Researchers developed computational “digital twins” of ex vivo human lungs using a large clinical ex vivo lung perfusion (EVLP) dataset, and reported that the models can assess therapeutic efficacy. The study reports that lung digital twins captured more than 75 parameters spanning physiology, biochemistry, imaging, transcriptomics, metabolomics, and proteomics. The work further showed that digital twins could accurately model therapeutic responses by directly comparing model outputs to experimental results from EVLP lungs treated with alteplase. The article positions EVLP as a data-rich route to move digital twin methods beyond disease-only prognostic models toward interventions and comparative effectiveness evaluation. For the biotech and medtech ecosystem, the near-term relevance is whether similar frameworks can support preclinical-to-translational decisions—such as prioritizing therapeutics, optimizing dosing hypotheses, or de-risking trial design by using multimodal organ-level response modeling.