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 Concept Videos

Esophageal Varices-II: Clinical Features and Management01:28

Esophageal Varices-II: Clinical Features and Management

110
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...
110

You might also read

Related Articles

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

Sort by
Same author

Diagnostic accuracy and association with lymph node metastasis of the systemic immune-inflammation index in thyroid cancer: a systematic review and meta-analysis.

Frontiers in immunology·2026
Same author

Two Decades of Progress and Remaining Challenges: Comparative Analysis of Rare Disease Policy Implementation in Bulgaria, Romania, and Greece.

Therapeutic innovation & regulatory science·2026
Same author

Boron symbiotaxis: A trace element perspective on host-microbiome signaling and lipidomic coherence in obesity.

Journal of trace elements in medicine and biology : organ of the Society for Minerals and Trace Elements (GMS)·2026
Same author

Pro-Inflammatory Synergy Between IL-17, IL-1 and Hyperuricemia in Psoriatic Arthritis: Clinical Implications of a Pilot Study.

Diseases (Basel, Switzerland)·2026
Same author

Paraneoplastic Endocrine Changes in Gastrointestinal Tumors: A Clinical and Mechanistic Review.

International journal of molecular sciences·2026
Same author

Diagnostic Yield and Histopathological Features of Colorectal Lesions Detected Through a Regional Screening Program from the South-West Oltenia Region, Romania.

Cancers·2026

Related Experiment Video

Updated: Aug 8, 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

8.3K

Predicting mortality in patients with nonvariceal upper gastrointestinal bleeding using machine-learning.

Bogdan Silviu Ungureanu1, Dan Ionut Gheonea1, Dan Nicolae Florescu1

  • 1Department of Gastroenterology, University of Medicine and Pharmacy of Craiova, Craiova, Romania.

Frontiers in Medicine
|March 6, 2023
PubMed
Summary

Artificial Neural Networks (ANNs) can accurately predict mortality in patients with nonvariceal upper gastrointestinal bleeding (NVUGIB). The K-Nearest Neighbor (K-NN) classifier achieved 98% accuracy, outperforming existing risk scores for patient triage.

Keywords:
Beylor Bleeding scoreGlasgow Blatchford scoreRockall scoreUGIBmachine learning

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

161
Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.1K

Related Experiment Videos

Last Updated: Aug 8, 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

8.3K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

161
Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.1K

Area of Science:

  • Gastroenterology
  • Medical Informatics
  • Artificial Intelligence

Background:

  • Non-endoscopic risk scores like Glasgow Blatchford (GBS) and Rockall (Rock) have limited specificity for assessing nonvariceal upper gastrointestinal bleeding (NVUGIB).
  • Accurate and specific risk stratification is crucial for effective patient triage and management in NVUGIB cases.

Purpose of the Study:

  • To develop an Artificial Neural Network (ANN) model for the non-endoscopic triage of NVUGIB patients.
  • To utilize machine learning algorithms to predict mortality as a primary outcome in NVUGIB.

Main Methods:

  • Retrospective analysis of 1,096 hospitalized NVUGIB patients, randomly divided into training and testing groups.
  • Evaluation of four machine learning algorithms: Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), logistic regression (LR), and K-Nearest Neighbor (K-NN).
  • Comparison of machine learning models against existing scores: GBS, Rockall (Rock), Beylor Bleeding score (BBS), AIM65, and T-score.

Main Results:

  • Machine learning models demonstrated superior accuracy in predicting mortality compared to existing risk scores.
  • The AIM65 score was identified as the most significant predictor of mortality, while BBS showed no influence.
  • Higher AIM65 and GBS scores, and lower Rockall and T-scores, correlated with increased mortality risk.

Conclusions:

  • The hyperparameter-tuned K-Nearest Neighbor (K-NN) classifier achieved the highest accuracy (98%), precision, and recall.
  • Machine learning, particularly K-NN, offers a highly accurate method for predicting mortality in NVUGIB patients.
  • This approach can significantly improve the non-endoscopic triage of NVUGIB, enhancing patient management.