{"entity":{"id":"digital-twins-trials","kind":"technology","name":"Digital twins and virtual control arms","aka":[],"tldr":"Using a model of what would have happened to a patient on standard treatment, so fewer people have to be randomised to it.","summary":"Prognostic models trained on historical trial and registry data generate an expected control trajectory for each enrolled patient, which can shrink the control arm or sharpen its estimate. Regulators have accepted external and synthetic control arms in narrow settings, mainly rare diseases and single-arm oncology submissions; in common cancers the concern is that treatment and supportive care drift faster than the model. Adoption is real but cautious.","status":"emerging","asOf":"2026-09-08","links":[{"label":"FDA guidance: externally controlled trials","url":"https://www.fda.gov/regulatory-information/search-fda-guidance-documents/considerations-design-and-conduct-externally-controlled-trials-drug-and-biological-products"}],"tags":["frontier","promising"],"related":["digital-twin-patient-models","mathematical-oncology"],"cancers":[],"sections":["ai-computation","drug-discovery"],"technologies":["ai-trial-matching","pathology-foundation-model"],"targets":[],"drugs":[],"companies":["tempus","owkin","foundation-medicine"],"institutions":[],"pathways":[],"terms":["real-world-evidence","basket-umbrella-platform"],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"principle":"A model predicts each participant's counterfactual outcome under control therapy; the prediction is used as a covariate or replaces part of the control arm.","strengths":["Fewer patients randomised to the inferior arm","Faster, cheaper trials in rare subgroups","Uses data already collected"],"limitations":["Bias when standard of care changes between eras","Regulatory acceptance is case by case","Model failure is invisible without a real control arm"]},"route":"/technologies/digital-twins-trials/","neighbours":{"technology":[{"id":"agent-based-tumour-models","kind":"technology","name":"Agent-based and multicellular simulations","route":"/technologies/agent-based-tumour-models/"},{"id":"ai-trial-matching","kind":"technology","name":"AI trial matching & clinical decision support","route":"/technologies/ai-trial-matching/"},{"id":"mathematical-oncology","kind":"technology","name":"Mathematical models of cancer (mathematical oncology)","route":"/technologies/mathematical-oncology/"},{"id":"pathology-foundation-model","kind":"technology","name":"Pathology & radiology foundation models","route":"/technologies/pathology-foundation-model/"},{"id":"digital-twin-patient-models","kind":"technology","name":"Patient digital twins","route":"/technologies/digital-twin-patient-models/"},{"id":"quantitative-systems-pharmacology","kind":"technology","name":"Quantitative systems pharmacology (QSP)","route":"/technologies/quantitative-systems-pharmacology/"}],"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"},{"id":"drug-discovery","kind":"section","name":"Drug Discovery Platforms","route":"/fronts/drug-discovery/"}],"company":[{"id":"foundation-medicine","kind":"company","name":"Foundation Medicine (Roche)","route":"/companies/foundation-medicine/"},{"id":"owkin","kind":"company","name":"Owkin","route":"/companies/owkin/"},{"id":"tempus","kind":"company","name":"Tempus AI","route":"/companies/tempus/"}],"term":[{"id":"basket-umbrella-platform","kind":"term","name":"Basket, umbrella, and platform trials","route":"/terms/basket-umbrella-platform/"},{"id":"bayesian-trial-design","kind":"term","name":"Bayesian trial design","route":"/terms/bayesian-trial-design/"},{"id":"master-protocol","kind":"term","name":"Master protocol (platform, basket and umbrella trials)","route":"/terms/master-protocol/"},{"id":"real-world-evidence","kind":"term","name":"Real-world evidence","route":"/terms/real-world-evidence/"},{"id":"response-adaptive-randomisation","kind":"term","name":"Response-adaptive randomisation","route":"/terms/response-adaptive-randomisation/"},{"id":"seamless-adaptive","kind":"term","name":"Seamless, adaptive and Bayesian trial designs","route":"/terms/seamless-adaptive/"}],"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"},{"id":"drug-discovery-roadmap","kind":"roadmap","name":"Drug discovery roadmap: screening in mice → maps of dependency → designing in silico","route":"/roadmaps/drug-discovery-roadmap/"},{"id":"frontier-2035","kind":"roadmap","name":"Radical oncology: what could change the war by 2035","route":"/roadmaps/frontier-2035/"},{"id":"trial-modernisation-roadmap","kind":"roadmap","name":"Trial modernisation roadmap: the randomised trial → platforms and adaptive designs → decentralised, pragmatic and always-on","route":"/roadmaps/trial-modernisation-roadmap/"}],"institution":[{"id":"cedars-sinai-cancer","kind":"institution","name":"Cedars-Sinai Cancer","route":"/institutions/cedars-sinai-cancer/"}],"trial":[{"id":"gbm-agile","kind":"trial","name":"GBM AGILE","route":"/trials/gbm-agile/"}]}}