A Review of Risk Scores within Upper Gastrointestinal Bleeding

Development and validation of a machine learning model to predict hemostatic intervention in patients with acute upper gastrointestinal bleeding

BACKGROUND

Acute upper gastrointestinal bleeding (UGIB) is common in clinical practice and has a wide range of severity. Along with medical therapy, endoscopic intervention is the mainstay treatment for hemostasis in high-risk rebleeding lesions. Predicting the need for endoscopic intervention would be beneficial in resource-limited areas for selective referral to an endoscopic center. The proposed risk stratification scores had limited accuracy. We developed a machine learning model to predict the need for endoscopic intervention in patients with acute UGIB.

METHODS

A prospectively collected database of UGIB patients from 2011 to 2020 was retrospectively reviewed. Patients older than 18 years diagnosed with UGIB who underwent endoscopy were included. Data comprised demographic characteristics, clinical presentation, and laboratory parameters. The cleaned data was used for model development and validation in Python. We conducted 80%-20% split sample training and test sets. The training set was used for supervised learning of 15 models using a stratified 5-fold cross-validation process. The model with the highest AUROC was then internally validated with the test set to evaluate performance.

RESULTS

Of 1389 patients, 615 (44.3%) of the cohorts received the endoscopic intervention (293 variceal- and 336 nonvariceal-bleeding interventions). Eighteen features, including demographic characteristics, clinical presentation, and laboratory parameters, were selected as input for 15 machine learning models. The result revealed that the linear discriminant analysis model could achieve the highest AUROC of 0.74 to predict endoscopic intervention. The model was validated with the test set, in which the AUROC was increased from 0.74 to 0.81. Finally, the model was deployed as a web application by Streamlit.

CONCLUSIONS

Our machine learning model can identify patients with acute UGIB who need endoscopic intervention with good performance. This may help primary care physicians prioritize patients who need referrals and optimize resource allocation in resource-limited areas. Further development and identification of more specific features might improve prediction performance.

TRIAL REGISTRATION

None (Retrospective cohort study) PATIENT & PUBLIC INVOLVEMENT: None.

The role of shock indexes and RDW/albumin ratio in upper gastrointestinal bleeding : Predicting adverse outcomes

OBJECTIVE

Upper gastrointestinal bleeding (UGIB) is a common condition in emergency departments (ED). The aim of this study is to evaluate the effectiveness of the red blood cell distribution width (RDW) to albumin ratio and three types of shock index (SI) as predictors of adverse outcomes in patients with UGIB in the ED.

METHODS

The study was designed as a retrospective, single-center study, and patients were screened using electronic medical records. Glasgow Blatchford, RDW/albumin ratio, SI, modified SI (MSI), and age SI were calculated, and adverse outcomes were defined as ICU admission, red blood cell transfusion, in-hospital mortality, and 30-day mortality. The effectiveness of these parameters in predicting adverse outcomes in UGIB patients admitted to the ED was evaluated.

RESULTS

The study enrolled 174 patients, of whom 17.2% required admission to the ICU, 33.9% received red blood cell transfusions, and 10.3% died within 30 days. Patients with adverse outcomes had significantly higher SI, MSI, age SI, and RDW/albumin ratio values. All four indices were statistically significant predictors of adverse outcomes (area under the curve [AUC] SI: 0.676; AUC MSI: 0.706; AUC age SI: 0.778; AUC RDW/albumin: 0.787). Age SI showed significantly higher prognostic performance in predicting adverse outcomes than SI and MSI.

CONCLUSION

The present study suggests that SI, MSI, age SI, and RDW/albumin ratio may be useful in predicting adverse outcomes in patients with UGIB. The RDW/albumin ratio was effective in predicting mortality, while age SI showed a higher predictive ability for adverse outcomes compared to SI and MSI.

Clinical Epidemiology, Etiology, and Outcomes of Upper Gastrointestinal Bleeding at a Tertiary Center in Bahrain: A Retrospective Study

Background Upper gastrointestinal bleeding (UGIB) is one of the most common major medical emergencies. This study sought to determine the epidemiology, clinical characteristics, and outcomes of UGIB in the largest major tertiary care center in Bahrain, compared to regional and international cohorts. Methods We conducted a retrospective cohort study of all patients diagnosed with UGIB between April 2021 and April 2022 in Salmaniya Medical Complex, Bahrain's largest tertiary-level public hospital. The primary outcomes measured included 30-day mortality rates and one-year readmission rates. Other variables collected included demographic factors, baseline characteristics, comorbidities, symptomatology, endoscopic findings, and etiologies of the bleeding. Results A total of 212 patients with UGIB were included. The mean age of the patients was 56.7 ± 19.1 years. More than 50% of patients with UGIB presented with melena and symptoms of anemia. The most common cause of UGIB in Bahrain was duodenal ulcers, which were found in 75 patients (37.7%). One in two patients with UGIB required packed red blood cells, while fresh-frozen plasma and platelet transfusions were reserved for severe cases. The readmission rate within one year of discharge (14.2%) was associated with smoking, cardiac history, melena, gastric malignancy, and rescope during admission. The 30-day mortality (15.6%) was associated with comorbidities of chronic kidney disease, cerebrovascular disease, and hematochezia on presentation. Conclusion Overall, the mortality rate of UGIB in Bahrain is higher than in countries in the region, the UK, and the US, signaling potential gaps in management and a reflection of a more complex patient population.

