A prioritized roadmap for integrating AI into early clinical xenotransplantation is presented, based on clinical need, data availability, technical readiness, feasibility of clinician‐supervised implementation, and potential impact on graft assessment and safety monitoring.
Abstract
ABSTRACT 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.
It is argued that formation of a tumour-intrinsic niche is a prerequisite for BRAF-mutant CRC seeding to distant organs and that interference with niche formation may help avoid metastatic relapse.
J. Bugter, L. El Bouazzaoui, E. Küçükköse et al.· bioRxiv· 2 citations
It is concluded that bridging the gap between foundational CRISPR research and its real-world applications is imperative and future efforts should focus on democratizing tools via open-source platforms, advancing delivery systems, and fostering sustainable innovation through synthetic biology integration to fully realize the transformative potential of genome editing in organisms beyond model organisms.
S. Sarsaiya, Archana Jain, Jishuang Chen et al.· Biotechnology Advances· 2 citations
A virus-like particle (VLP)-based toolkit that delivers diverse CRISPR editing modalities to human monocytes, macrophages and dendritic cells with high efficiency while preserving viability and innate immune responsiveness is presented.
Hyuncheol Jung, Pascal Devant, Carter Ching et al.· Nature Biotechnology· 0 citations
Findings provide direct functional evidence that szl regulates median caudal patterning in goldfish and suggest that szl-dependent modulation of the Chordin/BMP network can generate twin-tail-like caudal morphology.
Huijuan Li, Xiaoying Zhang, Xiaowen Wang et al.· International Journal of Mol...· 0 citations
Background and Aims
Cardiovascular diseases (CVDs) remain the leading cause of global morbidity and mortality, encompassing coronary artery disease, hypertension, heart failure, and cerebrovascular disorders. The global burden of CVD continues to rise, driven by complex interactions among endothelial dysfunction, oxidative stress, inflammation, genetic predisposition, and lifestyle-related risk factors. This review aims to provide a comprehensive overview of the epidemiology, pathophysiology, risk factors, and emerging therapeutic approaches for CVD, highlighting recent advances in precision medicine and phytotherapy.
Methods
A comprehensive literature search was conducted using PubMed, ScienceDirect, and Google Scholar databases. Keywords included "cardiovascular disease," "Atherosclerosis," "Pathophysiology," "Risk Factors," "Treatment," "Hyperglycemia," and "Hypertension." Approximately 300 publications were initially identified. Following title, abstract, and full-text screening, 156 relevant articles were selected for inclusion. About 85% of the reviewed literature was published between 2020 and 2025, while the remaining 15% originated from 2016 to 2019.
Results
The review demonstrates a substantial increase in the global burden of CVDs, with prevalence nearly doubling between 1990 and 2019 and mortality continuing to rise worldwide. Atherosclerosis emerged as the primary pathological basis of ischemic cardiovascular disorders, driven by endothelial dysfunction, oxidative stress, inflammatory cytokines, and vascular remodeling. Major modifiable risk factors include hypertension, smoking, diabetes, dyslipidemia, obesity, unhealthy diet, alcohol consumption, and physical inactivity, while age, sex, and genetic susceptibility contribute to disease risk. Emerging therapeutic strategies such as PCSK9 inhibitors, dual SGLT1/2 inhibitors, siRNA-based therapies, CRISPR/Cas9 genome editing, and anti-inflammatory biologics show promising clinical outcomes. Additionally, medicinal plants including Astragalus membranaceus, Citrus bergamia, Hibiscus sabdariffa, and Olea europaea exhibit cardioprotective effects.
Conclusion
CVD remains a significant global health challenge requiring multifaceted management strategies. The integration of conventional pharmacotherapy, precision medicine, gene-based interventions, and evidence-based phytotherapeutics offers promising opportunities to improve cardiovascular outcomes and reduce the growing global disease burden.
Nawfal Hasan Siam, Umme Halima Mithila, S. Tisha et al.· Health Science Reports· 0 citations
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
MIT News · Artificial Intelligence· news.mit.eduAug 17, 2026