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 Video

Updated: Dec 23, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K

Explainable Machine Learning Model for Predicting GI Bleed Mortality in the Intensive Care Unit.

Farah Deshmukh1, Shamel S Merchant2

  • 1Department of Internal Medicine, Bassett Medical Center and Columbia University College of Physicians and Surgeons, New York, New York, USA.

The American Journal of Gastroenterology
|April 29, 2020
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Atrial fibrillation in patients with alcohol-associated hepatitis leads to increased mortality.

European journal of gastroenterology & hepatology·2026
Same author

Trends and Disparities in Obesity-Related Mortality Among U.S. Adults: A CDC WONDER Analysis (1968-2025).

Obesity science & practice·2026
Same author

Line-Field Confocal Optical Coherence Tomography for the Diagnosis of Skin Tumors: A Systematic Review and Meta-Analysis.

Diagnostics (Basel, Switzerland)·2024
Same author

Gastroduodenal Fistula: A Rare Finding With an Atypical Presentation.

Gastroenterology research·2020
Same author

<i>Clostridioides difficile</i> co-infection with Enterohemorrhagic <i>Escherichia coli</i> (EHEC)-a potentially fatal combination.

IDCases·2020
Same author

Pulmonary Manifestations in Adolescents With Inflammatory Bowel Disease.

Clinical pediatrics·2020

A new machine learning (ML) model accurately predicts mortality risk in intensive care unit patients with gastrointestinal (GI) bleeds. This explainable ML model outperforms the APACHE IVa score, offering better insights for clinical decision-making.

Area of Science:

  • Medical Informatics
  • Critical Care Medicine
  • Machine Learning Applications

Background:

  • Acute gastrointestinal (GI) bleeds are a significant cause of hospitalization with a notable mortality risk.
  • Current risk stratification scores may not fully capture mortality risk in intensive care unit (ICU) patients with GI bleeds.

Purpose of the Study:

  • To develop and validate a machine learning (ML) model for predicting mortality in ICU patients admitted for GI bleeds.
  • To compare the predictive performance of the ML model against the established APACHE IVa risk score.
  • To utilize explainable ML methods for understanding model predictions.

Main Methods:

  • Analysis of 5,691 patient records from the Electronic Intensive Care Unit Collaborative Research Database.
  • Development of an ML model trained to identify ICU mortality in GI bleed patients.

More Related Videos

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.4K

Related Experiment Videos

Last Updated: Dec 23, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.4K
  • Performance evaluation using Area Under the Receiver Operating Characteristic Curve (AUC) analysis and comparison with APACHE IVa.

    • Main Results:

    • The ML model demonstrated superior performance compared to the APACHE IVa score, particularly in classifying low-risk patients.
    • The ML model achieved an AUC of 0.85 (95% CI: 0.80-0.90), outperforming the APACHE IVa score's AUC of 0.80 (95% CI: 0.73-0.86).
    • The ML model exhibited higher specificity (27%) at 100% sensitivity than APACHE IVa (4% specificity).

    Conclusions:

    • A novel, explainable ML model provides more accurate mortality prediction for ICU patients with GI bleeds than the APACHE IVa score.
    • Explainable AI enhances clinical understanding of mortality risk factors, aiding in patient management.
    • This ML model offers a promising advancement in critical care for GI bleed patients.