Digital twins: A new paradigm for innovation in clinical research and medical affairs

Digital Twin (DT) technology, originally conceptualised in engineering, has recently emerged as a transformative paradigm in healthcare, promising to redefine the generation, interpretation, and application of biomedical evidence. DTs enable real-time simulation, prediction, and optimisation of clinical outcomes. The review aims to elucidate how DTs may enhance methodological efficiency, ethical standards, and strategic innovation in biomedical science, while addressing their epistemological and regulatory challenges. A DT is a dynamic, data-driven virtual replica of a biological entity or clinical process, continuously updated through real-time data to simulate, predict, and optimise outcomes. Originating in engineering, DTs are now entering healthcare as enablers of predictive, preventive, and precision medicine. Supported by Internet of Things (IoT) technologies, cloud computing, and machine learning, DTs integrate heterogeneous data-genomic, physiological, behavioural, and environmental-into adaptive models capable of mirroring and anticipating patient trajectories. In clinical research, they enable synthetic control arms and in silico trials, reducing recruitment barriers, improving statistical power, and addressing ethical issues associated with placebo use. The recent qualification of DT-based methodologies such as PROCOVA™ by the EMA and FDA confirms their growing scientific and regulatory credibility. DTs are redefining Medical Affairs, strengthening its role as a bridge between data science and clinical practice. They enable patient-level insights and personalised scientific communication, transforming Medical Affairs into a predictive, data-driven discipline that supports evidence-based and patient-centered decisions.