Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A Clustering-Based Machine Learning Approach for Mortality Prediction in Gastrointestinal Bleeding: Development and

Laith Alomari1, Zaid Al-Fakhouri2, Jaber Jaradat3

  • 1Department of Medicine, Jefferson Einstein Philadelphia Hospital, Philadelphia, Pennsylvania.

Gastro Hep Advances
|May 28, 2026
PubMed
Summary

Related Concept Videos

Kaplan-Meier Approach01:24

Kaplan-Meier Approach

The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Precision for all children: embedding equity into precision medicine for children.

BMJ paediatrics open·2026
Same author

Pulmonary vasodilator therapy in COPD-associated pulmonary hypertension: A real-world case series of 14 patients confirmed by right heart catheterization.

Respiratory medicine case reports·2026
Same author

Prevalence, Characteristics, and Outcomes Associated With Early Vasculopathy in Patients With Chronic Lung Disease Undergoing Right Heart Catheterization.

Pulmonary circulation·2026
Same author

Short-Term Daily Vonoprazan Treatment Is More Commonly Associated With Infectious Gastroenteritis Than Short-Term Daily PPI Treatment.

Neurogastroenterology and motility·2026
Same author

Trends in Incidence and Prevalence of Acute Pancreatitis in the United States: A Population-Based Analysis from 1995 to 2024.

Digestive diseases and sciences·2026
Same author

Behind the Procedure: Understanding Complications in Anterior Cervical Surgery.

Cureus·2026
Same journal

Swallowing the Future of Cancer Prevention: Could EsoGuard Revolutionize the Fight Against Esophageal Cancer?

Gastro hep advances·2026
Same journal

Erratum.

Gastro hep advances·2026
Same journal

Duodenal Fluid Microbiome Diversity and Pancreatic Cyst Status Among Patients Undergoing Pancreatic Surveillance.

Gastro hep advances·2026
Same journal

A Compelling Mimic: Fish Mouth Major Papilla and Villous Biliary Mucosa on Cholangioscopy.

Gastro hep advances·2026
Same journal

Cribriform Constriction: An Exceedingly Rare Cause of Progressive Dysphagia.

Gastro hep advances·2026
Same journal

Implications of Liver Failure Cutoffs for Mortality Prediction in Hospitalized Cirrhosis Patients: A Multicentric Study.

Gastro hep advances·2026
See all related articles
This summary is machine-generated.

A new machine learning model accurately predicts 30-day mortality in gastrointestinal bleeding (GIB) patients, outperforming traditional scores. This tool offers improved risk stratification for GIB emergencies.

Area of Science:

  • Medical Informatics
  • Clinical Prediction Models
  • Machine Learning in Healthcare

Background:

  • Gastrointestinal bleeding (GIB) presents a significant clinical challenge with high morbidity and mortality.
  • Existing risk scores (AIMS65, GBS) have limitations in capturing complex patient data.
  • There is a need for more accurate predictive tools for GIB patient outcomes.

Purpose of the Study:

  • To develop and validate a machine learning model for predicting 30-day mortality in patients with GIB.
  • To compare the performance of the novel model against established risk scores.

Main Methods:

  • Retrospective analysis of 5453 GIB patients from MIMIC-IV-ED for model development.
  • External validation using 7166 GIB patients from Jefferson Health.
Keywords:
Ensemble ModelGastrointestinal BleedingMachine LearningMortality PredictionRisk Stratification

Related Experiment Videos

  • Development of random forest models on clustered patient data, incorporating 16 clinical variables.

    • Main Results:

    • The machine learning model achieved an AUC of 0.884 (internal) and 0.882 (external validation).
    • The model significantly outperformed AIMS65 (AUC 0.737) and GBS (AUC 0.768).
    • Key predictors included age, albumin, hemodynamic parameters, hemoglobin, and platelet count.

    Conclusions:

    • The developed machine learning model offers superior risk stratification for 30-day mortality in GIB.
    • The model demonstrates generalizability and potential for integration into electronic health records.
    • This tool can aid clinicians in managing GIB patients more effectively.