Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Esophageal Varices-II: Clinical Features and Management

Esophageal Varices-II: Clinical Features and Management

Esophageal varices often manifest as gastrointestinal bleeding episodes, presenting symptoms like hematemesis (vomiting of blood), hematochezia (passing fresh blood via the rectum), and melena (black, tarry stools). Other signs can include weight loss, anorexia, abdominal discomfort, jaundice, pruritus, altered mental status, and muscle cramps.
In the initial assessment, a thorough review of the patient's medical history is vital to identify risk factors such as liver disease, alcohol...

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...

You might also read

Related Articles

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

Sort by

Same author

Validation of a pan-ELastography Machine-learning (ELM) score to predict clinically significant portal hypertension in compensated advanced chronic liver disease.

Journal of hepatology·2026

Same author

Community-Based <i>Helicobacter pylori</i> Screening to Identify Gastric Cancer Risk Among Korean-Born Adults in the United States.

Public health reports (Washington, D.C. : 1974)·2026

Same author

Mortality and Infectious Adverse Events in Neutropenic Patients Undergoing Gastrointestinal Endoscopic Procedures: A Systematic Review and Meta-Analysis.

Gastro hep advances·2026

Same author

The impact of gastric adenocarcinoma location and clinical and socioeconomic determinants on survival: a retrospective population-based cohort study using SEER data (1975-2016).

BMC gastroenterology·2026

Same author

Adolescent social isolation creates a latent vulnerability in maternal care with intergenerational social consequences, rescued by experienced mothers.

bioRxiv : the preprint server for biology·2026

Same author

Outcomes After Percutaneous Coronary Intervention for Chronic Coronary Disease in Adults ≥ 75 versus < 75 Years.

Journal of the American Geriatrics Society·2026

Search research articles

Related Experiment Video

Updated: Jun 21, 2025

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

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

Published on: May 15, 2020

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

Dennis L Shung¹, Colleen E Chan², Kisung You³

¹Section of Digestive Diseases, Department of Medicine, Yale School of Medicine, New Haven, Connecticut; Clinical and Translational Research Accelerator, Department of Medicine, Yale School of Medicine, New Haven, Connecticut; Department of Biomedical Informatics and Data Science, Department of Medicine, Yale School of Medicine, New Haven, Connecticut.

Gastroenterology

|July 6, 2024

Summary

A new electronic health record (EHR)-based machine learning model for gastrointestinal bleeding (GIB) identifies more very-low-risk patients for emergency department discharge than existing scores. This advanced GIB risk stratification improves patient selection for early discharge.

Keywords:

Electronic Health Record Gastrointestinal Hemorrhage Machine Learning

More Related Videos

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Related Experiment Videos

Last Updated: Jun 21, 2025

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

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

Published on: May 15, 2020

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Area of Science:

Medical Informatics
Clinical Decision Support
Machine Learning in Healthcare

Background:

Current guidelines recommend risk stratification scores for gastrointestinal bleeding (GIB) patients to facilitate emergency department (ED) discharge.
Machine learning (ML) models integrated into electronic health records (EHRs) offer potential for real-time, automated risk assessment.

Purpose of the Study:

To develop and validate the first EHR-based ML model for GIB risk stratification.
To compare the performance of this ML model against established scores like the Glasgow-Blatchford Score and Oakland Score.

Main Methods:

Trained and validated an ML model using structured EHR data from over 2500 patients with overt GIB.
Compared ML model performance (AUC) against Glasgow-Blatchford and Oakland scores using internal and external validation cohorts.
Assessed specificity at 99% sensitivity to identify very-low-risk patients.

Main Results:

The ML model significantly outperformed both the Glasgow-Blatchford Score (AUC 0.92 vs 0.89) and Oakland Score (AUC 0.92 vs 0.89).
At 99% sensitivity, the ML model identified a higher proportion of very-low-risk patients (37.9%) compared to Glasgow-Blatchford (18.5%) and Oakland (11.7%) scores.

Conclusions:

An EHR-based ML model demonstrates superior performance in risk stratifying GIB patients compared to current clinical scores.
This ML model enhances the identification of very-low-risk patients suitable for early ED discharge.