MO‐hHHO: Multi‐Objective Hybrid Harris Hawks Optimization for Prediction of Coronary Artery Disease

Coronary artery disease is a major cause of mortality and morbidity worldwide, underscoring the need for accurate diagnosis to ensure effective treatment. Consequently, bio‐inspired algorithms have led to several impactful applications in heart‐related ailments, demonstrating significant effectivene...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Advanced intelligent systems Ročník 7; číslo 11
Hlavní autoři:	Vijayaraj, Anu Ragavi, Pasupathi, Subbulakshmi
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Weinheim John Wiley & Sons, Inc 01.11.2025 Wiley
Témata:	Accuracy Algorithms Artificial intelligence Atherosclerosis Cardiovascular disease Classification classifications Coronary artery disease Coronary vessels Datasets Discriminant analysis Effectiveness Exploitation Feature selection feature selections Genetic algorithms Harris Hawks optimizations Heart Heart diseases Heuristic methods Machine learning Methods multiobjective optimizations Optimization Optimization techniques parameter tunings Performance evaluation Support vector machines Task complexity Vein & artery diseases
ISSN:	2640-4567, 2640-4567
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Coronary artery disease is a major cause of mortality and morbidity worldwide, underscoring the need for accurate diagnosis to ensure effective treatment. Consequently, bio‐inspired algorithms have led to several impactful applications in heart‐related ailments, demonstrating significant effectiveness in this domain. The Harris’ Hawks Optimization (HHO) is a recent metaheuristic algorithm inspired by the cooperative behavior of the hawks. This article presents, for the first time, the Multi‐Objective hybrid Harris Hawks Optimization (MO‐hHHO) algorithm, a novel enhancement of the HHO. Designed to address complex multiobjective problems (MOPs), MO‐hHHO focuses on feature selection minimization and classifier hyperparameter optimization, achieving improved predictive accuracy. To assess the performance of the proposed algorithm, four different machine learning classifiers are used: random forest (RF), K‐nearest neighbors, logistic regression (LR), and support vector machines (SVM). Extensive experiments are carried out using heart disease dataset obtained from the Kaggle repository. The experimental results on both single‐objective problems and MOPs reveal that the MO‐hHHO effectively reduces the number of features while optimizing classifier hyperparameters, achieving superior classification accuracy, particularly for RF, LR, and SVM. Additionally, hybrid HHOs adaptive exploration and exploitation mechanisms ensure efficient convergence toward optimal solutions, making it well‐suited for high‐dimensional and complex optimization tasks. This article proposes a novel Multi‐Objective hybrid Harris Hawks Optimization (MO‐hHHO) algorithm for simultaneous feature selection and hyperparameter tuning in heart disease classification. The approach leverages adaptive exploration‐exploitation strategies to enhance convergence efficiency. Evaluations using four classifiers on a benchmark dataset demonstrate MO‐hHHO's effectiveness in high‐dimensional multiobjective optimization tasks with improved classification performance showcasing its potential in medical diagnostics.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	2640-4567 2640-4567
DOI:	10.1002/aisy.202500172