A new framework will replace some human clinical trials for medical devices with computer simulations that test devices on virtual patients. Medical devices—from pacemakers to artificial heart valves—currently require lengthy and expensive clinical trials to prove they are safe and effective. These trials can take years, cost millions, and sometimes fail only in late-stage testing when unexpected problems emerge. INSILICO aims to solve this by creating "virtual chimaeras": computer-generated patients that combine real anatomical, physiological, and pathological data from actual patient populations. Each virtual patient receives a simulated device implant, and the computer predicts how the patient's body will respond over time. If successful, this could transform how medical devices are approved. Device developers could run thousands of virtual trials before ever testing on a single human, catching design flaws early and reducing development costs. Regulators could evaluate safety evidence from simulations alongside traditional trials. The project also re-enacts an existing industry trial dataset to build trust in the approach. This is applied research with a clear regulatory goal—not fundamental science. The immediate practical aim is to speed up and lower the cost of bringing safe medical devices to patients.
View original technical description
INSILICO will establish the first integrated framework combining data- and knowledge-driven machine learning, realising in-silico trials (ISTs) in medical devices (MDs). Novel in-silico insights on MD safety and efficacy will impact regulatory science and innovation significantly by reducing R&D costs and speeding up regulatory clearance. I propose a new way to conceive ISTs as multi-model ensemble spaces of virtual experiments, equivalent to enrolling a cohort of synthetic, verifiably realistic virtual patients (VPs). Each VP will harbour a virtually implanted MD operating within physiological envelopes, modelling the patient's short-/long-term response. MD's performance and design will be predicted under diverse physiological regimes, highlighting uncertainties only encountered in late-phase clinical testing. INSILICO will overcome 3 high-risk high-impact technical barriers by 1) creating virtual patient cohorts reflecting various anatomy, physiology, and pathology ingesting real-world data from real patient populations, 2) accurately predicting interventional outcomes in virtual populations, 3) ensuring the reliability and scalability of computational predictions while accounting for aleatoric/epistemic uncertainties. The proposed unified physics-informed graph learning scheme will facilitate both the generation of VPs and physically consistent simulations. This project will 1) introduce the concept of virtual chimaeras, 2) extend physics-informed learning over graph networks to construct new reliable, accurate and fast multiphysics simulators, and 3) re-enact a unique industry-provided trial dataset to grow trust in ISTs by industry, trialists and regulators. INSILICO underpins next-generation ISTs, a paradigm shift beyond current conventional clinical trials as the primary source of scientific evidence on MD safety and efficacy. INSILICO will fundamentally transform MD regulatory science and innovation.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know