The article discusses the importance of explainable artificial intelligence (XAI) in medical imaging, particularly for multimodal and longitudinal data. It highlights the need for systems that can handle complex clinical workflows and provide interpretable results. The authors propose the XAI Orchestrator, a virtual assistant designed to help clinicians by synthesizing multimodal and longitudinal data, generating AI predictions, and providing explainability outputs. The XAI Orchestrator aims to be adaptive, hierarchical, interactive, and uncertainty-aware, offering a comprehensive explanation of AI decisions. The article also reviews existing XAI methods and challenges, emphasizing the need for further development and clinical validation. It suggests that large language models (LLMs) can play a crucial role in improving the usability and effectiveness of XAI systems, particularly in healthcare settings. The authors call for more involvement of clinical experts in the development and integration of XAI systems to ensure they meet user needs and improve clinical outcomes.The article discusses the importance of explainable artificial intelligence (XAI) in medical imaging, particularly for multimodal and longitudinal data. It highlights the need for systems that can handle complex clinical workflows and provide interpretable results. The authors propose the XAI Orchestrator, a virtual assistant designed to help clinicians by synthesizing multimodal and longitudinal data, generating AI predictions, and providing explainability outputs. The XAI Orchestrator aims to be adaptive, hierarchical, interactive, and uncertainty-aware, offering a comprehensive explanation of AI decisions. The article also reviews existing XAI methods and challenges, emphasizing the need for further development and clinical validation. It suggests that large language models (LLMs) can play a crucial role in improving the usability and effectiveness of XAI systems, particularly in healthcare settings. The authors call for more involvement of clinical experts in the development and integration of XAI systems to ensure they meet user needs and improve clinical outcomes.