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

Diabetic Nephropathy01:28

Diabetic Nephropathy

Definition Diabetic nephropathy is a chronic kidney complication that results from prolonged hyperglycemia.Prevalence It is the most common cause of chronic kidney disease (CKD) and end-stage renal disease (ESRD) worldwide, affecting up to half of individuals with diabetes.Pathophysiology • Sustained hyperglycemia triggers multiple hemodynamic and metabolic changes in the kidney. • Early in the disease, increased renal blood flow and glomerular hyperfiltration occur due to afferent arteriolar...
Diabetes Mellitus: Introduction01:26

Diabetes Mellitus: Introduction

Diabetes mellitus consists of chronic metabolic disorders characterized by persistent hyperglycemia. This elevated blood glucose results from defects in insulin secretion, impaired insulin action, or both. Insulin, produced by pancreatic β-cells, is essential for maintaining glucose homeostasis by facilitating cellular glucose uptake for energy or storage. Disruptions in insulin production or function lead to glucose accumulation in the bloodstream, causing the clinical features and long-term...
Diabetes Mellitus: Overview and Type I Subtype01:22

Diabetes Mellitus: Overview and Type I Subtype

Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
Diabetes: Management and Pharmacotherapy01:15

Diabetes: Management and Pharmacotherapy

The therapy for diabetes aims to alleviate hyperglycemia-related symptoms, prevent acute metabolic decompensation, and reduce chronic end-organ complications. Glycemic control is evaluated through short-term (self-monitoring, continuous glucose monitoring) and long-term (A1c, fructosamine) metrics, enabling near real-time tracking of blood glucose levels and reflecting glycemic control over specific time frames.
Insulin remains the cornerstone of treatment for most patients with type 1 and many...

You might also read

Related Articles

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

Sort by
Same author

Patients' perspectives on mobile health applications for diabetes self-management: A qualitative study in Malaysia.

Digital health·2026
Same author

Healthcare professionals' perspectives on artificial intelligence (AI)-based mobile applications (apps) for diabetes education and behavioural management.

Digital health·2025
Same author

A Hybrid Route Selection Scheme for 5G Network Scenarios: An Experimental Approach.

Sensors (Basel, Switzerland)·2022
Same author

Enhanced handover mechanism using mobility prediction in wireless networks.

PloS one·2020
Same author

Jmjd3-mediated epigenetic regulation of inflammatory cytokine gene expression in serum amyloid A-stimulated macrophages.

Cellular signalling·2014
Same author

Overexpression of EMMPRIN isoform 2 is associated with head and neck cancer metastasis.

PloS one·2014

Related Experiment Video

Updated: May 23, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

A hybrid ensemble approach for diabetes prediction using consensus-based feature selection.

JianHao Chen1,2, Yung-Wey Chong2, LiLi Wang1,2

  • 1School of Artificial Intelligence, Chongqing Youth Vocational & Technical College, Chongqing, China.

Digital Health
|May 22, 2026
PubMed
Summary

A new hybrid ensemble framework accurately predicts diabetes using eight key features, improving early detection. This data-driven approach enhances clinical decision-making for diabetes mellitus management.

Keywords:
diabetes predictionensemble learningfeature selectionmajority voting

Related Experiment Videos

Last Updated: May 23, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Area of Science:

  • Computational biology and bioinformatics
  • Medical informatics and health data science
  • Clinical diagnostics and predictive modeling

Background:

  • Diabetes mellitus affects 589 million adults globally, with many undiagnosed cases leading to severe complications.
  • Accurate, data-driven early detection of diabetes is crucial for timely clinical intervention and improved patient outcomes.
  • Existing diagnostic tools often identify diabetes only after complications arise, highlighting the need for advanced predictive models.

Purpose of the Study:

  • To develop a hybrid ensemble framework for enhanced diabetes prediction accuracy and clinical interpretability.
  • To integrate multiple feature selection strategies with a consensus approach for robust diabetes risk assessment.
  • To create a clinically relevant and interpretable model for early diabetes detection.

Main Methods:

  • Analysis of a dataset with 1,879 patients and 46 features, including engineered interaction features.
  • Combination of four supervised feature selection methods (RFE, Random Forest, ANOVA, Mutual Information) with PCA and a consensus criterion.
  • Optimization and integration of seven classifiers into a soft voting ensemble using GridSearchCV and 5-fold cross-validation.

Main Results:

  • Identification of eight consensus features (HbA1c, fasting blood sugar, hypertension, etc.), achieving an 82.6% dimensionality reduction.
  • The soft voting ensemble achieved high performance: AUC 0.948, accuracy 92.6%, precision 91.8%, recall 89.4%, and F1-score 90.6%.
  • The ensemble model outperformed individual classifiers in recall and F1-score, demonstrating superior predictive capability.

Conclusions:

  • The proposed framework offers a clinically interpretable and high-performing model for diabetes prediction through combined feature selection and ensemble learning.
  • Consensus-driven feature transparency and robust generalisation support the model's deployment in early screening and digital health applications.
  • Future research should focus on external validation, explainable AI integration, and real-time clinical decision support development.