The interconnected medical devices and networks face escalating cyber threats that demand intelligent detection mechanisms. Traditional deep learning approaches for cyber threat intelligence (CTI) in healthcare networks suffer from the black-box problem, limiting their practical deployment in critical medical environments where explainability is paramount. This paper presents a novel explainable deep learning (XDL) framework that integrates sparse autoencoders with neural synchronization mechanisms for transparent cyber threat detection in Internet of Medical Things (IoMT) networks. Our approach, termed XDL-CTI-MedNet, employs neuron-level local activation consistency constraints and synchronization-based functional module construction to achieve high detection accuracy and interpretable decision-making processes. The framework incorporates a multi-dimensional interpretability evaluation system that assesses explanation accuracy, stability, purity, and diversity from various analytical perspectives. Experiments on CIC IoMT 2024 and IoT healthcare security datasets demonstrate superior performance with 98.4-98.8% accuracy while achieving interpretability scores of 0.935-0.947, outperforming six baseline methods across all evaluation dimensions. Statistical validation through ten independent runs with different random initializations confirms robust performance with standard deviations below 0.8%, and the Friedman test analysis establishes statistical significance at the 0.05 confidence level.
Song et al. (Thu,) studied this question.