The Predictive Value of Preendoscopic Risk Scores to Predict Adverse Outcomes in Emergency Department Patients With Upper Gastrointestinal Bleeding: A Systematic Review

Validation of an Electronic Health Record-Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding

BACKGROUND & AIMS

Guidelines recommend use of risk stratification scores for patients presenting with gastrointestinal bleeding (GIB) to identify very-low-risk patients eligible for discharge from emergency departments. Machine learning models may outperform existing scores and can be integrated within the electronic health record (EHR) to provide real-time risk assessment without manual data entry. We present the first EHR-based machine learning model for GIB.

METHODS

The training cohort comprised 2546 patients and internal validation of 850 patients presenting with overt GIB (ie, hematemesis, melena, and hematochezia) to emergency departments of 2 hospitals from 2014 to 2019. External validation was performed on 926 patients presenting to a different hospital with the same EHR from 2014 to 2019. The primary outcome was a composite of red blood cell transfusion, hemostatic intervention (ie, endoscopic, interventional radiologic, or surgical), and 30-day all-cause mortality. We used structured data fields in the EHR, available within 4 hours of presentation, and compared the performance of machine learning models with current guideline-recommended risk scores, Glasgow-Blatchford Score, and Oakland Score. Primary analysis was area under the receiver operating characteristic curve. Secondary analysis was specificity at 99% sensitivity to assess the proportion of patients correctly identified as very low risk.

RESULTS

The machine learning model outperformed the Glasgow-Blatchford Score (area under the receiver operating characteristic curve, 0.92 vs 0.89; P < .001) and Oakland Score (area under the receiver operating characteristic curve, 0.92 vs 0.89; P < .001). At the very-low-risk threshold of 99% sensitivity, the machine learning model identified more very-low-risk patients: 37.9% vs 18.5% for Glasgow-Blatchford Score and 11.7% for Oakland Score (P < .001 for both comparisons).

CONCLUSIONS

An EHR-based machine learning model performs better than currently recommended clinical risk scores and identifies more very-low-risk patients eligible for discharge from the emergency department.

Emergency medicine updates: Upper gastrointestinal bleeding

INTRODUCTION

Upper gastrointestinal bleeding (UGIB) is a condition commonly seen in the emergency department (ED). Therefore, it is important for emergency clinicians to be aware of the current evidence regarding the diagnosis and management of this disease.

OBJECTIVE

This paper evaluates key evidence-based updates concerning UGIB for the emergency clinician.

DISCUSSION

UGIB most frequently presents with hematemesis. There are numerous causes, with the most common peptic ulcer disease, though variceal bleeding in particular can be severe. Nasogastric tube lavage for diagnosis is not recommended based on the current evidence. A hemoglobin transfusion threshold of 7 g/dL is recommended (8 g/dL in those with myocardial ischemia), but patients with severe bleeding and hemodynamic instability require emergent transfusion regardless of their level. Medications that may be used in UGIB include proton pump inhibitors, prokinetic agents, and vasoactive medications. Antibiotics are recommended for those with cirrhosis and suspected variceal bleeding. Endoscopy is the diagnostic and therapeutic modality of choice and should be performed within 24 h of presentation in non-variceal bleeding after resuscitation, though patients with variceal bleeding may require endoscopy within 12 h. Transcatheter arterial embolization or surgical intervention may be necessary. Intubation should be avoided if possible. If intubation is necessary, several considerations are required, including resuscitation prior to induction, utilizing preoxygenation and appropriate suction, and administering a prokinetic agent. There are a variety of tools available for risk stratification, including the Glasgow Blatchford Score.

CONCLUSIONS

An understanding of literature updates can improve the ED care of patients with UGIB.

Efficacy of Vonoprazan vs. Intravenous Proton Pump Inhibitor in Prevention of Re-Bleeding of High-Risk Peptic Ulcers: A Randomized Controlled Pilot Study

Background: Proton pump inhibitor (PPI) therapy is well-established for its effectiveness in reducing re-bleeding in high-risk peptic ulcer patients following endoscopic hemostasis. Vonoprazan (VPZ) has demonstrated the capacity to achieve gastric pH levels exceeding 4, comparable to PPIs. This study aims to evaluate the comparative efficacy of intravenous PPI infusion versus VPZ in preventing re-bleeding after endoscopic hemostasis in patients with high-risk peptic ulcers. Methods: A randomized, double-blind, controlled, and double-dummy design was employed. Patients with peptic ulcer bleeding (Forrest class IA/IB or IIA/IIB) who underwent endoscopic hemostasis were randomly assigned to either the PPI group or the VPZ group. Re-bleeding rates at 3, 7, and 30 days, the number of blood transfusions required, length of hospitalization, and ulcer healing rate at 56 days were assessed. Results: A total of 44 eligible patients were enrolled, including 20 patients (PPI group, n = 11; VPZ group, n = 9) with high-risk peptic ulcers. The mean age was 66 years, with 70% being male. Re-bleeding within 72 h occurred in 9.1% of the PPI group versus 0% in the VPZ group (p = 1.000). There was no significant difference in re-bleeding rates within 7 days and 30 days (18.2% vs. 11.1%, p = 1.000). Additionally, the ulcer healing rate did not significantly differ between the groups (87.5% vs. 77.8%). Conclusions: This pilot study demonstrates comparable efficacy between oral vonoprazan and continuous PPI infusion in preventing recurrent bleeding events among high-risk peptic ulcer patients following successful endoscopic hemostasis.

Scoring systems for risk stratification in upper and lower gastrointestinal bleeding

Several scoring systems have been developed for both upper and lower GI bleeding to predict the bleeding severity and discriminate between low-risk patients, who may be suitable for outpatient management, and those who would likely need hospital-based interventions and are at high risk for adverse outcomes. Risk scores created to identify low-risk patients (namely the Glasgow Blatchford Score and the Oakland score) showed very good discriminative performances and their implementation has proven to be effective in reducing hospital admissions and healthcare burden. Conversely, the performances of risk scores in identifying specific adverse events to define high-risk patients are less accurate, and whether their integration into routine clinical practice has a tangible impact on patient management remains unproven. This review describes the existing risk score systems for GI bleeding, emphasizes key research findings, elucidates the circumstances in which their utilization can be beneficial, examines their constraints when considering routine clinical application, and discuss future development.

Urgent endoscopy versus early endoscopy: Does urgent endoscopy play a role in acute non-variceal upper gastrointestinal bleeding?

INTRODUCTION

The main clinical practice guidelines recommend endoscopy within 24hours after admission to the Emergency Department in patients with non-variceal upper gastrointestinal bleeding. However, it is a wide time frame and the role of urgent endoscopy (<6hours) is controversial.

MATERIAL AND METHODS

Prospective observational study carried out at La Paz University Hospital, where all patients were selected, from January 1, 2015 to April 30, 2020, who attended the Emergency Room and underwent endoscopy for suspected upper gastrointestinal bleeding. Two groups of patients were established: urgent endoscopy (<6hours) and early endoscopy (6-24hours). The primary endpoint of the study was 30-day mortality.

RESULTS

A total of 1096 were included, of whom 682 underwent urgent endoscopy. Mortality at 30days was 6% (5% vs 7.7%, P=.064) and rebleeding was 9.6%. There were no statistically significant differences in mortality, rebleeding, need for endoscopic treatment, surgery and/or embolization, but there were differences in the necessity for transfusion(57.5% vs 68.4%, P<.001) and the number of concentrates of transfused red blood cells (2.85±4.01 vs 3.51±4.09, P=.008).

CONCLUSION

Urgent endoscopy, in patients with acute upper gastrointestinal bleeding, as well as the high-risk subgroup (GBS ≥12), was not associated with lower 30-day mortality than early endoscopy. However, urgent endoscopy in patients with high-risk endoscopic lesions (ForrestI-IIB), was a significant predictor of lower mortality. Therefore, more studies are required for the correct identification of patients who benefit from this medical approach (urgent endoscopy).

