Secure Explainable AI Framework for Privacy-Aware Digital Healthcare Marketing Data Analytics
Abstract
Artificial Intelligence in Digital Healthcare Marketing offers great promise for personalized patient engagement, however, data privacy, model interpretability, and regulatory compliance are important challenges. In this paper, we propose an optimized secure and explainable AI framework for healthcare marketing, combining federated learning with differential privacy mechanisms to guarantee data localization and robust privacy assurances. It contains a query fragment caching algorithm to enhance the analytical performance while maintaining privacy protection, and it adds SHAP and LIME techniques to ensure model transparency. Experimental results on a large healthcare marketing dataset show that the proposed approach obtains 92.4% accuracy and a privacy budget of $\varepsilon=2.5$ with an interpretability score of 0.87. The comparative analysis shows that the framework provides a 37.2% faster query response time and a 28.6% lower risk of privacy leakage than the existing frameworks, confirming the feasibility of implementing a privacy-aware, explainable artificial intelligence system in healthcare marketing settings with regulatory requirements.