The current state of artificial intelligence in cardiac transplantation

Purpose of review The field of heart transplantation is a complex practice that combines both science and art to optimize the quality and quantity of an organ transplant recipient's life span. In the current age of Transplant Medicine there are many limiting factors that prevent potentially usable organs to be transplanted in addition to the many unknown factors in assessing the risk of posttransplant complications in a proactive manner. This review focuses on the current state, and potential use, and implementation of artificial intelligence technologies in the field of heart transplantation. Furthermore, the utilization of predictive algorithms to assess donor quality, graft function, posttransplant complications and prediction of high-risk complications will be discussed. Artificial intelligence technologies in the pretransplant population is also explored. Recent findings Artificial intelligence process use has been increasing over the past decade. Early adoption in radiology and laboratory medicine have shown promise for future applications. Implementation of nascent technologies within the field of transplant medicine remains in its infancy. Cardiac and renal medicine have been recent focuses of large-scale artificial intelligence projects because of the wealth of data, the main limiting factor for producing accurate models. Understanding the true role of artificial intelligence in medicine is key - and has been divided into three areas of focus: data quality, interpretation, and clinical application. These areas allow the clinician to translate problems facing patients into algorithms utilized by data scientists to create solutions, which may provide in-depth analysis and detection of relationships not immediately clear. Although some published data has led to commercial products for cardiac, diabetic, and dermatologic applications -- widespread adoption remains limited to specialized centers. Artificial intelligence applications with clinically relevant models in transplant medicine have the potential to optimize organ utilization, prediction of complications, and potential pretransplant management, which may mitigate the need for transplant. Further translational projects are under development at major centers, with proof of concepts demonstrating validity and safety in the clinical setting. Limiting factors of infrastructure, expertise, and data availability continue to be addressed. Ongoing efforts for commercialization and large-scale trials will provide a foundation for the development of artificial intelligence applications in transplant medicine.