Interpretations of the Role of Plasma Albumin in Prognostic Indices: A Literature Review

This review assesses how publications interpret factors that influence the serum or plasma albumin (PA) level in prognostic indices, focusing on inflammation and nutrition. On PubMed, a search for "albumin AND prognosis" yielded 23,919 results. From these records, prognostic indices were retrieved, and their names were used as search strings on PubMed. Indices found in 10 or more original research articles were included. The same search strings, restricted to "Review" or "Systematic review", retrieved yielded on the indices. The data comprised the 10 latest original research articles and up to 10 of the latest reviews. Thirty indices had 294 original research articles (6 covering two indices) and 131 reviews, most of which were from recent years. A total of 106 articles related the PA level to inflammation, and 136 related the PA level to nutrition. For the reviews, the equivalent numbers were 54 and 65. In conclusion, more publications mention the PA level as a marker of nutrition rather than inflammation. This is in contrast to several general reviews on albumin and nutritional guidelines, which state that the PA level is a marker of inflammation but not nutrition. Hypoalbuminemia should prompt clinicians to focus on the inflammatory aspects in their patients.

Pre-Endoscopic Scores Predicting Low-Risk Patients with Upper Gastrointestinal Bleeding: A Systematic Review and Meta-Analysis

BACKGROUND

Several risk scores have attempted to risk stratify patients with acute upper gastrointestinal bleeding (UGIB) who are at a lower risk of requiring hospital-based interventions or negative outcomes including death. This systematic review and meta-analysis aimed to compare predictive abilities of pre-endoscopic scores in prognosticating the absence of adverse events in patients with UGIB.

METHODS

We searched MEDLINE, EMBASE, Central, and ISI Web of knowledge from inception to February 2023. All fully published studies assessing a pre-endoscopic score in patients with UGIB were included. The primary outcome was a composite score for the need of a hospital-based intervention (endoscopic therapy, surgery, angiography, or blood transfusion). Secondary outcomes included: mortality, rebleeding, or the individual endpoints of the composite outcome. Both proportional and comparative analyses were performed.

RESULTS

Thirty-eight studies were included from 2153 citations, (n = 36,215 patients). Few patients with a low Glasgow-Blatchford score (GBS) cutoff (0, ≤1 and ≤2) required hospital-based interventions (0.02 (0.01, 0.05), 0.04 (0.02, 0.09) and 0.03 (0.02, 0.07), respectively). The proportions of patients with clinical Rockall (CRS = 0) and ABC (≤3) scores requiring hospital-based intervention were 0.19 (0.15, 0.24) and 0.69 (0.62, 0.75), respectively. GBS (cutoffs 0, ≤1 and ≤2), CRS (cutoffs 0, ≤1 and ≤2), AIMS65 (cutoffs 0 and ≤1) and ABC (cutoffs ≤1 and ≤3) scores all were associated with few patients (0.01-0.04) dying. The proportion of patients suffering other secondary outcomes varied between scoring systems but, in general, was lowest for the GBS. GBS (using cutoffs 0, ≤1 and ≤2) showed excellent discriminative ability in predicting the need for hospital-based interventions (OR 0.02, (0.00, 0.16), 0.00 (0.00, 0.02) and 0.01 (0.00, 0.01), respectively). A CRS cutoff of 0 was less discriminative. For the other secondary outcomes, discriminative abilities varied between scores but, in general, the GBS (using cutoffs up to 2) was clinically useful for most outcomes.

CONCLUSIONS

A GBS cut-off of one or less prognosticated low-risk patients the best. Expanding the GBS cut-off to 2 maintains prognostic accuracy while allowing more patients to be managed safely as outpatients. The evidence is limited by the number, homogeneity, quality, and generalizability of available data and subjectivity of deciding on clinical impact. Additional, comparative and, ideally, interventional studies are needed.

Utility of the CANUKA Scoring System in the Risk Assessment of Upper GI Bleeding

BACKGROUND

The Canada-United Kingdom-Adelaide (CANUKA) score was developed to stratify patients who experience upper gastrointestinal bleeding (UGIB) to predict who could be discharged from the emergency department. Our aim was to determine if the CANUKA score could be utilized for UGIB in-patients undergoing endoscopy in predicting adverse outcomes. We additionally sought to establish a CANUKA score cut point to predict adverse outcomes and in-hospital mortality and compare this to established scoring systems.

METHODS

Between January 1, 2018 to June 30, 2019 all patients who underwent upper endoscopy after admission for UGIB were identified. We assigned a CANUKA score and compared the area under the receiver operating curve to established scoring systems.

RESULTS

Our data set included 641 patients, with a mean age of 59.5±14.5 years. A CANUKA score ≥10 was associated with an adverse outcome [unadjusted odds ratio, 3.08 (1.79, 5.27)]. No patients experienced an adverse outcome with a CANUKA score <4. No patients died with a CANUKA score <6. Those with a CANUKA score of <10 had an in-hospital mortality of 2.1% compared with 6.8% for those with a score ≥10 ( P =0.008). AIMS65 had the best area under the receiver operating characteristic curve (0.809) for predicting mortality.

CONCLUSIONS

The CANUKA score may serve utility as a predictor of adverse outcomes and mortality in patients admitted with UGIB undergoing endoscopy. Future studies, ideally prospective and multicenter, will be needed to validate its clinical utility.

Strengths and limitations of risk stratification tools for patients with upper gastrointestinal bleeding: a narrative review

INTRODUCTION

Despite advances in the management of patients with upper gastrointestinal bleeding (UGIB), associated morbidity and mortality remain significant. Most patients, however, will experience favorable outcomes without a need for hospital-based interventions. Risk assessment scores may assist in such early risk-stratification. These scales may optimize identification of low-risk patients, resulting in better resource utilization, including a reduced need for early endoscopy and fewer hospital admissions. The aim of this article is to provide an updated detailed review of risk assessment scores in UGIB.

AREA COVERED

A literature review identified past and currently available pre-endoscopic risk assessment scores for UGIB, with a focus on low-risk prediction. Strengths and weaknesses of the different scales are discussed as well as their impact on clinical decision-making.

EXPERT OPINION

The current evidence supports using the Glasgow Blatchford Score as it is the most accurate tool available when attempting to identify low-risk patients who can be safely managed on an outpatient basis. Currently, no risk assessment tool appears accurate enough in confidently classifying patients as high risk. Future research should utilize more standardized methodologies, while favoring interventional trial designs to better characterize the clinical impact attributable to the use of such risk stratification schemes.

Novel risk score for acute upper gastrointestinal bleeding in elderly patients: a single-centre retrospective study

OBJECTIVES

Acute upper gastrointestinal bleeding (UGIB) is a common reason for emergency hospital admission. Identifying low-risk patients suitable for outpatient management is a clinical and research priority. This study aimed to develop a simple risk score to identify elderly patients with UGIB for whom hospital admission is not required.

DESIGN

This was a single-centre retrospective study.

SETTING

This study was conducted at Zhongda Hospital affiliated with Southeast University in China.

PARTICIPANTS

Patients from January 2015 to December 2020 for the derivation cohort and from January 2021 to June 2022 for the validation cohort were enrolled in this study. A total of 822 patients (derivation cohort=606 and validation cohorts=216) were included in this study. Patients aged ≥65 years with coffee-grounds vomiting, melena or/and haematemesis were included in the analysis. Patients admitted but had UGIB or transferred between hospitals were excluded.

METHODS

Baseline demographic characteristics and clinical parameters were recorded at the first visit. Data were collected from electronic records and databases. Multivariable logistic regression modelling was performed to identify predictors of safe discharge.

RESULTS

304/606 (50.2%) and 132/216 (61.1%) patients were not safely discharged in the derivation and validation cohorts, respectively. A clinical risk score of five variables was entered into UGIB risk stratification: Charlson Comorbidity Index >2, systolic blood pressure <100 mm Hg, haemoglobin <100 g/L, blood urea nitrogen ≥6.5 mmol/L, albumin <30 g/L. The optimal cut-off value was ≥1, the sensitivity was 97.37% and the specificity was 19.21% for predicting the inability to discharge safely. The area under the receiver operating characteristic curve was 0.806.

