Artificial intelligence in preclinical nonhuman primate xenotransplantation: bridging the gap from data complexity to clinical precision

Nonhuman primate (NHP) preclinical models remain an indispensable gateway for translating xenotransplantation into human clinical trials. These models generate high-dimensional immunological, physiological, behavioral, and histopathological datasets that are difficult to interpret with conventional analytical approaches and that limit the precision of translational inference. Artificial intelligence (AI) and machine learning (ML) may help address this complexity: computer vision can support continuous noninvasive behavioral phenotyping and pain assessment; anomaly detection algorithms can extract early warning signals from biosignal streams; multiomics integration can identify xenograft-specific biomarker signatures; digital twin frameworks may enable hypothesis-generating simulations of prospective human recipient responses; and explainable AI (XAI) can make model outputs more transparent and regulatory defensible. This review synthesizes current evidence across these domains, highlights methodological limitations, and proposes a research agenda through which AI-augmented NHP experimentation can become a bridge from preclinical data complexity to clinical precision in xenotransplantation. The framework also supports the ethical mandate of the 3Rs (Replacement, Reduction, and Refinement), aligning scientific rigor with animal welfare imperatives.