Digital twins are increasingly presented as a computational foundation for personalized and preventive medicine, because they promise to integrate multimodal data into dynamic representations of patients, organs, diseases, or care pathways. Yet the translational maturity of medical digital twins remains limited. Many systems labelled as digital twins are still digital models, digital shadows, descriptive simulations, or prediction tools whose clinical claims exceed the evidence provided for calibration, uncertainty, transportability, causal validity, or real-world utility. This Perspective argues that the next bottleneck for digital twins in health is not model complexity but clinical trustworthiness. The main contribution of this Perspective is a claim-to-evidence typology that links the evidentiary burden of a digital twin to the clinical claim it makes, rather than to its computational architecture alone. This approach connects individual-level multimodal modelling with epidemiology, prediction science, causal inference, and implementation science. This article outlines a staged framework that distinguishes descriptive, predictive, counterfactual, interventional, and population-health clinical claims made by systems labelled or proposed as digital twins, each associated with a distinct evidentiary threshold. This article further proposes that validation should integrate verification, calibration, external and temporal validation, uncertainty quantification, fairness assessment, target trial emulation where causal claims are made, and post-deployment monitoring. Without such methodological discipline, digital twins may remain sophisticated but clinically fragile simulations. Conversely, population-calibrated and prospectively evaluated digital twins could become a robust infrastructure for personalized prevention, adaptive treatment, and learning health systems.
Alexandre Vallée· Frontiers in Digital Health· 0 citations
Abstract Objective To clarify how validation requirements should be specified for medical digital twins used in clinical decision support, particularly when such systems are intended to compare interventions, treatment timings, dosages, or sequential care strategies. Perspective Medical digital twins are heterogeneous systems that may combine prediction, simulation, mechanistic modeling, machine learning, data assimilation, uncertainty quantification, and decision-support functions. Their evaluation should therefore be driven by their intended use rather than by a single definition of what a digital twin is. For digital twins used primarily for visualization, monitoring, or short-term forecasting, predictive accuracy, calibration, discrimination, and robustness may be the central validation targets. However, when digital twins are used to support intervention-oriented clinical decisions, retrospective accuracy under historical clinical practice is insufficient on its own. Key message Intervention-oriented digital twins address action-conditioned questions: what is predicted to happen under specified alternative actions, assumptions, time horizons, and clinical contexts. Their validation should therefore extend beyond scalar performance metrics to include uncertainty representation, updating stability, robustness under regime change, action-regime validity, counterfactual consistency, clinically weighted error, and decision-level consequences. This requires drawing on established traditions in forecast verification, causal inference, uncertainty quantification, model verification and validation, decision theory, control theory, and post-deployment monitoring. The level of causal or mechanistic support required should match the clinical claim being made, whether at the genotype, phenotype, physiological, or care-process level. Conclusion The scientific-instrument framing is proposed as a pragmatic validation lens for intervention-oriented digital twins, not as a universal definition of digital twins. It helps define the scope within which their outputs can support clinical reasoning. Medical digital twins should be accompanied by explicit validation statements specifying their target population, prediction horizon, supported interventions, uncertainty bounds, and known failure conditions.
Alexandre Vallée· JAMIA Open· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