CONCLUSIONS

A novel clinical risk score with good discriminative performance was developed to identify elderly patients with UGIB who were suitable for safe outpatient management. This score can reduce unnecessary hospitalisations.

A Review of Risk Scores within Upper Gastrointestinal Bleeding

Upper gastrointestinal bleeding is a common medical emergency. Thorough initial assessment and appropriate resuscitation are essential to stabilise the patient. Risk scores provide an important tool to discriminate between lower- and higher-risk patients. Very low-risk patients can be safely discharged for out-patient management, while higher-risk patients can receive appropriate in-patient care. The Glasgow Blatchford Score, with a score of 0-1, performs best in the identification of very low-risk patients who will not require hospital based intervention or die, and is recommended by most guidelines to facilitate safe out-patient management. The performance of risk scores in the identification of specific adverse events to define high-risk patients is less accurate, with no individual score performing consistently well. Ongoing developments in the use of machine learning models and artificial intelligence in predicting poor outcomes in UGIB appear promising and will likely form the basis of dynamic risk assessment in the future.

The global epidemiology of upper and lower gastrointestinal bleeding in general population: A systematic review

BACKGROUND

Gastrointestinal bleeding (GIB) is a common and potentially life-threatening clinical event. To date, the literature on the long-term global epidemiology of GIB has not been systematically reviewed.

AIM

To systematically review the published literature on the worldwide epidemiology of upper and lower GIB.

METHODS

EMBASE^® and MEDLINE were queried from 01 January 1965 to September 17, 2019 to identify population-based studies reporting incidence, mortality, or case-fatality rates of upper GIB (UGIB) or lower GIB (LGIB) in the general adult population, worldwide. Relevant outcome data were extracted and summarized (including data on rebleeding following initial occurrence of GIB when available). All included studies were assessed for risk of bias based upon reporting guidelines.

RESULTS

Of 4203 retrieved database hits, 41 studies were included, comprising a total of around 4.1 million patients with GIB worldwide from 1980–2012. Thirty-three studies reported rates for UGIB, four for LGIB, and four presented data on both. Incidence rates ranged from 15.0 to 172.0/100000 person-years for UGIB, and from 20.5 to 87.0/100000 person-years for LGIB. Thirteen studies reported on temporal trends, generally showing an overall decline in UGIB incidence over time, although a slight increase between 2003 and 2005 followed by a decline was shown in 5/13 studies. GIB-related mortality data were available from six studies for UGIB, with rates ranging from 0.9 to 9.8/100000 person-years, and from three studies for LGIB, with rates ranging from 0.8 to 3.5/100000 person-years. Case-fatality rate ranged from 0.7% to 4.8% for UGIB and 0.5% to 8.0% for LGIB. Rates of rebleeding ranged from 7.3% to 32.5% for UGIB and from 6.7% to 13.5% for LGIB. Two main areas of potential bias were the differences in the operational GIB definition used and inadequate information on how missing data were handled.

CONCLUSION

Wide variation was seen in estimates of GIB epidemiology, likely due to high heterogeneity between studies however, UGIB showed a decreasing trend over the years. Epidemiological data were more widely available for UGIB than for LGIB.

The Accuracy of Pre-Endoscopic Scores for Mortality Prediction in Patients with Upper GI Bleeding and No Endoscopy Performed

(1) Background: The assessment of mortality and rebleeding rate in upper gastrointestinal bleeding (UGIB) is essential, and several prognostic scores have been proposed. Some patients with UGIB did not undergo endoscopy, either because they refused the procedure, suffered from alcohol withdrawal symptoms or altered general status, or because the bleeding was severe enough to cause death before the endoscopy. The mortality risk in the subgroup of patients without endoscopy is poorly evaluated in the literature. (2) Methods: The purpose of the study was to identify the most useful scores for the assessment of in-hospital mortality in patients with UGIB with no endoscopy performed and no known etiology. A total of 198 patients with UGIB and no endoscopy performed were admitted between January 2017 and December 2021 and the accuracy of 12 prognostic scores and the Charlson comorbidity index for in-hospital mortality prediction were analyzed, as well as Child-Pugh Turcotte (CPT) and Meld scores in patients with cirrhosis. (3) Results: The mortality rate was 37.9%, higher than in variceal (21.9%, p < 0.0001) and non-variceal bleeding (7.4%, p < 0.0001). The most accurate scores by AUC were the International Bleeding score (INBS, 0.844), Glasgow Blatchford (0.783), MAP score (0.78), Iino (0.766), AIM65 and modified N-score (0.745 each), modified Glasgow-Blatchford (0.73), H3B2 and N-score (0.701); Rockall, Baylor, and T-score had an AUC below 0.7. MELD score was superior to CPT in patients with cirrhosis (AUC 0.811 versus 0.670). (4) Conclusions: The mortality rate in UGIB with no endoscopy was higher than in both variceal and non-variceal bleeding and was higher in the pandemic period but with no statistical significance (45.3% versus 32.14%, p = 0.0586), mainly because of positive cases. Only one case of rebleeding was noted; the hospitalization period was significantly shorter. The most accurate score was International Bleeding Score; the MELD score had a higher but moderate accuracy compared with CPT in patients with cirrhosis.

Predicting mortality in patients with nonvariceal upper gastrointestinal bleeding using machine-learning

Background

Non-endoscopic risk scores, Glasgow Blatchford (GBS) and admission Rockall (Rock), are limited by poor specificity. The aim of this study was to develop an Artificial Neural Network (ANN) for the non-endoscopic triage of nonvariceal upper gastrointestinal bleeding (NVUGIB), with mortality as a primary outcome.

Methods

Four machine learning algorithms, namely, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), logistic regression (LR), K-Nearest Neighbor (K-NN), were performed with GBS, Rock, Beylor Bleeding score (BBS), AIM65, and T-score.

Results

A total of 1,096 NVUGIB hospitalized in the Gastroenterology Department of the County Clinical Emergency Hospital of Craiova, Romania, randomly divided into training and testing groups, were included retrospectively in our study. The machine learning models were more accurate at identifying patients who met the endpoint of mortality than any of the existing risk scores. AIM65 was the most important score in the detection of whether a NVUGIB would die or not, whereas BBS had no influence on this. Also, the greater AIM65 and GBS, and the lower Rock and T-score, the higher mortality will be.

Conclusion

The best accuracy was obtained by the hyperparameter-tuned K-NN classifier (98%), giving the highest precision and recall on the training and testing datasets among all developed models, showing that machine learning can accurately predict mortality in patients with NVUGIB.

A Glasgow-Blatchford Bleeding Score of >2 Is a Poor Predictor of Endoscopic Intervention in Nonvariceal Upper GI Bleeding

OBJECTIVES

Recent data show that a Glasgow-Blatchford Bleeding Score (GBS) >2 does not identify patients with upper gastrointestinal (GI) bleeding who benefit from inpatient esophagogastroduodenoscopy (EGD). This study aimed to determine the rate of endoscopic hemostatic interventions (HI) in patients with nonvariceal acute GI bleeding (NVAUGIB) admitted with a GBS >2. Secondary aims included comparison of clinical outcomes in patients with and without HI and cost of nontherapeutic EGDs.

METHODS

We conducted a retrospective review of medical records of patients admitted to a referral hospital for NVAUGIB from January 2015 to December 2017. Mortality, blood transfusion rates, length of stay, length of intensive care unit stay, and cost of a nontherapeutic EGD were outcomes of interest. Patients 18 years of age and older of both sexes were included. The accuracy of the GBS >2 cutoff was determined using receiver operating characteristic curve analysis.

RESULTS

A total of 357 patients were included and only 58 (16.2%) required HI. The area under the curve for GBS >2 as a predictor of HI was 0.57. The performance of HI did not influence mortality (P = 0.33), blood transfusion rates (P = 0.51), length of stay (P = 0.2), or length of intensive care unit stay (P = 0.36). The estimated cost of performing nontherapeutic EGD was approximately $855,000 for the 299 patients who did not need HI.

