PSO-XAI: A PSO-Enhanced Explainable AI Framework for Reliable Breast Cancer Detection

2025-10-23

AI Summary

Breast cancer is a prevalent malignancy among women, yet current diagnostic approaches suffer from high misdiagnosis rates, prohibitive costs, and poor interpretability. To address these limitations, this paper proposes an interpretable AI framework integrating enhanced Particle Swarm Optimization (PSO)-based feature selection with multi-model ensemble learning—comprising 29 classifiers spanning classical models, ensemble methods, and neural networks—and leverages model-agnostic explanation techniques (SHAP and LIME). Evaluated via five-fold cross-validation on public benchmark datasets, the framework achieves 99.1% classification accuracy while substantially reducing feature dimensionality, thus balancing high performance with clinical traceability. Key contributions include: (i) a customized PSO algorithm improving robustness and stability in feature selection; (ii) a unified interpretability interface ensuring transparency across diverse model architectures; and (iii) cross-paradigm ensemble integration enhancing generalization capability. This work establishes a novel paradigm for accurate, reliable, and clinically actionable early diagnosis of breast cancer.

Technology Category

• Machine Learning: Ensemble Methods
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Breast cancer is considered the most critical and frequently diagnosed cancer in women worldwide, leading to an increase in cancer-related mortality. Early and accurate detection is crucial as it can help mitigate possible threats while improving survival rates. In terms of prediction, conventional diagnostic methods are often limited by variability, cost, and, most importantly, risk of misdiagnosis. To address these challenges, machine learning (ML) has emerged as a powerful tool for computer-aided diagnosis, with feature selection playing a vital role in improving model performance and interpretability. This research study proposes an integrated framework that incorporates customized Particle Swarm Optimization (PSO) for feature selection. This framework has been evaluated on a comprehensive set of 29 different models, spanning classical classifiers, ensemble techniques, neural networks, probabilistic algorithms, and instance-based algorithms. To ensure interpretability and clinical relevance, the study uses cross-validation in conjunction with explainable AI methods. Experimental evaluation showed that the proposed approach achieved a superior score of 99.1% across all performance metrics, including accuracy and precision, while effectively reducing dimensionality and providing transparent, model-agnostic explanations. The results highlight the potential of combining swarm intelligence with explainable ML for robust, trustworthy, and clinically meaningful breast cancer diagnosis.

Problem

• Enhancing breast cancer detection accuracy using machine learning
• Reducing misdiagnosis risks through explainable AI methods
• Optimizing feature selection with Particle Swarm Optimization algorithm

Innovation

• Customized Particle Swarm Optimization for feature selection
• Model-agnostic explainable AI methods for interpretability
• Evaluated across 29 models achieving 99.1% accuracy