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: May 6, 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

8.0K

Predictive models for ICU patient readmission based on machine learning: A systematic review.

Zhixiang Zheng1, Wenjun Yan2, Kai Cao3

  • 1Infectious Diseases Department, The First Affiliated Hospital of Soochow University, Jiangsu, China.

Journal of the Intensive Care Society
|April 7, 2026
PubMed
Summary

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

An Evidence-Based Quality Improvement Programme for Glycaemic Management in Critically Ill Patients Receiving Enteral Nutrition.

Nursing in critical care·2026
Same author

Feasibility of fully automatic assessment of cervical canal stenosis using MRI via deep learning.

Quantitative imaging in medicine and surgery·2025
Same author

Revisiting the Association Between Beta-blockers and Psoriasis: Evidence from Real-World Data.

Endocrine, metabolic & immune disorders drug targets·2025
Same author

Posterior capsular Opacification: Pathogenesis, challenges, and innovative therapeutic strategies.

Experimental eye research·2025
Same author

Surface-Localized Crosslinked MEW PCL-Hydrogel Scaffolds with Tunable Porosity for Enhanced Cell Adhesion and Viability.

Polymers·2025
Same author

Mn<sub>3</sub>O<sub>4</sub> nanozyme-based anti-inflammatory therapy modulates microglial phenotype by downregulating TLR4/NOX2 expression and further alleviates Alzheimer's disease pathology.

Theranostics·2025

Artificial intelligence (AI) models show moderate-to-high predictive performance for critically ill patient readmissions. Despite high bias risk, AI models outperform traditional methods, aiding in better patient management and reduced readmissions.

Area of Science:

  • Medical Informatics
  • Clinical Prediction Models
  • Artificial Intelligence in Healthcare

Background:

  • Artificial intelligence (AI) prediction models integrate multi-dimensional clinical data to identify high-risk populations.
  • These models support individualized discharge planning and optimize follow-up interventions to reduce readmission risk.
  • The increasing number of AI models for critically ill patient readmissions necessitates a quality and applicability evaluation.

Purpose of the Study:

  • To systematically evaluate published studies on AI prediction models for critically ill patient readmissions.
  • To assess the quality, risk of bias, and applicability of these AI models in clinical practice.

Main Methods:

  • A comprehensive search of multiple databases (CNKI, PubMed, Web of Science, etc.) was conducted from 2020 to June 2025.
Keywords:
artificial intelligencecritically ill patientsmeta-analysisreadmissionsystematic review

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

898

Related Experiment Videos

Last Updated: May 6, 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

8.0K
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

898
  • Data extraction included study design, data sources, predictors, model development, and performance metrics.
  • The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used for bias and applicability assessment.

    • Main Results:

    • 31 studies with 31 AI prediction models for critically ill patient readmissions were included.
    • The pooled Area Under the Curve (AUC) for 24 validation models was 0.82 (95% CI: 0.77-0.87).
    • All included studies exhibited a high risk of bias, primarily due to reporting quality and applicability limitations.

    Conclusions:

    • AI prediction models demonstrate moderate-to-high predictive performance for critically ill patient readmissions.
    • AI models significantly outperform traditional prediction models in predictive accuracy.
    • Despite identified biases, AI models offer valuable decision support for clinical practice and future research.