CONCLUSIONS

A GBS cutoff of >2 is not an accurate criterion to triage patients with NVAUGIB for inpatient emergent EGD. More clinically meaningful and cost-effective methods to triage these patients are necessary.

Scoring systems for predicting clinical outcomes in peptic ulcer bleeding

Few studies have focused on assessing the usefulness of scoring systems such as the Rockall score (RS), Glasgow-Blatchford score (GBS), and AIMS65 score for risk stratification and prognosis prediction in peptic ulcer bleeding patients. This study aimed to assess scoring systems in predicting clinical outcomes of patients with peptic ulcer bleeding. A total of 682 peptic ulcer bleeding patients who underwent esophagogastroduodenoscopy between January 2013 and December 2017 were found eligible for this study. The area under the receiver-operating characteristic curve (AUROC) of each score was calculated for predicting rebleeding, hospitalization, blood transfusion, and mortality. The median age of patients was 64 (interquartile range, 56-75) years. Of the patients, 74.9% were men, and 373 underwent endoscopic intervention. The median RS, GBS, and AIMS65 scores were significantly higher in patients who underwent endoscopic intervention than in those who did not. The AUROC of RS for predicting rebleeding was significantly higher than that of GBS (P = .022) or AIMS65 (P < .001). GBS best predicted the need for blood transfusion than either pre-RS (P = .013) or AIMS65 (P = .001). AIMS65 score showed the highest AUROC for mortality (0.652 vs. 0.622 vs. 0.691). RS was significantly associated with rebleeding (odds ratio, 1.430; P < .001) and overall survival (hazard ratio, 1.217; P < .001). The RS, GBS, and AIMS65 scoring systems are acceptable tools for predicting clinical outcomes in peptic ulcer bleeding. RS is an independent prognostic factor of rebleeding and overall survival.

Prediction of the need for emergency endoscopic treatment for upper gastrointestinal bleeding and new score model: a retrospective study

Background

Gastrointestinal bleeding is one of the major gastrointestinal diseases. In this study, our objective was to compare Glasgow-Blatchford score (GBS), AIMS65 score, MAP score, Modified GBS, and Iino score as outcome measures for upper gastrointestinal bleeding. In addition, we extracted factors associated with hemostatic procedures including endoscopy, and proposed a new robust score model.

Methods

From January 2015 to December 2019, 675 patients with symptoms such as hematemesis who visited the National Hospital Organization Disaster Medical Center and underwent urgent upper endoscopy with diagnosis of suspected non-variceal upper gastrointestinal bleeding were retrospectively reviewed. We evaluated the GBS, AIMS65 score, MAP score, Modified GBS, and Iino score, and assessed the outcomes of patients requiring hemostatic treatments at the subsequent emergency endoscopy. We performed logistic regression analysis of factors related to endoscopic hemostasis and upper gastrointestinal bleeding, created a new score model, and evaluated the prediction of hemostatic treatment and mortality in the new score and the existing scores.

Results

The factors associated with endoscopic treatment were hematemesis, heart rate, HB (hemoglobin), blood pressure, blood urea nitrogen (BUN). Based on these predictors and the partial regression coefficients, a new score named H3B2 (using the initial letters of hematemesis, heart rate, HB, blood pressure, and BUN) was generated. H3B2 score was slightly more discriminatory compared to GBS and Modified GBS (area under the receiver operating characteristic curves (AUROC): 0.73 versus 0.721 and 0.7128, respectively) in predicting hemostatic treatment in emergency endoscopy. The H3B2 score also showed satisfactory prediction accuracy for subsequent deaths (AUROC: 0.6857. P < 0.001).

Conclusions

We proposed a new score, the H3B2 score, consisting of simple and objective indices in cases of suspected upper gastrointestinal bleeding. The H3B2 score is useful in identifying high-risk patients with suspected upper gastrointestinal bleeding who require urgent hemostatic treatment including emergency endoscopy.

A Comparative Analysis of Risk Scoring Systems in Predicting Clinical Outcomes in Upper Gastrointestinal Bleed

Background

Upper gastrointestinal bleed (UGIB) is a life-threatening condition that presents as hematemesis (fresh blood), coffee-ground vomiting, or melena. Multiple scoring systems are developed to predict different clinical outcomes, which are important to managing UGIB and are essential to determining low and high-risk patients. The study aimed to compare the sensitivity and specificity of risk scoring systems and their optimum cut-off values in the assessment of UGIB.

Methods

The prospective cross-sectional study included patients (N = 81) with acute UGIB. Four different proposed scores [Glasgow-Blatchford score (GBS), AIMS65, pre-endoscopic Rockall, and full Rockall scoring system] were used for evaluating patients with UGIB. The optimum cut-off values of these risk scores were used to predict the clinical outcomes.

Results

The AIMS65 score [Area Under the Receiver Operating Characteristic curve (AUROC): 0.91, cut-off: >1, sensitivity: 100%, specificity: 76.62%] and pre-Rockall were similar (AUROC: 0.91, cut-off: >0, sensitivity: 100%, specificity: 93.51%) at predicting mortality. The GBS (cut-off: >9, AUROC: 0.79, sensitivity: 69.23, specificity: 87.50) and AIMS65 scores (cut-off: >0, AUROC: 0.67, sensitivity: 72.31, specificity: 62.5) were good predictors of need for ICU care.

Conclusion

GBS was superior in predicting categorization into high risk and low risk, and endoscopic intervention, blood transfusion, and intensive care unit (ICU) care in UGIB patients. Pre-Rockall score and AIMS65 score were similar in predicting the mortality rate in UGIB.

The effect of the shock index and scoring systems for predicting mortality among geriatric patients with upper gastrointestinal bleeding: a prospective cohort study

BACKGROUND

Gastrointestinal (GI) bleeding is an important cause of mortality and morbidity among geriatric patients.

OBJECTIVE

To investigate whether the shock index and other scoring systems are effective predictors of mortality and prognosis among geriatric patients presenting to the emergency department with complaints of upper GI bleeding.

DESIGN AND SETTING

Prospective cohort study in an emergency department in Bursa, Turkey.

METHODS

Patients over 65 years admitted to a single-center, tertiary emergency service between May 8, 2019, and April 30, 2020, and diagnosed with upper GI bleeding were analyzed. 30, 180 and 360-day mortality prediction performances of the shock index and the Rockall, Glasgow-Blatchford and AIMS-65 scores were evaluated.

RESULTS

A total of 111 patients who met the criteria were included in the study. The shock index (P < 0.001) and AIMS-65 score (P < 0.05) of the patients who died within the 30-day period were found to be significantly different, while the shock index (P < 0.001), Rockall score (P < 0.001) and AIMS-65 score (P < 0.05) of patients who died within the 180-day and 360-day periods were statistically different. In the receiver operating characteristic (ROC) analysis for predicting 360-day mortality, the area under the curve (AUC) value was found to be 0.988 (95% confidence interval, CI, 0.971-1.000; P < 0.001).

CONCLUSION

The shock index measured among geriatric patients with upper GI bleeding at admission seems to be a more effective predictor of prognosis than other scoring systems.

Comparisons of six endoscopy independent scoring systems for the prediction of clinical outcomes for elderly and younger patients with upper gastrointestinal bleeding

OBJECTIVES

To compare the predictive ability of six pre-endoscopic scoring systems (ABC, AIMS65, GBS, MAP(ASH), pRS, and T-score) for outcomes of upper gastrointestinal bleeding (UGIB) in elderly and younger patients.

METHODS

A retrospective study of 1260 patients, including 530 elderly patients (age [Formula: see text] 65) and 730 younger patients (age < 65) presenting with UGIB, was performed at Zhongda Hospital Southeast University, from January 2015 to December 2020. Six scoring systems were used.