Importance of risk assessment, endoscopic hemostasis, and recent advancements in the management of acute non-variceal upper gastrointestinal bleeding

Acute non-variceal upper gastrointestinal bleeding (ANVUGIB) is a common medical emergency in clinical practice. While the incidence has significantly reduced, the mortality rates have not undergone a similar reduction in the last few decades, thus presenting a significant challenge. This editorial outlines the key causes and risk factors of ANVUGIB and explores the current standards and recent updates in risk assessment scoring systems for predicting mortality and endoscopic treatments for achieving hemostasis. Since ANUVGIB predominantly affects the elderly population, the impact of comorbidities may be responsible for the poor outcomes. A thorough drug history is important due to the increasing use of antiplatelet agents and anticoagulants in the elderly. Early risk stratification plays a crucial role in deciding the line of management and predicting mortality. Emerging scoring systems such as the ABC (age, blood tests, co-morbidities) score show promise in predicting mortality and guiding clinical decisions. While conventional endoscopic therapies remain cornerstone approaches, novel techniques like hemostatic powders and over-the-scope clips offer promising alternatives, particularly in cases refractory to traditional modalities. By integrating validated scoring systems and leveraging novel therapeutic modalities, clinicians can enhance patient care and mitigate the substantial morbidity and mortality associated with ANVUGIB.

Neutrophil-lymphocyte ratio predict outcome of upper gastrointestinal bleeding in emergency

Background

The neutrophil-lymphocyte ratio (NLR) is a simple marker of systemic inflammatory responses. The present study aims to evaluate the prognostic significance of the NLR on admission day in predicting outcomes for patients with upper gastrointestinal bleeding (UGIB), which is a prevalent medical emergency.

Methods

726 patients who were admitted to our clinic between January 2019 and December 2022 diagnosed with UGIB, and who underwent necessary examinations, were included in the study. The patients' Glasgow-Blatchford Score (GBS), Full Rockall Score (FRS), and NLR levels were calculated at the first admission. Outcomes were defined as in-hospital mortality, need for blood transfusion, surgical treatment and endoscopic therapy. Patients were categorized into four groups using NLR quartile levels to compare their clinical characteristics, Glasgow Blatchford Score, Full Rockall Score levels, and prognosis. Secondary, we modified FRS and GBS by adding NLR, respectively. We used area under the receiver operating characteristic curve (AUROC) to assess the accuracy of risk prediction for NLR, NLR-GBS, and NLR-FRS improved models.

Results

Of 726 patients, 6% died in hospital, 23.9% received endoscopic interventon, 4.8% received surgical treatment, and 46.4% received transfusion therapy. Multifactorial logistic regression showed that a high level of NLR was a risk factor for death in patients with UGIB (p = 0.028). NLR, GBS, FRS, NLR-GBS, and NLR-FRS have sufficient accuracy in predicting inpatient mortality, endoscopic treatment, and transfusion treatment, and the differences are statistically significant (p < 0.05). In the comprehensive prediction of adverse outcomes, NLR-GBS has the highest AUROC, and in predicting inpatient mortality, NLR-FRS has the highest AUROC.

Conclusion

For UGIB patients, a high NLR was strongly associated with high risk UGIB. Combined testing with the GBS and FRS can achieve good predictive results, which is valuable in guiding the pre-screening and triage of emergency nursing care and clinical treatment to ensure that patients receive rapid and effective treatment and improve the quality of care.

Validating the CHAMPS Score: A Novel and Reliable Prognostic Score of Non-Variceal Upper Gastrointestinal Bleeding

Introduction

The Charlson Comorbidity Index ≥2, in-Hospital onset, Albumin <2.5 g/dL, altered Mental status, Eastern Cooperative Oncology Group Performance status ≥2, Steroid use (CHAMPS) score is a novel and promising prognostic tool. We present an initial external validation of the CHAMPS score for predicting mortality in acute nonvariceal upper gastrointestinal bleeding (NVUGIB) across multiple clinical outcomes.

Methods

A prospective cohort study was conducted on adult patients with NVUGIB admitted to the Department of Gastroenterology between November 2022 and June 2023. The CHAMPS score performance in predicting in-hospital outcomes was evaluated by employing area under the receiver operating characteristic (AUROC) curves, followed by a comparative analysis with five pre-existing scores.

Results

A total of 140 patients were included in the study. The CHAMPS score showed its highest performance in predicting mortality rates (AUROC = 0.89), significantly outperforming the Glasgow-Blatchford Bleeding Score (GBS) as well as the Albumin level <3.0 mg/dL, International normalized ratio >1.5, altered Mental status, Systolic blood pressure ≤90 mmHg, and age >65 years (AIMS65) score (AUROC = 0.72 and 0.71, respectively; all p < 0.05). Subgroup analysis for bleeding-related and non-bleeding-related mortality further confirmed the robust predictive capability of the CHAMPS score (AUROC = 0.88 and 0.87, respectively). The CHAMPS score failed to predict rebleeding and intervention reliably, exhibiting AUROC values of 0.43 and 0.55, respectively. The optimal CHAMPS score cutoff value for predicting mortality was 3 points, achieving 100% sensitivity and 71.2% specificity. In the low-risk category defined by both CHAMPS and GBS scores, mortality and rebleeding rates were 0%. However, within the CHAMPS score-based low-risk group, 58.8% required intervention, contrasting with a 0% intervention rate for the GBS score-based low-risk group (GBS score ≤1).

Conclusion

The CHAMPS score consistently demonstrated a robust predictive performance for mortality (AUROC > 0.8), facilitating the identification of high-risk patients requiring aggressive treatment and low-risk patients in need of localized treatment or safe discharge after successful bleeding control.