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: Jul 9, 2026

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

A Machine Learning Approach for Predicting 30-Day Hospital Readmission in Patients with Diabetes.

Safaa Saad Salim1, Abdullahi Abdu Ibrahim1

  • 1Department of Electrical and Computer Engineering, Altınbaş University, Mahmutbey Dilmenler Caddesi, No: 26, Bağcılar, İstanbul 34217, Turkey.

Healthcare (Basel, Switzerland)
|May 13, 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

Development of an advanced maternal health risk detection system using enhanced XGBOOST and blending models.

Digital health·2026
Same author

A causality-enhanced multiresolution residual learning framework for image retrieval with fast osprey optimization.

Scientific reports·2026
Same author

Advancing medical imaging: detecting polypharmacy and adverse drug effects with Graph Convolutional Networks (GCN).

BMC medical imaging·2024
Same author

Effects of the Hubbard U correction on the electronic and magnetic properties of the tetragonal V<sub>2</sub>P<sub>2</sub> sheet.

RSC advances·2022
Same author

Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network.

International journal of biomedical imaging·2021

Machine learning accurately predicts 30-day hospital readmissions for diabetic patients. This framework aids in identifying high-risk individuals for targeted interventions, improving patient outcomes and reducing healthcare costs.

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Diabetes Management

Background:

  • Hospital readmission for diabetes patients is a significant healthcare burden, increasing costs and negatively impacting patient health.
  • Early identification of high-risk diabetic patients is crucial for implementing timely interventions and enhancing care management strategies.

Purpose of the Study:

  • To develop and validate a machine learning (ML) framework for predicting 30-day hospital readmissions in diabetic patients.
  • To utilize a comprehensive multi-institutional clinical dataset for robust model development and evaluation.

Main Methods:

  • The study employed the Diabetes 130-US Hospitals dataset (101,766 encounters) with extensive data preprocessing.
  • Evaluated multiple ML models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and a stacking ensemble, using nested cross-validation and bootstrap resampling.
Keywords:
XGBoostclinical decision supportdiabeteshospital readmissionmachine learningpredictive modeling

Related Experiment Videos

Last Updated: Jul 9, 2026

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

  • Assessed clinical utility via decision curve analysis and interpretability using SHAP analysis.

    • Main Results:

    • The stacking ensemble model achieved a calibrated AUC of 0.688 and a Brier score of 0.094.
    • Effective risk stratification was observed, differentiating clearly between low- and high-risk patient groups.
    • Decision curve analysis confirmed the model's positive clinical net benefit across various thresholds.

    Conclusions:

    • The developed ML framework offers a reliable and interpretable method for predicting 30-day readmissions in diabetic patients.
    • This tool has the potential to significantly support clinical decision-making and optimize patient care management strategies.