Building Digital Twins for Elderly Care: An End-to-End Framework from Data Acquisition to Modeling

The rapid growth of the aging population, which is expected to reach 2.1 billion by 2050, poses profound challenges for healthcare systems and quality of life of the elderly. Current research on digital healthcare has focused on incorporating Artificial Intelligence (AI) and wearable technology to deliver personalized care to the elderly population. Digital Twins (DTs) are virtual models that replicate real-world entities using real-time data and offer new possibilities for personalized healthcare. Although studies have explored the adaptation of DTs technology for personalized healthcare, especially for older adults, significant gaps remain in comprehensive data integration, advanced predictive capabilities, and underutilization of Generative AI (Gen AI) for real-time support, limiting support for caregivers in elderly care. This study addresses these gaps by proposing a comprehensive Elderly Digital Twin (EDT) framework that integrates diverse real-time physiological data to enhance personalized healthcare. The feasibility and applicability of the framework were validated by developing a cardiac DT incorporating real-time monitoring, prediction, and analysis of heart rate (HR), heart rate zone (HRZ), sleep quality DT model, and SpO2 monitoring DT model. Advanced predictive modeling demonstrated high accuracy, with LSTM achieving a 92% validation accuracy in predicting sleep levels. Bi-LSTM demonstrated robust performance in real-time HR (BPM) prediction, achieving an MSE of 0.2944 and MAE of 0.3410. The EDT framework was deployed via a Node.js-based web application that offers real-time physiological monitoring, interactive 3D cardiac simulation, and GPT-4o-powered personalized feedback to enhance caregiver decision making and elderly self-management. This study contributes to advancing DT technology by creating an interpretable, scalable system for proactive elderly care, and sets the stage for future research into multiorgan digital twins and broader clinical deployment.