Hypertension is a global health challenge requiring innovative approaches to enable real-time, continuous blood pressure (BP) monitoring. Traditional BP monitoring methods fail to provide the continuous tracking needed for proactive hypertension management. This research addresses these limitations by designing a continuous BP monitoring system that integrates multimodal data with a hybrid deep learning model for real-time BP estimation. Using a Design Science Research (DSR) approach, the system was developed through iterative cycles, identifying challenges, meta requirements, and design principles to ensure scalability, efficiency, and explainability of the artefact. Results demonstrate the artefact’s potential to enhance clinical decision-making and support real-time hypertension care. This research provides practical insights into designing intelligent digital health systems that enable continuous monitoring and improve hypertension care. By leveraging Artificial Intelligence-based solutions and a DSR approach, the research work demonstrates how data-driven systems can enhance clinical decision-making and support the effective management of hypertension.