Digital twins: an innovative and promising option to optimize care pathways for older patients

The digital transformation of healthcare, which has been continuously evolving for over two decades, has recently paved the way for major innovations, notably through the emergence of the digital twin (DT) concept. Originating from self-supervised machine learning, the DT involves creating a virtual replica (virtual product) of a patient, organ, or healthcare system (real product) to predict its evolution based on real-life data. It is based on clinical, biological, environmental data, as well as data from sensors and medico-administrative databases (e.g., SNDS) and relies on various digital technologies. Initially applied in aerospace, industry, and agriculture, DTs have recently gained traction in healthcare, particularly for the personalization of care plans and pathways. In geriatrics, DTs could help model the functional or clinical evolution of older adults, optimize healthcare resources, and adapt therapeutic protocols. The development of DTs in geriatrics involves addressing several major challenges, including older adults' acceptance of technology, building multidisciplinary teams, accurately modelling the complexity of aging, and considering the environmental impact of DT technologies. In summary, the digital twin represents a promising tool to support healthy aging and care pathways, provided its clinical integration and social acceptability are strengthened.