RESULTS

ABC had the largest areas under the curve (AUCs) of 0.827 (0.792-0.858), and 0.958 (0.929-0.987) for elderly and younger groups for predicting mortality respectively. The differences of the AUCs for predicting the outcome of mortality and rebleeding between the two groups were significant for ABC and pRS (p < 0.01). For intervention prediction, significant differences were observed only for pRS [AUC 0.623 (0.578-0.669) vs. 0.699 (0.646-0.752)] (p < 0.05) between the two groups. For intensive care unit (ICU) admission, the AUC for MAP (ASH) [0.791 (0.718-0.865) vs. 0.891 (0.831-0.950)] and pRS [0.610 (0.514-0.706) vs. 0.891 (0.699-0.865)] were more effective for the younger group (p < 0.05 and p < 0.01, respectively). For comparison of scoring systems in the same cohort, ABC was significantly higher than pRS: AUC 0.710 (0.699-0.853, p < 0.05) and T-score 0.670 (0.628-0.710, p < 0.01) for predicting mortality in the elderly group. In the younger group, ABC was significantly higher than GBS and T-score (p < 0.01). MAP(ASH) performs the best in predicting intervention in both groups.

CONCLUSIONS

ABC and pRS are more accurate for predicting mortality and rebleeding in the younger cohort, and pRS may not be suitable for elderly patients. There was no difference between the two study populations for GBS, AIMS65, and T-score. Except for ICU admission, MAP(ASH) showed fair accuracy for both cohorts.

Update on the management of upper gastrointestinal bleeding

Upper gastrointestinal bleeding is a common emergency presentation requiring prompt resuscitation and management. Peptic ulcers are the most common cause of the condition. Thorough initial management with a structured approach is vital with appropriate intravenous fluid resuscitation and use of a restrictive transfusion threshold of 7-8 g/dL. Pre-endoscopic scoring tools enable identification of patients at high risk and at very low risk who might benefit from specific management. Endoscopy should be carried out within 24 h of presentation for patients admitted to hospital, although optimal timing for patients at a higher risk within this period is less clear. Endoscopic treatment of high risk lesions and use of subsequent high dose proton pump inhibitors is a cornerstone of non-variceal bleeding management. Variceal haemorrhage results in higher mortality than non-variceal haemorrhage and, if suspected, antibiotics and vasopressors should be administered urgently, before endoscopy. Oesophageal variceal bleeding requires endoscopic band ligation, whereas bleeding from gastric varices requires thrombin or tissue glue injection. Recurrent bleeding is managed by repeat endoscopic treatment. If uncontrolled bleeding occurs, interventional radiological embolisation or surgery is required for non-variceal bleeding or transjugular intrahepatic portosystemic shunt placement for variceal bleeding.

Systematic review and meta-analysis of risk scores in prediction for the clinical outcomes in patients with acute variceal bleeding

BACKGROUND

Acute variceal bleeding (AVB) is a life-threatening condition that needs risk stratification to guide clinical treatment. Which risk system could reflect the prognosis more accurately remains controversial. We aimed to conduct a meta-analysis of the predictive value of GBS, AIMS65, Rockall (clinical Rockall score and full Rockall score), CTP and MELD.

METHOD

PubMed, Web of Science, Embase, Cochrane library, WANGFANG and CNKI were searched. Twenty-eight articles were included in the study. The Meta-DiSc software and MedCalc software were used to pool the predictive accuracy.

RESULTS

Concerning in-hospital mortality, CTP, AIMS65, MELD, Full-Rockall and GBS had a pooled AUC of 0.824, 0.793, 0.788, 0.75 and 0.683, respectively. CTP had the highest sensitivity of 0.910 (95% CI: 0.864-0.944) with a specificity of 0.666 (95% CI: 0.635-0.696). AIMS65 had the highest specificity of 0.774 (95% CI: 0.749-0.798) with a sensitivity of 0.679 (95% CI: 0.617-0.736). For follow-up mortality, MELD, AIMS65, CTP, Clinical Rockall, Full-Rockall and GBS showed a pooled AUC of 0.798, 0.77, 0.746, 0.704, 0.678 and 0.618, respectively. CTP had the highest specificity (0.806, 95% CI: 0.763-0.843) with a sensitivity of 0.722 (95% CI: 0.628-0.804). GBS had the highest sensitivity 0.800 (95% CI: 0.696-0.881) with a specificity of 0.412 (95% CI: 0.368-0.457). As for rebleeding, no score performed particularly well.

CONCLUSIONS

No risk scores were ideally identified by our systematic review. CTP was superior to other risk scores in identifying AVB patients at high risk of death in hospital and patients at low risk within follow-up. Guidelines have recommended the use of GBS to risk stratification of patients with upper gastrointestinal bleeding. However, if the cause of upper gastrointestinal bleeding is suspected oesophageal and gastric varices, extra care should be taken. Because in this meta-analysis, the ability of GBS was limited.Key messageCTP was superior in identifying AVB patients at high risk of death in hospital and low risk within follow-up.GBS, though recommended by the Guidelines, should be cautiously used when assessing AVB patients.

Clinical Decision Rules in the Evaluation and Management of Adult Gastrointestinal Emergencies

Although abdominal pain is a common chief complaint in the emergency department, only 1 in 6 patients with abdominal pain are diagnosed with a gastrointestinal (GI) emergency. These patients often undergo extensive testing as well as hospitalizations to rule out an acute GI emergency and there is evidence that not all patients benefit from such management. Several clinical decision rules (CDRs) have been developed for the diagnosis and management of patients with suspected acute appendicitis and upper GI bleeding to identify those patients who may safely forgo further testing or hospital admission. Further validation studies demonstrating the superiority of these CDRs over contemporary practice are needed.

Hypocalcemia is associated with adverse clinical course in patients with upper gastrointestinal bleeding

Acute non-variceal upper gastrointestinal bleeding (NV-UGIB) is associated with significant morbidity and mortality. Early and efficient risk stratification can facilitate management and improve outcomes. We aimed to determine whether the level of ionized calcium (Ca⁺⁺), an essential co-factor in the coagulation cascade, is associated with the severity of bleeding and the need for advanced interventions among these patients. This was a retrospective single-center cohort study of all patients admitted due to NV-UGIB. The primary outcome was transfusion of ≥ 2 packed red blood cells, arterial embolization, or emergency surgery. Secondary outcomes included (1) transfusion of ≥ 2 packed red blood cells, (2) arterial embolization, or emergency surgery, and (3) all-cause in-hospital mortality. Multivariable logistic regression was performed to determine whether Ca⁺⁺ was an independent predictor of these adverse outcomes. 1345 patients were included. Hypocalcemia was recorded in 604 (44.9%) patients. The rates of primary adverse outcome were significantly higher in the hypocalcemic group, 14.4% vs. 5.1%, p < 0.001. Secondary outcomes-multiple transfusions, need for angiography or surgery, and mortality were also increased (9.9% vs. 2.3%, p < 0.001, 5.3% vs. 2.8%, p = 0.03, and 33.3% vs. 24.7%, p < 0.001, respectively). Hypocalcemia was an independent predictor of primary and all the secondary outcomes, except mortality. Hypocalcemia in high-risk hospitalized patients with NV-UGIB is common and independently associated with adverse outcomes. Ca⁺⁺ monitoring in this population may facilitate the rapid identification of high-risk patients. Trials are needed to assess whether correction of hypocalcemia will lead to improved outcomes.

Endotherapy for Nonvariceal Upper Gastrointestinal Hemorrhage

Nonvariceal upper gastrointestinal hemorrhage (NVUGIH) is a common GI emergency with significant morbidity and mortality. Triaging cases on the basis of patient-related factors, restrictive blood transfusion strategy, and hemodynamic stabilization are key initial steps for the management of patients with NVUGIH. Endoscopy remains a vital step for both diagnosis and definitive management. Multiple studies and guidelines have now defined the optimum timing for performing the endoscopy after hospitalization, to better the outcome. Conventional methods for achieving endoscopic hemostasis, such as injection therapy, contact, and noncontact thermal therapy, and mechanical therapy, such as through-the-scope clips, have reported to have 76 to 90% efficacy for primary hemostasis. Newer modalities to enhance hemostasis rates have come in vogue. Many of these modalities, such as cap-mounted clips, coagulation forceps, and hemostatic powders have proved to be efficacious in multiple studies. Thus, the newer modalities are recommended not only for management of persistent bleed and recurrent bleed after failed initial hemostasis, using conventional modalities but also now being advocated for primary hemostasis. Failure of endotherapy would warrant radiological or surgical intervention. Some newer tools to optimize endotherapy, such as endoscopic Doppler probes, for determining flow in visible or underlying vessels in ulcer bleed are now being evaluated. This review is focused on the technical aspects and efficacy of various endoscopic modalities, both conventional and new. A synopsis of the various studies describing and comparing the modalities have been outlined. Postendoscopic management including Helicobacter pylori therapy and starting of anticoagulants and antiplatelets have also been outlined.

