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

Receiver Operating Characteristic Plot01:15

Receiver Operating Characteristic Plot

474
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
474
Esophageal Varices-II: Clinical Features and Management01:28

Esophageal Varices-II: Clinical Features and Management

378
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...
378

You might also read

Related Articles

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

Sort by
Same author

Low-Density Lipoprotein Cholesterol and Dementia Risk: Integrating Mendelian Randomization and Target Trial Emulation Within the Heart-Brain Axis.

medRxiv : the preprint server for health sciences·2026
Same author

Predictability of complex networks.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Biochemical-knowledge-driven machine learning pipeline for generating potent antimicrobial peptides.

Briefings in bioinformatics·2026
Same author

AI-based multiomics profiling reveals complementary omics contributions to personalized prediction of cardiovascular disease.

Nature communications·2026
Same author

Chatbot-Delivered Stage of Change-Tailored Web-Based Intervention to Promote Physical Activity Among Inactive Community-Dwelling People Aged 65 years or More: Protocol for a Randomized Controlled Trial.

JMIR research protocols·2025
Same author

Comparison of New-Onset Peripheral Artery Disease in Patients With Type 2 Diabetes Exposed to Sodium-Glucose Cotransporter-2 Inhibitors, Dipeptidyl Peptidase-4 Inhibitors, or Glucagon-Like Peptide-1 Agonists: A Population-Based Cohort Study.

Journal of the American Heart Association·2025
Same journal

Multimodule Human-Artificial Intelligence Collaboration Pipeline for Large Language Model-Assisted Thematic Analysis Across Digital Health Interview Studies: Comparative Evaluation Study.

JMIR medical informatics·2026
Same journal

Graph Network Feature Space Fusion for Predicting Irregularly Sampled Medical Time-Series Data: Deep Learning Model Development and Validation Study.

JMIR medical informatics·2026
Same journal

Intrasystem Repeatability of S-Detect for Breast Ultrasound Classification With Identical Static Images: Single-Center Retrospective Repeatability Study.

JMIR medical informatics·2026
Same journal

Clinician Perspectives on Ambient AI Scribes in the Intensive Care Unit: Qualitative Interview Study.

JMIR medical informatics·2026
Same journal

IdeaDistiller-AI Support for Idea Synthesis in Concept Mapping: Algorithm Development and Validation Study.

JMIR medical informatics·2026
Same journal

Pregnancy-Related Clinical Codes in Unlikely Populations in Primary Care.

JMIR medical informatics·2026
See all related articles

Related Experiment Video

Updated: Jan 18, 2026

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

Predicting Unplanned Readmission Risk in Patients With Cirrhosis: Complication-Aware Dynamic Classifier Selection

Zixin Shi1, Linjun Huang1, Xiaomei Xu2

  • 1College of Medical Informatics, Chongqing Medical University, 1 Yixueyuan Road, Yuzhong District, Chongqing, 400016, China, 86 13500303273.

JMIR Medical Informatics
|September 10, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel framework for predicting cirrhosis readmissions using electronic health records (EHRs). The approach improves prediction accuracy by dynamically selecting optimal machine learning models for individual patient subgroups, enhancing clinical decision support.

Keywords:
EHRcirrhosisdata miningdecision-makingelectronic health recordsframeworkgastrointestinal diseasemultiple classifier systemspredictive modelsreadmission risk

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

495
Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
05:16

Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure

Published on: June 10, 2025

535

Related Experiment Videos

Last Updated: Jan 18, 2026

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
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

495
Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
05:16

Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure

Published on: June 10, 2025

535

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Clinical Decision Support Systems

Background:

  • Cirrhosis is a major cause of mortality and high healthcare costs due to frequent hospitalizations and readmissions.
  • Electronic Health Records (EHRs) offer valuable data but present challenges like incompleteness and temporal dynamics for predictive modeling.
  • Accurate identification of high-risk patients is crucial for timely interventions and improved patient outcomes.

Purpose of the Study:

  • To develop and evaluate a novel framework for predicting patient readmission risk in cirrhosis using EHR data.
  • To address patient heterogeneity and data limitations by adaptively selecting predictive models for individual patients.
  • To enhance the accuracy and interpretability of predictive models for clinical decision support.

Main Methods:

  • A framework was developed to characterize patient subgroups based on diagnostic patterns.
  • A meta-learning approach was employed to train a meta-classifier for dynamic, on-the-fly selection of optimal predictive models.
  • A tailored region of competence was incorporated to refine model selection, specifically for cirrhosis complications.

Main Results:

  • The framework was validated on multicenter data from 3307 cirrhosis patients across 6 hospitals.
  • It demonstrated an average improvement in Area Under the Curve (AUC) of 5% and 4% over baseline models for predicting 14-day and 30-day readmissions, respectively.
  • The approach successfully aligned diverse patient subgroups with the most competent classifiers, enhancing predictive performance.

Conclusions:

  • The proposed framework enables interpretable training and dynamic selection of heterogeneous predictive models by leveraging subgroup expertise.
  • This advancement significantly improves prediction accuracy for cirrhosis readmissions.
  • The approach holds considerable potential for clinical applications, offering tailored decision-support algorithms for diverse patient populations.