen studies with 30 assessments of ML models met inclusion criteria. No study had low risk of bias. Median AUC reported in validation datasets for predefined outcomes of mortality, intervention, or rebleeding was 0.84 (range 0.40-0.98). AUCs were higher with artificial neural networks (median 0.93, range 0.78-0.98) than other ML models (0.81, range 0.40-0.92). ML performed better than clinical risk scores (Glasgow-Blatchford, Rockall, Child-Pugh, MELD) for mortality in upper GIB. Limitations include heterogeneity of ML models, inconsistent comparisons of ML models with clinical risk scores, and high risk of bias. ML generally provided good-excellent prognostic performance in patients with GIB, and artificial neural networks tended to outperform other ML models. ML was better than clinical risk scores for mortality in upper GIB.
Quality Evaluation of the Non-Variceal Upper Gastrointestinal Bleeding Guidelines/Consensuses via AGREE II Tools
Wang Y, Guo J, Rao Y, Xiao GR, Zhao X
Journal of the College of Physicians and Surgeons--Pakistan : JCPSP. 2019;29(10):977-985
Non-variceal upper gastrointestinal bleeding (NUGIB) is a common disease in clinical practice; and many related guidelines/consensuses have been published. The authors assessed the methodological quality of the NUGIB guidelines/ consensuses published in English, in order to uncover which guidelines/consensuses are of better quality in methodology and the deficiency in the area. Appraisal of guidelines for research and evaluation instrument tools were adopted to assess the quality of the guidelines/consensuses. Each guideline/consensus was assessed independently by three researchers. Intra-class correlation (ICC) among researchers was retrieved to reflect reliability. Eight guidelines/consensuses regarding the management of NUGIB published in English were obtained. The ICCs among the evaluators were all above 0.75, indicating satisfactory reliability. Quality evaluation of the obtained guidelines via the AGREE II tools showed that the overall quality of the included guidelines/consensuses was moderate in all domains. A few guidelines/consensuses were better developed in scientific and methodological aspects than the others. The grades of recommendations with the guidelines/consensuses, according to a brief and preliminary scheme, were of practical value. Moreover, the recommendations regarding the pharmacological treatments in the guidelines/consensuses above, are various according to the study. Overall, the quality of some NUGIB guidelines/consensuses were generally acceptable and applicable, those yet are with minor deficiencies. The others may be improved according to the AGREE II items, likely by evaluating the quality of the guidelines/consensuses when the guidelines/consensuses are updated.