Machine learning and artificial intelligence in cardiac transplantation: A systematic review

Abstract

Background This review aims to systematically evaluate the currently available evidence investigating the use of artificial intelligence (AI) and machine learning (ML) in the field of cardiac transplantation. Furthermore, based on the challenges identified we aim to provide a series of recommendations and a knowledge base for future research in the field of ML and heart transplantation. Methods A systematic database search was conducted of original articles that explored the use of ML and/or AI in heart transplantation in EMBASE, MEDLINE, Cochrane database, and Google Scholar, from inception to November 2021. Results Our search yielded 237 articles, of which 13 studies were included in this review, featuring 463 850 patients. Three main areas of application were identified: (1) ML for predictive modeling of heart transplantation mortality outcomes; (2) ML in graft failure outcomes; (3) ML to aid imaging in heart transplantation. The results of the included studies suggest that AI and ML are more accurate in predicting graft failure and mortality than traditional scoring systems and conventional regression analysis. Major predictors of graft failure and mortality identified in ML models were: length of hospital stay, immunosuppressive regimen, recipient's age, congenital heart disease, and organ ischemia time. Other potential benefits include analyzing initial lab investigations and imaging, assisting a patient with medication adherence, and creating positive behavioral changes to minimize further cardiovascular risk. Conclusion ML demonstrated promising applications for improving heart transplantation outcomes and patient‐centered care, nevertheless, there remain important limitations relating to implementing AI into everyday surgical practices.

Clinical Decision Support Systems Used in Transplantation: Are They Tools for Success or an Unnecessary Gadget? A Systematic Review

“…A large number of transplant-related tools or predictive models (especially as new technologies in AI emerge) are being created; however, the pipeline for implementing these tools into clinical practice is extremely sparse. [70][71][72][73] They are generally not implemented in a prospective manner in real patient cohorts to assess the impact of these tools on clinical outcomes. Furthermore, especially within the AI-based CDSS tools, there is sparse analysis of the explainability of these tools and individualized analysis of end-user requirements for the transparency of such clinical programs.…”

Role of HLA in cardiothoracic transplantation

“…Although algorithms to identify B or T cell-mismatched HLA epitopes may be one of the best tools developed in the modern era, it is crucial to address the ethical governance issues surrounding their utilization, while B and T cell-mismatched HLA epitope identification algorithms offer promising medical benefits, addressing ethical governance issues is essential to protect individuals' rights, privacy, and well-being, as well as to promote fairness and responsible use of these tools in healthcare and research. [11][12][13]19 HLAMatchmaker can calculate the number of eplet mismatches present in the donor but not in the recipient. The newly developed Predicted Indirectly Recognizable Epitope tool 14 may be useful for this purpose; however, it is not applicable for individual patients.…”

Understanding Tricuspid Regurgitation Post Cardiac Transplantation; Why “Anatomical” and “Functional” Just Won’t Cut It

“…There are new artificial intelligence-based algorithms to help with patient selection, with the final decision still resting with the transplant cardiologist. 54 This may help with the multiple factors that go into donor: recipient matching.…”