Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 22, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Feature reduction using swarm optimization and random forest classifiers for early diabetes risk prediction.

Proshenjit Sarker¹, Abdullah-Al Nahid¹, Kwonhue Choi²

¹Electronics and Communication Engineering Discipline, Khulna University, Khulna, 9208, Bangladesh.

Scientific Reports

|March 21, 2026

Summary

This summary is machine-generated.

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

Gallstone disease classification using SLOA-optimized CatBoost classifier with explainable AI.

PloS one·2026

Same author

Metaheuristic-based gallstone classification using rotational forest explained with SHAP.

Frontiers in digital health·2026

Same author

Circular RNAs: A key modulator of established cancer hallmarks.

Critical reviews in oncology/hematology·2026

Same author

CatBoost with physics-based metaheuristics for thyroid cancer recurrence prediction.

BioData mining·2025

Same author

Lightweight ECC-Based Self-Healing Federated Learning Framework for Secure IIoT Networks.

Sensors (Basel, Switzerland)·2025

Same author

Diabetes Prediction Using Feature Selection Algorithms and Boosting-Based Machine Learning Classifiers.

Diagnostics (Basel, Switzerland)·2025

This study introduces advanced machine learning models for early diabetes detection, achieving high accuracy with significant feature reduction. Tuna Swarm Optimization with Random Forest (TSO_RF) demonstrated superior performance, identifying key risk factors like Polyuria and Polydipsia.

Area of Science:

Medical Informatics
Computational Biology
Artificial Intelligence in Healthcare

Background:

Diabetes mellitus is a chronic metabolic disorder with severe health implications, necessitating early detection.
Type 2 diabetes, characterized by insulin resistance or deficiency, poses a significant global health challenge.
Current early detection methods often involve numerous features, increasing patient burden and reducing efficiency.

Purpose of the Study:

To develop and evaluate machine learning models for efficient early diabetes risk prediction.
To achieve high accuracy while significantly reducing the number of predictive features.
To provide explainable AI insights into model behavior and feature importance.

Main Methods:

Three swarm-based metaheuristic algorithms (Fox Optimizer, Honey Badger Algorithm, Tuna Swarm Optimization) were integrated with a Random Forest Classifier.

More Related Videos

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Related Experiment Videos

Last Updated: Mar 22, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

The Early Stage Diabetes Risk Prediction dataset, comprising 520 individuals and 16 predictors, was utilized.

Explainable AI techniques, specifically SHAP (SHapley Additive exPlanations), were employed for model interpretability.

Main Results:

Tuna Swarm Optimization with Random Forest (TSO_RF) achieved 100% accuracy without cross-validation and 98.14% mean 10-fold cross-validation accuracy.
TSO_RF utilized only 14 features, demonstrating effective feature reduction while maintaining high performance.
SHAP analysis identified Polyuria, Polydipsia, and Gender as critical predictors for diabetes risk.

Conclusions:

The proposed TSO_RF model offers a highly accurate and efficient approach for early diabetes detection.
Significant feature reduction is achievable without compromising predictive performance.
Explainable AI provides crucial insights into the factors driving diabetes risk prediction.