Artificial Intelligence in the Advancement of Mechanical Circulatory Support and Cardiac Care: A Systematic Review of Its Role and Potential
Artificial Organs · 17.11.2026
DOI: 10.1111/aor.70263 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Artificial Organs, online erschienen am 17.11.2026. Verfasst von Emily R Woodland und 6 weiteren Autor:innen. Beteiligte Einrichtung: From the BioCirc Research Laboratory, School of Biomedical Engineering, Science, and Health Systems, Drexel University, Philadelphia, Pennsylvania, U…. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIH HHS, Office of Postsecondary Education, National Institutes of Health.
Abstract (Originalsprache)
Background
In recent years, there has been a notable surge in the ability of machines to perform complex and intelligent human‐centered tasks, particularly within the domain of cardiovascular health. Rapid advancements in artificial intelligence (AI) and machine learning (ML) algorithms reflect the considerable potential for such analyses to meaningfully extend into translational device development and clinical usage of medical devices, especially mechanical circulatory support (MCS) therapies. Here, we investigate and report the applications, limitations, and strategies in which AI is currently being employed in MCS and the potential opportunities of AI approaches to advance the field of MCS.
Methods
To effectively assess the scope and impact of AI in MCS, we conducted a systematic literature review. A comprehensive search of 4 recognized research databases (PubMed, Google Scholar, Ovid MEDLINE, and ProQuest) was performed using this Boolean string: “(Artificial Intelligence) AND (AI) AND (Mechanical Circulatory Support) AND (MCS) NOT (Heart Transplant) NOT (Cardiogenic Shock) NOT (Critical Care).” This strategy was designed to identify the application of AI in MCS only. Database search results were then screened by titles and abstracts, followed by full‐text eligibility assessment and duplicate removal. Following these screening and eligibility steps, 30 of the 328 identified articles remained for inclusion.
Results
Most relevant publications covered two main subjects: the prediction and management of postoperative outcomes, and the development of personalized device‐patient matching and timing. Across the reviewed studies, AI/ML models demonstrated promising performance in study‐specific predictions of complications, recovery‐related outcomes, and survival and were investigated as tools to support clinical decision‐making. Barriers to broad implementation of AI include the necessity for sizable, high‐quality datasets to achieve algorithm training benchmarks, the lack of organized and complete databases, such as INTERMACS, and limited computational resources. Emerging frontiers of MCS recognize the potential for AI and ML techniques to refine image recognition capabilities, diagnostic assessment, device placement, and post‐implantation monitoring approaches in the future.
Conclusions
AI‐driven approaches demonstrate a promising convergence of computational power and clinical expertise, with the potential to support more personalized, efficient, and informed management of MCS patients. However, the current evidence remains largely exploratory, and broad implementation will require robust clinical validation together with attention to data integrity, model accuracy, resource access, and clinical acceptance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- From the BioCirc Research Laboratory, School of Biomedical Engineering, Science, and Health Systems, Drexel University, Philadelphia, Pennsylvania, USA.
- Computer Science, College of Computing and Informatics, Drexel University, Philadelphia, Pennsylvania, USA.
- Cardiac Surgery, Thomas Jefferson University, Philadelphia, Pennsylvania, USA.
- Biomedical Engineering, College of Engineering, University of Arizona, Tucson, Arizona, USA.
- Materials Science Engineering, College of Engineering, University of Arizona, Tucson, Arizona, USA.
- Cardiology, College of Medicine, University of Arizona, Tucson, Arizona, USA.
ORCID-Profile: Emily R Woodland, Preetha Chatterjee, Amy L Throckmorton
Förderung
- NIH HHS
- Office of Postsecondary Education
- National Institutes of Health
Zitieren
APA
Woodland, E. R., Matlis, G. C., Chatterjee, P., Palazzolo, T. C., Tchantchaleishvili, V., Slepian, M. J., & Throckmorton, A. L. (2026). Artificial Intelligence in the Advancement of Mechanical Circulatory Support and Cardiac Care: A Systematic Review of Its Role and Potential. Artificial Organs. https://doi.org/10.1111/aor.70263
Vancouver
Woodland ER, Matlis GC, Chatterjee P, Palazzolo TC, Tchantchaleishvili V, Slepian MJ, et al. Artificial Intelligence in the Advancement of Mechanical Circulatory Support and Cardiac Care: A Systematic Review of Its Role and Potential. Artificial Organs. 2026. doi:10.1111/aor.70263
BibTeX
@article{Woodland2026,
author = {Woodland, Emily R and Matlis, Giselle C and Chatterjee, Preetha and Palazzolo, Thomas C and Tchantchaleishvili, Vakhtang and Slepian, Marvin J and Throckmorton, Amy L},
title = {Artificial Intelligence in the Advancement of Mechanical Circulatory Support and Cardiac Care: A Systematic Review of Its Role and Potential},
journal = {Artificial Organs},
year = {2026},
doi = {10.1111/aor.70263}
}
EUVIMED