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 Videos

Enhancing stroke risk prediction through class balancing and data augmentation with CBDA-ResNet50.

Muhammad Asim Saleem¹, Ashir Javeed², Wasan Akarathanawat^3,4

¹Department of Electrical Engineering, Faculty of Engineering, Center of Excellence in Artificial Intelligence, Machine Learning and Smart Grid Technology, Chulalongkorn University, Bangkok, 10330, Thailand.

Scientific Reports

|July 8, 2025

Summary

Related Concept Videos

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

You might also read

Related Articles

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

Sort by

Same author

A hybrid AI vision model for single-camera tracking of rehabilitation exercises: a proof of concept in clinical settings.

Scientific reports·2026

Same author

Retraction Note: An intelligent learning system based on electronic health records for unbiased stroke prediction.

Scientific reports·2026

Same author

A hybrid approach for accurate skin lesion segmentation using LEDNet and Swin-UMamba.

Scientific reports·2026

Same author

The Smart Stroke Fast Track: A Digital Workflow Innovation to Reduce Door-to-Needle Time in Acute Ischemic Stroke.

Cerebrovascular diseases (Basel, Switzerland)·2026

Same author

Artificial intelligence-based fault classification on photovoltaic plants using a low-cost open-source IoT system.

Scientific reports·2025

Same author

Screening Performance of Stroke Scale for Mid-Level Personnel (SML) in Detecting Acute Stroke with Large Vessel Occlusion: A Cross-sectional Study.

Archives of academic emergency medicine·2025

Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026

Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026

Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026

Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026

Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026

Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026

See all related articles

This summary is machine-generated.

A new deep learning model, CBDA-ResNet50, enhances stroke risk prediction accuracy. This advanced approach improves early detection and prevention, potentially reducing healthcare costs.

Area of Science:

Medical Imaging
Artificial Intelligence
Cardiovascular Disease Research

Background:

Early stroke risk prediction is crucial for timely intervention and mitigating severe health and economic impacts.
Medical imaging datasets often suffer from class imbalance and limited data, leading to unreliable predictions.
Existing stroke risk prediction models may falter when specific risk factors are absent.

Purpose of the Study:

To develop an improved deep learning model for accurate early stroke risk prediction.
To enhance the ResNet50 architecture using class balancing and data augmentation techniques.
To overcome limitations of traditional models in handling imbalanced medical imaging data.

Main Methods:

Proposed a novel class-balanced and data-augmented deep learning model (CBDA-ResNet50) based on ResNet50.

Keywords:

Class balancing Data augmentation Deep learning ResNet50 Stroke prediction

Related Experiment Videos

Implemented weighted cross-entropy to address class imbalance.

Utilized the Adam optimizer and ReduceLROnPlateau scheduler for learning rate optimization.

Main Results:

Achieved a high accuracy of 97.87% and a balanced accuracy of 98.27%.
Demonstrated superior performance compared to previous state-of-the-art models.
Showcased reliable predictions even with absent stroke risk factors in the data.

Conclusions:

The CBDA-ResNet50 model significantly improves stroke risk prediction accuracy.
Combining deep learning with advanced data processing techniques enhances prediction reliability.
CBDA-ResNet50 shows potential for early stroke prevention, improving patient outcomes and reducing healthcare expenditure.