In a Perspective, Reinhard Laubenbacher and colleagues argue that personalized, predictive computer simulations - or "digital twins" - which integrate known human physiology and immunology with real-time patient-specific clinical data, could allow for more effective treatments for viral infections for individual patients. Epidemiological computer models continue to play a crucial role in addressing the global COVID-19 pandemic. They are often relied upon by policymakers and healthcare officials to inform the most effective public health responses. However, no analogous tools currently exist to help doctors predict the course of viral infection and decide upon the most appropriate treatment for an individual COVID-19 patient. Originally an engineering concept, a "digital twin" combines real-world data and computer modeling to create a virtual replica of a physical thing or system, which can be used as dynamic models to monitor and evaluate their function or failure. According to Laubenbacher et al., medical digital twins could serve a similar purpose for health care professionals, providing personalized, predictive computer simulations of viral infections and immune responses to optimize treatments. Laubenbacher et al. discuss the challenges of building accurate models that encompass myriad biological processes and body systems affected by viral infection. For example, building useful digital twins requires improved communication and data sharing between clinicians and computer modelers so that biological insights can be translated into computational models. Although, the authors note that many of the necessary sub-models required to assemble digital twins for infection either already exist or could be developed using existing experimental technologies. What's more, medical digital twins are beginning to be used in other areas of human health, including diabetes treatment and pediatric cardiology. "Such medical digital twins could be a powerful addition to our arsenal of tools to fight future pandemics, combining mechanistic knowledge, observational data, medical histories and the power of artificial intelligence," write the authors.
###
Journal
Science