# Early Implications for Solid Organ Transplantation With the Use of Artificial Intelligence From a Bibliometric Perspective

## TL;DR

This paper uses bibliometric analysis to explore how AI is being applied in solid organ transplantation, highlighting trends and potential benefits for patient care.

## Contribution

The study provides a comprehensive bibliometric analysis of AI applications in solid organ transplantation, identifying key research trends and institutions.

## Key findings

- The United States leads in AI-related publications and collaborations in solid organ transplantation.
- Machine learning and deep learning are the most commonly used AI techniques in this field.
- AI models show potential to improve patient outcomes by integrating diverse data types.

## Abstract

Artificial intelligence (AI) is increasingly transforming health care, particularly in solid organ transplantation, where it addresses complex challenges such as organ allocation, graft rejection prediction, and immunosuppressive management. This bibliometric analysis evaluated the scientific impact and evolution of AI applications in kidney, liver, heart, and lung transplantation. A comprehensive search across PubMed, Scopus, and Web of Science identified 2384 publications from 1989 to 2025, of which 815 met inclusion criteria after double-blind screening with Rayyan AI. Coauthorship, keyword co-occurrence, and collaboration networks were analyzed using VOSviewer and Bibliometrix. The United States led in publications, citations, and collaboration strength, with Mayo Clinic emerging as the most productive institution, followed by China. Machine learning, expert systems, and deep learning were the most frequently applied AI techniques, whereas kidney and liver transplantation were the most extensively studied. Thematic clusters included rejection prediction, patient survival, organ allocation, postoperative monitoring, and immunosuppression personalization. Artificial intelligence–driven models integrate clinical, immunological, histological, and imaging data to enhance predictive accuracy, support clinical decision making, and improve graft and patient outcomes. Although many of these models remain under validation, early findings indicate strong potential to optimize patient care and surgical outcomes. This study highlights global research trends and emphasizes the need for interdisciplinary collaboration to develop context-specific AI tools. Moreover, promoting bibliometric literacy among health care professionals may strengthen evidence-based research and accelerate the responsible integration of AI into transplant medicine.