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

Related Concept Videos

Diabetes: Symptoms, Diagnosis, and Complications

Diabetes: Symptoms, Diagnosis, and Complications

For most patients, experiencing several weeks of polyuria, polydipsia, fatigue, and significant weight loss may indicate the presence of diabetes. Furthermore, adults displaying the phenotypic appearance of type 2 diabetes (particularly those who are obese and not initially insulin-requiring), may have islet cell autoantibodies, suggesting autoimmune-mediated β cell destruction and a diagnosis of latent autoimmune diabetes of adults (LADA). The categorization of glucose homeostasis is...

You might also read

Related Articles

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

Sort by

Same author

Word Sequential Using Deep LSTM and Matrix Factorization to Handle Rating Sparse Data for E-Commerce Recommender System.

Computational intelligence and neuroscience·2021

Same journal

Readability of AI-Generated Patient Information on Glucagon-Like Peptide-1 Receptor Agonists.

JMIR bioinformatics and biotechnology·2026

Same journal

Random Survival Forest Versus Elastic-Net Regularized Cox Regression for Survival Prediction in Acute Myeloid Leukemia at Distinct Treatment Time Points: Model Performance Comparison Study.

JMIR bioinformatics and biotechnology·2026

Same journal

Temporal Reproducibility of a Genetic Algorithm-Derived Health Risk Score: Standardized Out-of-Fold Validation Framework (2021-2023).

JMIR bioinformatics and biotechnology·2026

Same journal

The AudioGene Translational Dashboard for Diagnosing Autosomal Dominant Nonsyndromic Hearing Loss: Phenotypic Data Visualization and Analysis Study.

JMIR bioinformatics and biotechnology·2026

Same journal

A Strategic Partnership to Advance AI Applications in Genomics and Bioinformatics for Health Innovation.

JMIR bioinformatics and biotechnology·2026

Same journal

Prevalence and Associated Risk Factors of Bovine Fasciolosis in Bahir Dar, Ethiopia: Cross-Sectional Study.

JMIR bioinformatics and biotechnology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 10, 2026

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

Optimizing Feature Selection and Machine Learning Algorithms for Early Detection of Prediabetes Risk: Comparative

Mahmoud B Almadhoun¹, M A Burhanuddin¹

¹Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia, Melaka, Durian Tunggal, 75450, Malaysia, 60 194807552.

JMIR Bioinformatics and Biotechnology

|December 4, 2025

Summary

This summary is machine-generated.

Machine learning models, particularly random forest and XGBoost, effectively predict prediabetes risk. Key predictors include BMI, age, and cholesterol levels, enabling early intervention for cardiovascular and kidney health.

Keywords:

extreme gradient boosting feature selection k-nearest neighbors machine learning prediabetes prediction support vector machine

More Related Videos

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

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Apr 10, 2026

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

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

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Computational biology and bioinformatics
Clinical informatics and decision support
Preventive medicine and public health

Background:

Prediabetes signifies an intermediate metabolic stage preceding type 2 diabetes.
It elevates the risk of severe complications, including cardiovascular disease and kidney failure.
Early identification of prediabetes is critical for timely interventions to prevent diabetes progression.

Purpose of the Study:

To compare the predictive performance of various machine learning (ML) algorithms for prediabetes detection.
To identify key clinical predictors associated with prediabetes using ML techniques.
To enhance the interpretability and accuracy of ML models for clinical application.

Main Methods:

Evaluated multiple ML models: Random Forest, XGBoost, SVM, and KNN on a dataset of 4743 individuals.
Employed LASSO regression and PCA for feature selection and dimensionality reduction.
Utilized hyperparameter tuning (RandomizedSearchCV, GridSearchCV) and SMOTE for model optimization and handling data imbalance.
Applied SHAP analysis for model-agnostic feature importance assessment.

Main Results:

Random Forest achieved the highest cross-validated ROC-AUC of 0.9117, demonstrating robust generalization.
XGBoost also showed strong performance in distinguishing between normal and prediabetic states.
SHAP analysis identified BMI, age, HDL, and LDL cholesterol as primary predictors.
Hyperparameter tuning significantly improved model performance, e.g., SVM ROC-AUC increased from 0.813 to 0.863.

Conclusions:

Optimized ML models, especially Random Forest and XGBoost, are effective for early prediabetes risk assessment.
Integrating SHAP, LASSO, and PCA enhances model transparency for clinical decision support systems.
Future research should focus on validating these models in diverse settings and incorporating additional biomarkers for improved accuracy in personalized preventive care.