Related Experiment Video
Updated: Sep 7, 2025
06:45
A Modified Cuff Technique for Mouse Cervical Heterotopic Heart Transplantation Model
Published on: February 7, 2022
3.4K
Machine learning and artificial intelligence in cardiac transplantation: A systematic review
Vinci Naruka1,2, Arian Arjomandi Rad2, Hariharan Subbiah Ponniah2
1Department of Cardiothoracic Surgery, Imperial College NHS Trust, Hammersmith Hospital, London, UK.
Artificial Organs
|June 20, 2022
Summary
Artificial intelligence (AI) and machine learning (ML) show promise in predicting heart transplant outcomes, outperforming traditional methods. Further research is needed to overcome implementation challenges in clinical practice.
Area of Science:
- Cardiology
- Medical Informatics
- Artificial Intelligence
Background:
- Growing interest in artificial intelligence (AI) and machine learning (ML) applications within cardiac transplantation.
- Need for systematic evaluation of existing evidence on AI/ML in heart transplantation.
- Identification of challenges and recommendations for future research.
Purpose of the Study:
- To systematically review the evidence on AI and ML in heart transplantation.
- To identify key applications and challenges of AI/ML in this field.
- To provide recommendations for future research and knowledge base development.
Main Methods:
- Systematic database search of EMBASE, MEDLINE, Cochrane, and Google Scholar.
- Inclusion of original articles on ML/AI in heart transplantation from inception to November 2021.
- Review of 13 studies encompassing 463,850 patients.
Main Results:
- AI and ML applications identified in predictive modeling of mortality, graft failure, and imaging analysis.
- AI/ML models demonstrated higher accuracy in predicting graft failure and mortality compared to traditional methods.
- Key predictors identified include hospital stay, immunosuppression, recipient age, congenital heart disease, and ischemia time.
Conclusions:
- Machine learning shows significant potential for enhancing heart transplantation outcomes and patient care.
- AI/ML tools can aid in analyzing investigations, medication adherence, and behavioral changes.
- Implementation of AI into surgical practice faces notable limitations that require further investigation.
