PSO‐XAI: An Optimized and Interpretable Approach for Breast Cancer Diagnosis

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, the risk of misdiagnosis. To address these challenges, machine learning (ML) has emerged as a powerful tool for computer‐aided diagnosis, with feature selection (FS) playing a vital role in improving model performance and interpretability. This research study proposes an integrated framework, incorporating customized Particle Swarm Optimization (PSO), for FS. This framework has been evaluated on a comprehensive set of 29 different models that span classical classifiers, ensemble techniques, neural networks, probabilistic algorithms, instance algorithms, and semisupervised algorithms. To ensure interpretability and clinical relevance, the study uses cross‐validation in conjunction with explainable AI methods. Experimental evaluation showed that the Multilayer Perceptron achieved a peak accuracy of 99.1% using only 12 features, and Random Forest achieved 98.2% accuracy using only 8 features with a 73.3% dimensionality reduction. The results highlight the potential of combining swarm intelligence with explainable ML for robust, trustworthy, and clinically meaningful breast cancer diagnosis.