Optimization Algorithms for Feature Selection in Healthcare

Abstract

Feature selection plays a critical role in healthcare data analytics by identifying the most relevant attributes that contribute to accurate disease prediction and diagnosis. This paper presents a framework based on Optimization Algorithms for Feature Selection in Healthcare, aiming to enhance model performance while reducing computational complexity. The proposed approach employs metaheuristic optimization techniques such as Genetic Algorithms, Particle Swarm Optimization, and nature-inspired methods to select optimal feature subsets from high-dimensional medical datasets. These techniques are integrated with machine learning models to improve classification accuracy and reduce overfitting. The framework also incorporates hybrid strategies that combine global search capabilities of optimization algorithms with local refinement techniques. Experimental results demonstrate that the proposed method significantly improves prediction performance while minimizing redundant and irrelevant features. Additionally, integration with prior research in ensemble learning and healthcare analytics enhances robustness and generalization. The study highlights the importance of optimization-driven feature selection in developing efficient, scalable, and accurate healthcare predictive systems, particularly in resource-constrained environments.