Related Experiment Videos

A novel dynamic Optuna hybrid Harris Hawks Optimization approach for classification of CAD

C K Revathi1, H Santhi2

  • 1Full-time research scholar, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India.

Plos One
|July 17, 2026
PubMed

Insights

This study introduces a new Dynamic Optuna Hybrid Harris Hawks Optimization (Dynamic Optuna H-HHO) to improve deep learning for coronary artery disease (CAD) prediction. The novel framework significantly boosts predictive accuracy for CAD detection.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Computational Biology

Background:

  • Coronary Artery Disease (CAD) is a major global health concern, driven by atherosclerotic plaque formation leading to coronary artery stenosis.
  • Current deep learning models for CAD prediction face limitations due to conventional optimization techniques, such as premature convergence and poor adaptability.
  • Accurate and early prediction of CAD is crucial for effective patient management and reducing mortality rates.

Purpose of the Study:

  • To propose and evaluate a novel Dynamic Optuna Hybrid Harris Hawks Optimization (Dynamic Optuna H-HHO) framework.
  • To enhance the performance and predictive accuracy of deep learning models for Coronary Artery Disease (CAD).
  • To overcome the limitations of traditional optimization methods in deep learning for medical image analysis.

Main Methods:

  • Development of the Dynamic Optuna H-HHO framework, incorporating dynamic parameter adjustment, adaptive escape energy, and Optuna-based hyperparameter tuning.
  • Application of the framework to optimize deep learning classifiers: ResNet-50, VGG-16, InceptionV3, and MobileNet.
  • Comparative performance evaluation against models optimized using the conventional Hybrid Harris Hawks Optimization (H-HHO) algorithm on a coronary artery stenosis dataset.

Main Results:

  • The Dynamic Optuna H-HHO framework demonstrated consistent improvements in predictive accuracy across all tested deep learning models.
  • InceptionV3 achieved a peak accuracy of 97.9% and MobileNet reached 97.6% using the proposed framework.
  • Conventional H-HHO optimization yielded a maximum accuracy of only 82.46%, highlighting the superiority of the new method.

Conclusions:

  • The Dynamic Optuna H-HHO framework offers a robust and scalable solution for enhancing deep learning-based Coronary Artery Disease (CAD) prediction.
  • The integration of adaptive optimization and automated hyperparameter tuning significantly improves model performance.
  • This advancement holds promise for more accurate and reliable CAD diagnosis, potentially reducing mortality rates.

Related Concept Videos

Methods of Medium Optimization01:28

Methods of Medium Optimization

Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...
Optimization Problems01:26

Optimization Problems

Optimization problems often involve identifying maximum or minimum values under specific constraints. A well-known example is determining the longest horizontal pipe that can be moved around a right-angled corner, where a 3-meter-wide hallway meets a 2-meter-wide hallway. This scenario, common in architectural design and industrial transport, can be understood conceptually through geometric and trigonometric reasoning.To visualize the problem, consider the pipe as a straight line that touches...