ACG Clinical Guideline: Upper Gastrointestinal and Ulcer Bleeding

We performed systematic reviews addressing predefined clinical questions to develop recommendations with the GRADE approach regarding management of patients with overt upper gastrointestinal bleeding. We suggest risk assessment in the emergency department to identify very-low-risk patients (e.g., Glasgow-Blatchford score = 0-1) who may be discharged with outpatient follow-up. For patients hospitalized with upper gastrointestinal bleeding, we suggest red blood cell transfusion at a threshold of 7 g/dL. Erythromycin infusion is suggested before endoscopy, and endoscopy is suggested within 24 hours after presentation. Endoscopic therapy is recommended for ulcers with active spurting or oozing and for nonbleeding visible vessels. Endoscopic therapy with bipolar electrocoagulation, heater probe, and absolute ethanol injection is recommended, and low- to very-low-quality evidence also supports clips, argon plasma coagulation, and soft monopolar electrocoagulation; hemostatic powder spray TC-325 is suggested for actively bleeding ulcers and over-the-scope clips for recurrent ulcer bleeding after previous successful hemostasis. After endoscopic hemostasis, high-dose proton pump inhibitor therapy is recommended continuously or intermittently for 3 days, followed by twice-daily oral proton pump inhibitor for the first 2 weeks of therapy after endoscopy. Repeat endoscopy is suggested for recurrent bleeding, and if endoscopic therapy fails, transcatheter embolization is suggested.

Endoscopic diagnosis and management of nonvariceal upper gastrointestinal hemorrhage (NVUGIH): European Society of Gastrointestinal Endoscopy (ESGE) Guideline - Update 2021

1: ESGE recommends in patients with acute upper gastrointestinal hemorrhage (UGIH) the use of the Glasgow-Blatchford Score (GBS) for pre-endoscopy risk stratification. Patients with GBS ≤ 1 are at very low risk of rebleeding, mortality within 30 days, or needing hospital-based intervention and can be safely managed as outpatients with outpatient endoscopy.Strong recommendation, moderate quality evidence. 2: ESGE recommends that in patients with acute UGIH who are taking low-dose aspirin as monotherapy for secondary cardiovascular prophylaxis, aspirin should not be interrupted. If for any reason it is interrupted, aspirin should be re-started as soon as possible, preferably within 3-5 days.Strong recommendation, moderate quality evidence. 3: ESGE recommends that following hemodynamic resuscitation, early (≤ 24 hours) upper gastrointestinal (GI) endoscopy should be performed. Strong recommendation, high quality evidence. 4: ESGE does not recommend urgent (≤ 12 hours) upper GI endoscopy since as compared to early endoscopy, patient outcomes are not improved. Strong recommendation, high quality evidence. 5: ESGE recommends for patients with actively bleeding ulcers (FIa, FIb), combination therapy using epinephrine injection plus a second hemostasis modality (contact thermal or mechanical therapy). Strong recommendation, high quality evidence. 6: ESGE recommends for patients with an ulcer with a nonbleeding visible vessel (FIIa), contact or noncontact thermal therapy, mechanical therapy, or injection of a sclerosing agent, each as monotherapy or in combination with epinephrine injection. Strong recommendation, high quality evidence. 7 : ESGE suggests that in patients with persistent bleeding refractory to standard hemostasis modalities, the use of a topical hemostatic spray/powder or cap-mounted clip should be considered. Weak recommendation, low quality evidence. 8: ESGE recommends that for patients with clinical evidence of recurrent peptic ulcer hemorrhage, use of a cap-mounted clip should be considered. In the case of failure of this second attempt at endoscopic hemostasis, transcatheter angiographic embolization (TAE) should be considered. Surgery is indicated when TAE is not locally available or after failed TAE. Strong recommendation, moderate quality evidence. 9: ESGE recommends high dose proton pump inhibitor (PPI) therapy for patients who receive endoscopic hemostasis and for patients with FIIb ulcer stigmata (adherent clot) not treated endoscopically. (A): PPI therapy should be administered as an intravenous bolus followed by continuous infusion (e. g., 80 mg then 8 mg/hour) for 72 hours post endoscopy. (B): High dose PPI therapies given as intravenous bolus dosing (twice-daily) or in oral formulation (twice-daily) can be considered as alternative regimens.Strong recommendation, high quality evidence. 10: ESGE recommends that in patients who require ongoing anticoagulation therapy following acute NVUGIH (e. g., peptic ulcer hemorrhage), anticoagulation should be resumed as soon as the bleeding has been controlled, preferably within or soon after 7 days of the bleeding event, based on thromboembolic risk. The rapid onset of action of direct oral anticoagulants (DOACS), as compared to vitamin K antagonists (VKAs), must be considered in this context.Strong recommendation, low quality evidence.

Is Immature Granulocyte Count a Potential Prognostic Marker for Upper Gastrointestinal Tract Bleeding? A New Road to Explore

How to cite this article: Prabu NR, Patil VP. Is Immature Granulocyte Count a Potential Prognostic Marker for Upper Gastrointestinal Tract Bleeding? A New Road to Explore. Indian J Crit Care Med 2020;24(9):750-752.

Comparison of three risk scores to predict outcomes in upper gastrointestinal bleeding; modifying Glasgow-Blatchford with albumin

INTRODUCTION

Management of upper gastrointestinal bleeding (UGIB) is of great importance. In this way, we aimed to evaluate the performance of three well known scoring systems of AIMS65, Glasgow-Blatchford Score (GBS) and Full Rockall Score (FRS) in predicting adverse outcomes in patients with UGIB as well as their ability in identifying low risk patients for outpatient management. We also aimed to assess whether changing albumin cutoff in AIMS65 and addition of albumin to GBS add predictive value to these scores.

METHODS

This was a retrospective study on adult patients who were admitted to Razi hospital (Rasht, Iran) with diagnosis of upper gastrointestinal bleeding between March 21, 2013 and March 21, 2017. Patients who didn't undergo endoscopy or had incomplete medical data were excluded. Initially, we calculated three score systems of AIMS65, GBS and FRS for each patient by using initial Vital signs and lab data. Secondary, we modified AIMS65 and GBS by changing albumin threshold from <3.5 to <3.0 in AIMS65 and addition of albumin to GBS, respectively. Primary outcomes were defined as in hospital mortality, 30-day rebleeding, need for blood transfusion and endoscopic therapy. Secondary outcome was defined as composition of primary outcomes excluding need for blood transfusion. We used AUROC to assess predictive accuracy of risk scores in primary and secondary outcomes. For albumin-GBS model, the AUROC was only calculated for predicting mortality and secondary outcome. The negative predictive value for AIMS65, GBS and modified AIMS65 was then calculated.

RESULT

Of 563 patients, 3% died in hospital, 69.4% needed blood transfusion, 13.1% needed endoscopic therapy and 3% had 30-day rebleeding. The leading cause of UGIB was erosive disease. In predicting composite of adverse outcomes all scores had statistically significant accuracy with highest AUROC for albumin-GBS. However, in predicting in hospital mortality, only albumin-GBS, modified AIMS65 and AIMS65 had acceptable accuracy. Interestingly, albumin, alone, had higher predictive accuracy than other original risk scores. None of the four scores could predict 30-day rebleeding accurately; on the contrary, their accuracy in predicting need for blood transfusion was high enough. The negative predictive value for GBS was 96.6% in score of ≤2 and 85.7% and 90.2% in score of zero in AIMS65 and modified AIMS65, respectively.

