Derivation and validation of Re.Co.De death score risk in patients with acute nonvariceal upper GI bleeding

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.

The interaction of patients' physical status and time to endoscopy on mortality risk in patients with upper gastrointestinal bleeding: A national prospective cohort study

BACKGROUND AND AIM

The correct time to perform an upper endoscopy is decisive in acutely GI bleeding patients. However, patients' physical status may affect mortality. We speculated that the physical status and procedural time could be the principal factors accountable for death-risk. The primary aim was to verify the interaction between physical status and time to endoscopy on mortality; the secondary aim was to verify the interaction of the physical status and time to endoscopy on the length of stay (LOS).

METHODS

Consecutive patients admitted to 50 Italian hospitals were included. Clinical and endoscopic data were recorded. A multiple logistic regression analysis was performed and the interaction of adjusted clinical physical status and time to endoscopy on mortality was calculated.

RESULTS

Complete data were available for 3.190 patients. The time frames did not interfere with outcomes but influenced LOS. Conversely, the ASA score correlated with mortality, LOS, need for transfusions and rebleeding risk.

CONCLUSION

Endoscopy time should be tailored to the patient's physical. In our experience, ASA 1-2-3 patients can be safely submitted to endoscopy to reduce the LOS; on the contrary, keen attention should be paid to ASA4 patients, following the 'not too early-not too late' rule (12-24 h from admission).

Review article: Upper gastrointestinal bleeding - review of current evidence and implications for management

BACKGROUND

Acute upper gastrointestinal bleeding (UGIB) is a common emergency requiring hospital-based care. Advances in care across pre-endoscopic, endoscopic and post-endoscopic phases have led to improvements in clinical outcomes.

AIMS

To provide a detailed, evidence-based update on major aspects of care across pre-endoscopic, endoscopic and post-endoscopic phases.

METHODS

We performed a structured bibliographic database search for each topic. If a recent high-quality meta-analysis was not available, we performed a meta-analysis with random effects methods and odds ratios with 95% confidence intervals.

RESULTS

Pre-endoscopic management of UGIB includes risk stratification, a restrictive red blood cell transfusion policy unless the patient has cardiovascular disease, and pharmacologic therapy with erythromycin and a proton pump inhibitor. Patients with cirrhosis should be treated with prophylactic antibiotics and vasoactive medications. Tranexamic acid should not be used. Endoscopic management of UGIB depends on the aetiology. For peptic ulcer disease (PUD) with high-risk stigmata, endoscopic therapy, including over-the-scope clips (OTSCs) and TC-325 powder spray, should be performed. For variceal bleeding, treatment should be customised by severity and anatomic location. Post-endoscopic management includes early enteral feeding for all UGIB patients. For high-risk PUD, PPI should be continued for 72 h, and rebleeding should initially be evaluated with a repeat endoscopy. For variceal bleeding, high-risk patients or those with further bleeding, a transjugular intrahepatic portosystemic shunt can be considered.

CONCLUSIONS

Management of acute UGIB should include treatment plans for pre-endoscopic, endoscopic and post-endoscopic phases of care, and customise treatment decisions based on aetiology and severity of bleeding.

Clinical characteristics of acute non-varicose upper gastrointestinal bleeding and the effect of endoscopic hemostasis

BACKGROUND

Acute non-variceal upper gastrointestinal bleeding (ANVUGIB) constitutes a prevalent emergency within Gastroenterology, encompassing 80%-90% of all gastrointestinal hemorrhage incidents. This condition is distinguished by its abrupt onset, swift progression, and notably elevated mortality rate.

AIM

To gather clinical data from patients with ANVUGIB at our hospital in order to elucidate the clinical characteristics specific to our institution and analyze the therapeutic effectiveness of endoscopic hemostasis.

METHODS

We retrospectively retrieved the records of 532 patients diagnosed with ANVUGIB by endoscopy at our hospital between March 2021 and March 2023, utilizing our medical record system. Data pertaining to general patient information, etiological factors, disease outcomes, and other relevant variables were meticulously collected and analyzed.

RESULTS

Among the 532 patients diagnosed with ANVUGIB, the male-to-female ratio was 2.91:1, with a higher prevalence among males. Notably, 43.6% of patients presented with black stool as their primary complaint, while 27.4% had hematemesis as their initial symptom. Upon admission, 17% of patients exhibited both hematemesis and black stool, while most ANVUGIB patients primarily complained of overt gastrointestinal bleeding. Urgent routine blood examinations at admission revealed that 75.8% of patients had anemia, with 63.4% experiencing moderate to severe anemia, and 1.5% having extremely severe anemia (hemoglobin < 30 g/L). With regard to etiology, 53.2% of patients experienced bleeding without a definitive trigger, 24.2% had a history of using gastric mucosa-irritating medications, 24.2% developed bleeding after alcohol consumption, 2.8% attributed it to improper diet, 1.7% to emotional excitement, and 2.3% to fatigue preceding the bleeding episode. Drug-induced ANVUGIB was more prevalent in the elderly than middle-aged and young individuals, while bleeding due to alcohol consumption showed the opposite trend. Additionally, diet-related bleeding was more common among the young age group compared to the middle-aged group. Gastrointestinal endoscopy identified peptic ulcers as the most frequent cause of ANVUGIB (73.3%), followed by gastrointestinal malignancies (10.9%), acute gastric mucous lesions (9.8%), and androgenic upper gastrointestinal bleeding (1.5%) among inpatients with ANVUGIB. Of the 532 patients with gastrointestinal bleeding, 68 underwent endoscopic hemostasis, resulting in an endoscopic treatment rate of 12.8%, with a high immediate hemostasis success rate of 94.1%.

CONCLUSION

ANVUGIB patients exhibit diverse characteristics across different age groups, and endoscopic hemostatic treatments have demonstrated remarkable efficacy.