Artificial Intelligence in Xenotransplantation: A Prioritized Roadmap for Early Clinical Translation, Opportunities and Challenges
Xenotransplantation · 2026-09 · 33 (5)
DOI: 10.1111/xen.70162 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Xenotransplantation, online erschienen am 26.08.2026. Verfasst von Kasra Shirini und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA. Hauptthemen laut MEDLINE: Transplantation, Heterologous, Artificial Intelligence, Heterografts. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Xenotransplantation represents a potential solution to the persistent global organ shortage, yet its clinical application remains stalled by complex immunologic responses, coagulation dysregulation, species‐specific biology, and infectious risks. Artificial intelligence (AI) could enhance safety, accelerate decision‐making, and enable precision medicine initiatives within this rapidly evolving field. However, effective implementation of AI in xenotransplantation requires approaches specifically adapted to the biological and operational complexities of cross‐species transplantation. Here, we present our suggestion of a prioritized roadmap for integrating AI into early clinical xenotransplantation, based on clinical need, data availability, technical readiness, feasibility of clinician‐supervised implementation, and potential impact on graft assessment and safety monitoring. Priority domains include digital pathology and imaging, machine perfusion–based viability monitoring, multimodal and multi‐omics detection of graft injury and rejection, and surveillance for potential xenozoonotic infections. One of the essential prerequisites to ensure the development of reliable AI in xenotransplantation is to develop standardized definitions of xenograft injury phenotypes and ground truth datasets, which in this emerging field are currently lacking. The limitations to the application of AI in xenotransplantation, which include the lack of clinical data, species‐specific differences, and delays in annotations and regulations, can be addressed via data sharing, federated learning, fairness, and validation. By combining gene‐edited donors and refined immunosuppression regimens with clinically supervised, auditable, and transplant‐specific, AI‐based support systems, xenotransplantation could be made safer and more reproducible in the clinical arena.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
- Department of Surgery, Duke University School of Medicine, Durham, North Carolina, USA.
- Paris Institute for Transplantation and Organ Regeneration (PITOR), Université Paris Cité, PARCC INSERM, Paris, France.
- Department of Surgery, University of Maryland School of Medicine, Baltimore, Maryland, USA.
ORCID-Profile: Raphael P H Meier
Zitieren
APA
Shirini, K., Hahn, Z., Ladowski, J. M., Schulick, A., Babadi, S., Loupy, A., Yamada, K., & Meier, R. P. H. (2026). Artificial Intelligence in Xenotransplantation: A Prioritized Roadmap for Early Clinical Translation, Opportunities and Challenges. Xenotransplantation, 33(5). https://doi.org/10.1111/xen.70162
Vancouver
Shirini K, Hahn Z, Ladowski JM, Schulick A, Babadi S, Loupy A, et al. Artificial Intelligence in Xenotransplantation: A Prioritized Roadmap for Early Clinical Translation, Opportunities and Challenges. Xenotransplantation. 2026;33(5). doi:10.1111/xen.70162
BibTeX
@article{Shirini2026,
author = {Shirini, Kasra and Hahn, Zoe and Ladowski, Joseph M and Schulick, Alexander and Babadi, Saghar and Loupy, Alexandre and Yamada, Kazuhiko and Meier, Raphael P H},
title = {Artificial Intelligence in Xenotransplantation: A Prioritized Roadmap for Early Clinical Translation, Opportunities and Challenges},
journal = {Xenotransplantation},
year = {2026},
volume = {33},
number = {5},
doi = {10.1111/xen.70162}
}
EUVIMED