CONCLUSION

Neither of risk scores was highly accurate as a prognostic factor in our population; however, modified AIMS65 and albumin-GBS may be optimal choice in evaluating risk of mortality and general assessment. In identifying patient for safe discharge, GBS ≤ 2 seemed to be advisable choice.

British Society of Gastroenterology (BSG)-led multisociety consensus care bundle for the early clinical management of acute upper gastrointestinal bleeding

Medical care bundles improve standards of care and patient outcomes. Acute upper gastrointestinal bleeding (AUGIB) is a common medical emergency which has been consistently associated with suboptimal care. We aimed to develop a multisociety care bundle centred on the early management of AUGIB. Commissioned by the British Society of Gastroenterology (BSG), a UK multisociety task force was assembled to produce an evidence-based and consensus-based care bundle detailing key interventions to be performed within 24 hours of presentation with AUGIB. A modified Delphi process was conducted with stakeholder representation from BSG, Association of Upper Gastrointestinal Surgeons, Society for Acute Medicine and the National Blood Transfusion Service of the UK. A formal literature search was conducted and international AUGIB guidelines reviewed. Evidence was appraised using the Grading of Recommendations, Assessment, Development and Evaluation tool and statements were formulated and subjected to anonymous electronic voting to achieve consensus. Accepted statements were eligible for incorporation into the final bundle after a separate round of voting. The final version of the care bundle was reviewed by the BSG Clinical Services and Standards Committee and approved by all stakeholder groups. Consensus was reached on 19 statements; these culminated in 14 corresponding care bundle items, contained within 6 management domains: Recognition, Resuscitation, Risk assessment, Rx (Treatment), Refer and Review. A multisociety care bundle for AUGIB has been developed to facilitate timely delivery of evidence-based interventions and drive quality improvement and patient outcomes in AUGIB.

Validation of a Machine Learning Model That Outperforms Clinical Risk Scoring Systems for Upper Gastrointestinal Bleeding

BACKGROUND & AIMS

Scoring systems are suboptimal for determining risk in patients with upper gastrointestinal bleeding (UGIB); these might be improved by a machine learning model. We used machine learning to develop a model to calculate the risk of hospital-based intervention or death in patients with UGIB and compared its performance with other scoring systems.

METHODS

We analyzed data collected from consecutive unselected patients with UGIB from medical centers in 4 countries (the United States, Scotland, England, and Denmark; n = 1958) from March 2014 through March 2015. We used the data to derive and internally validate a gradient-boosting machine learning model to identify patients who met a composite endpoint of hospital-based intervention (transfusion or hemostatic intervention) or death within 30 days. We compared the performance of the machine learning prediction model with validated pre-endoscopic clinical risk scoring systems (the Glasgow-Blatchford score [GBS], admission Rockall score, and AIMS65). We externally validated the machine learning model using data from 2 Asia-Pacific sites (Singapore and New Zealand; n = 399). Performance was measured by area under receiver operating characteristic curve (AUC) analysis.

RESULTS

The machine learning model identified patients who met the composite endpoint with an AUC of 0.91 in the internal validation set; the clinical scoring systems identified patients who met the composite endpoint with AUC values of 0.88 for the GBS (P = .001), 0.73 for Rockall score (P < .001), and 0.78 for AIMS65 score (P < .001). In the external validation cohort, the machine learning model identified patients who met the composite endpoint with an AUC of 0.90, the GBS with an AUC of 0.87 (P = .004), the Rockall score with an AUC of 0.66 (P < .001), and the AIMS65 with an AUC of 0.64 (P < .001). At cutoff scores at which the machine learning model and GBS identified patients who met the composite endpoint with 100% sensitivity, the specificity values were 26% with the machine learning model versus 12% with GBS (P < .001).

CONCLUSIONS

We developed a machine learning model that identifies patients with UGIB who met a composite endpoint of hospital-based intervention or death within 30 days with a greater AUC and higher levels of specificity, at 100% sensitivity, than validated clinical risk scoring systems. This model could increase identification of low-risk patients who can be safely discharged from the emergency department for outpatient management.

Management of Nonvariceal Upper Gastrointestinal Bleeding: Guideline Recommendations From the International Consensus Group

DESCRIPTION

This update of the 2010 International Consensus Recommendations on the Management of Patients With Nonvariceal Upper Gastrointestinal Bleeding (UGIB) refines previous important statements and presents new clinically relevant recommendations.

METHODS

An international multidisciplinary group of experts developed the recommendations. Data sources included evidence summarized in previous recommendations, as well as systematic reviews and trials identified from a series of literature searches of several electronic bibliographic databases from inception to April 2018. Using an iterative process, group members formulated key questions. Two methodologists prepared evidence profiles and assessed quality (certainty) of evidence relevant to the key questions according to the GRADE (Grading of Recommendations Assessment, Development and Evaluation) approach. Group members reviewed the evidence profiles and, using a consensus process, voted on recommendations and determined the strength of recommendations as strong or conditional.

RECOMMENDATIONS

Preendoscopic management: The group suggests using a Glasgow Blatchford score of 1 or less to identify patients at very low risk for rebleeding, who may not require hospitalization. In patients without cardiovascular disease, the suggested hemoglobin threshold for blood transfusion is less than 80 g/L, with a higher threshold for those with cardiovascular disease. Endoscopic management: The group suggests that patients with acute UGIB undergo endoscopy within 24 hours of presentation. Thermocoagulation and sclerosant injection are recommended, and clips are suggested, for endoscopic therapy in patients with high-risk stigmata. Use of TC-325 (hemostatic powder) was suggested as temporizing therapy, but not as sole treatment, in patients with actively bleeding ulcers. Pharmacologic management: The group recommends that patients with bleeding ulcers with high-risk stigmata who have had successful endoscopic therapy receive high-dose proton-pump inhibitor (PPI) therapy (intravenous loading dose followed by continuous infusion) for 3 days. For these high-risk patients, continued oral PPI therapy is suggested twice daily through 14 days, then once daily for a total duration that depends on the nature of the bleeding lesion. Secondary prophylaxis: The group suggests PPI therapy for patients with previous ulcer bleeding who require antiplatelet or anticoagulant therapy for cardiovascular prophylaxis.

Clinical utility of pre-endoscopy risk scores in upper gastrointestinal bleeding

Introduction: Acute upper-gastrointestinal bleeding (AUGIB) is a common medical emergency, with an incidence of 103-172 per 100,000 in the United Kingdom (UK) and mortality of 2% to 10%. Early and accurate prediction of the severity of an AUGIB episode may help guide management, including in or outpatient management, level of care required, and timing of endoscopy. This article aims to address the clinical utility of the various pre-endoscopic risk assessment tools used in AUGIB.Areas covered: The authors undertook a literature review of the current evidence on the pre-endoscopic risk assessment scores. Additional the authors discuss the recently published novel risk assessment scores.Expert opinion: The evidence shows that GBS is the most clinically useful risk assessment score in correctly identifying very low-risk patients suitable for outpatient management. At present, research is ongoing to assess machine learning in the assessment of patients presenting with AUGIB. More research is needed but it shows promise for the future.

Validation of a Machine Learning Model That Outperforms Clinical Risk Scoring Systems for Upper Gastrointestinal Bleeding

BACKGROUND & AIMS

Scoring systems are suboptimal for determining risk in patients with upper gastrointestinal bleeding (UGIB); these might be improved by a machine learning model. We used machine learning to develop a model to calculate the risk of hospital-based intervention or death in patients with UGIB and compared its performance with other scoring systems.

