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

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...

You might also read

Related Articles

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

Sort by

Same author

Strengthening field-informed for-profit private sector engagement strategy in malaria elimination: insights from a single-group quasi-experimental pilot study in Bangladesh.

Malaria journal·2026

Same author

Sleep lowers waking theta frequency in the rat hippocampus.

Cell reports·2026

Same author

Spatiotemporal trends of foot and mouth disease (FMD) in Bangladesh from 2017 to 2023 and their associations with climatic factors and machine learning (ML) based prediction.

Scientific reports·2026

Same author

Identification of Key Microbial Signatures Associated With Breast Cancer: Machine Learning-Based Approaches Using Gut Microbiome Data.

Cancer medicine·2026

Same author

Predicting short birth intervals in Bangladesh using stacked machine learning and SHAP explainability: evidence from BDHS 2022.

Reproductive health·2026

Same author

Factors associated with malnutrition among under five children in Bangladesh: a multivariate analysis.

Journal of health, population, and nutrition·2026

Search research articles

Related Experiment Video

Updated: Jul 8, 2025

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

Predicting the risk of diabetic retinopathy using explainable machine learning algorithms.

Md Merajul Islam¹, Md Jahanur Rahman², Md Symun Rabby³

¹Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh; Department of Statistics, Jatiya Kabi Kazi Nazrul Islam University, Mymensingh-2224, Bangladesh.

Diabetes & Metabolic Syndrome

|December 13, 2023

Summary

This study developed an explainable machine learning system to predict diabetic retinopathy (DR) risk. The XGBoost model achieved 90.01% accuracy, identifying key predictors for early DR detection in China.

Keywords:

Diabetic retinopathy Machine learning Prediction Predictors

More Related Videos

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

Retinal Pathophysiological Evaluation in a Rat Model

Retinal Pathophysiological Evaluation in a Rat Model

Published on: May 6, 2022

Related Experiment Videos

Last Updated: Jul 8, 2025

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

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

Retinal Pathophysiological Evaluation in a Rat Model

Retinal Pathophysiological Evaluation in a Rat Model

Published on: May 6, 2022

Area of Science:

Ophthalmology
Medical Informatics
Data Science

Background:

Diabetic retinopathy (DR) poses a significant global health challenge for individuals with diabetes.
Early detection and risk prediction are crucial for managing DR and preventing vision loss.

Purpose of the Study:

To develop an explainable machine learning (ML) system for predicting the risk of diabetic retinopathy (DR).
To identify key predictors contributing to DR risk through feature selection and explainability techniques.

Main Methods:

Utilized a cross-sectional dataset of 6374 individuals from a Chinese cohort.
Employed Boruta and LASSO for feature selection to identify DR predictors.
Trained and optimized four ML models (ANN, SVM, RF, XGBoost) and used SHAP for prediction explanation.

Main Results:

Boruta and LASSO identified community, TCTG, HDLC, BUN, FPG, HbA1c, weight, and duration as significant DR predictors.
The XGBoost model demonstrated superior performance with 90.01% accuracy, 91.80% precision, 97.91% recall, 94.86% F1 score, and 0.850 AUC.
SHAP analysis highlighted HbA1c, community, FPG, TCTG, duration, and UA1b as influential predictors.

Conclusions:

The developed system effectively identifies significant predictors for early DR risk assessment.
This explainable ML tool can aid in predicting high-risk DR patients in China at an early stage.