METHODS

We analyzed data collected from consecutive unselected patients with UGIB from medical centers in 4 countries (the United States, Scotland, England, and Denmark; n = 1958) from March 2014 through March 2015. We used the data to derive and internally validate a gradient-boosting machine learning model to identify patients who met a composite endpoint of hospital-based intervention (transfusion or hemostatic intervention) or death within 30 days. We compared the performance of the machine learning prediction model with validated pre-endoscopic clinical risk scoring systems (the Glasgow-Blatchford score [GBS], admission Rockall score, and AIMS65). We externally validated the machine learning model using data from 2 Asia-Pacific sites (Singapore and New Zealand; n = 399). Performance was measured by area under receiver operating characteristic curve (AUC) analysis.

RESULTS

The machine learning model identified patients who met the composite endpoint with an AUC of 0.91 in the internal validation set; the clinical scoring systems identified patients who met the composite endpoint with AUC values of 0.88 for the GBS (P = .001), 0.73 for Rockall score (P < .001), and 0.78 for AIMS65 score (P < .001). In the external validation cohort, the machine learning model identified patients who met the composite endpoint with an AUC of 0.90, the GBS with an AUC of 0.87 (P = .004), the Rockall score with an AUC of 0.66 (P < .001), and the AIMS65 with an AUC of 0.64 (P < .001). At cutoff scores at which the machine learning model and GBS identified patients who met the composite endpoint with 100% sensitivity, the specificity values were 26% with the machine learning model versus 12% with GBS (P < .001).

CONCLUSIONS

We developed a machine learning model that identifies patients with UGIB who met a composite endpoint of hospital-based intervention or death within 30 days with a greater AUC and higher levels of specificity, at 100% sensitivity, than validated clinical risk scoring systems. This model could increase identification of low-risk patients who can be safely discharged from the emergency department for outpatient management.

AIMS65 scoring system is comparable to Glasgow-Blatchford score or Rockall score for prediction of clinical outcomes for non-variceal upper gastrointestinal bleeding

Background

Risk stratification for patients with nonvariceal upper gastrointestinal (NVUGI) bleeding is crucial for successful prognosis and treatment. Recently, the AIMS65 score has been used to predict mortality risk and rebleeding. The purpose of this study was to compare the performance of the AIMS65 score with the Glasgow-Blatchford score (GBS), Rockall score, and pre-endoscopic Rockall score in Korea.

Methods

We retrospectively studied 512 patients with NVUGI bleeding who were treated at a university hospital between 2013 and 2016. The AIMS65, GBS, Rockall score, and pre-endoscopic Rockall score were used to stratify patients based on their bleeding risk. The primary outcome was in-hospital mortality. The secondary outcomes were composite clinical outcomes of mortality, rebleeding, and intensive care unit (ICU) admission. Each scoring system was compared using the receiver-operating curve (ROC).

Results

A total of 17 patients (3.3%) died and rebleeding developed in 65 patients (12.7%). Eighty-six patients (16.8%) required ICU admission. The AIMS65 (area under the curve (AUC) 0.84, 95% confidence interval, 0.81–0.88)) seemed to be superior to the GBS (AUC 0.72, 0.68–0.76), the Rockall score (AUC 0.75, 0.71–0.79), or the pre-endoscopic Rockall score (AUC 0.74, 0.70–0.78) in predicting in-hospital mortality, but there was not a statistically significant difference between the groups (P = 0.07). The AUC value of the AIMS65 was not significantly different from the other scoring systems in prediction of rebleeding, endoscopic intervention, or ICU admission.

Conclusions

The AIMS65 score in NVUGI bleeding patients was comparable to the GBS or Rockall scoring systems when predicting the mortality, rebleeding, or ICU admission. Because AIMS65 is a much easier, readily calculated scoring system compared to the others, we would recommend using the AIMS65 in daily practice.

Management of acute upper gastrointestinal bleeding

Upper gastrointestinal bleeding (UGIB) is a common medical emergency, with a reported mortality of 2-10%. Patients identified as being at very low risk of either needing an intervention or death can be managed as outpatients. For all other patients, intravenous fluids as needed for resuscitation and red cell transfusion at a hemoglobin threshold of 70-80 g/L are recommended. After resuscitation is initiated, proton pump inhibitors (PPIs) and the prokinetic agent erythromycin may be administered, with antibiotics and vasoactive drugs recommended in patients who have cirrhosis. Endoscopy should be undertaken within 24 hours, with earlier endoscopy considered after resuscitation in patients at high risk, such as those with hemodynamic instability. Endoscopic treatment is used for variceal bleeding (for example, ligation for esophageal varices and tissue glue for gastric varices) and for high risk non-variceal bleeding (for example, injection, thermal probes, or clips for lesions with active bleeding or non-bleeding visible vessel). Patients who require endoscopic therapy for ulcer bleeding should receive high dose proton pump inhibitors after endoscopy, whereas those who have variceal bleeding should continue taking antibiotics and vasoactive drugs. Recurrent ulcer bleeding is treated with repeat endoscopic therapy, with subsequent bleeding managed by interventional radiology or surgery. Recurrent variceal bleeding is generally treated with transjugular intrahepatic portosystemic shunt. In patients who require antithrombotic agents, outcomes appear to be better when these drugs are reintroduced early.

Asia-Pacific working group consensus on non-variceal upper gastrointestinal bleeding: an update 2018

Non-variceal upper gastrointestinal bleeding remains an important emergency condition, leading to significant morbidity and mortality. As endoscopic therapy is the 'gold standard' of management, treatment of these patients can be considered in three stages: pre-endoscopic treatment, endoscopic haemostasis and post-endoscopic management. Since publication of the Asia-Pacific consensus on non-variceal upper gastrointestinal bleeding (NVUGIB) 7 years ago, there have been significant advancements in the clinical management of patients in all three stages. These include pre-endoscopy risk stratification scores, blood and platelet transfusion, use of proton pump inhibitors; during endoscopy new haemostasis techniques (haemostatic powder spray and over-the-scope clips); and post-endoscopy management by second-look endoscopy and medication strategies. Emerging techniques, including capsule endoscopy and Doppler endoscopic probe in assessing adequacy of endoscopic therapy, and the pre-emptive use of angiographic embolisation, are attracting new attention. An emerging problem is the increasing use of dual antiplatelet agents and direct oral anticoagulants in patients with cardiac and cerebrovascular diseases. Guidelines on the discontinuation and then resumption of these agents in patients presenting with NVUGIB are very much needed. The Asia-Pacific Working Group examined recent evidence and recommends practical management guidelines in this updated consensus statement.

Validity of the Pre-endoscopic Scoring Systems for the Prediction of the Failure of Endoscopic Hemostasis in Bleeding Gastroduodenal Peptic Ulcers

Objective Although several pre-endoscopic scoring systems have been used to predict the mortality or the need for intervention for upper gastrointestinal bleeding, their usefulness to predict the failure of endoscopic hemostasis in bleeding gastroduodenal peptic ulcers has not yet been fully investigated. In this study, we evaluated the usefulness of the Glasgow-Blatchford score (GBS), the clinical Rockall score (CRS), and the AIMS65 score in predicting the failure of endoscopic hemostasis in patients with bleeding gastroduodenal peptic ulcers. Methods We retrospectively evaluated 226 consecutive emergency endoscopic cases with bleeding gastroduodenal peptic ulcers between April 2010 and September 2016. The study outcome was the failure of first endoscopic hemostasis. The GBS, CRS, and AIMS65 scores were assessed for their ability to predict the failure of endoscopic hemostasis using a receiver-operating characteristic curve. Results Eight cases (3.5%) failed to achieve first endoscopic hemostasis. Surgery was required in six cases, and interventional radiology was required in two cases. The GBS was superior to both the CRS and the AIMS65 score in predicting the failure of endoscopic hemostasis [area under the curve, 0.77 (95% confidence interval, 0.64-0.90), 0.65 (0.56-0.74) and 0.75 (0.56-0.95), respectively]. No failure of endoscopic hemostasis was noted in cases in which the patient scored less than GBS 10 and CRS 2. Conclusion The GBS was the most useful scoring system for the prediction of failure of endoscopic hemostasis in patients with bleeding gastroduodenal peptic ulcers. The GBS was also useful in identifying the patients who did not require surgery or interventional radiology.