JMIR Publications

ABSTRACT

Background:

Artificial intelligence (AI) is a revolutionary upcoming tool yet to be fully integrated into several healthcare sectors, including medical imaging. AI can transform how medical imaging is conducted and interpreted, especially in cardio-oncology.

Objective:

This study aims to systematically review the available literature on the use of AI in cardio-oncology imaging to predict cardiotoxicity and describe the possible improvement of different imaging modalities that can be achieved if AI is successfully deployed to routine practice.

Methods:

We conducted a database search in PubMed, Ovid Medline, Cochrane Library, CINHAL and Google Scholar from inception to 2023 using the AI research assistant tool (Elicit) to search for original studies reporting AI outcomes in adult patients diagnosed with any cancer and undergoing cardiotoxicity assessment. Outcomes included incidence of cardiotoxicity, left ventricular ejection fraction (LVEF), risk factors associated with cardiotoxicity, heart failure, myocardial dysfunction, signs of cancer therapy-related cardiovascular toxicity, Echocardiography, and cardiac magnetic resonance imaging. Descriptive information about each study was recorded, including imaging technique, AI Model, outcomes, and limitations.

Results:

Seven studies conducted between 2018 and 2023 are included in this review. Most of these studies were conducted in the USA (71%), included breast cancer patients (86%), and used magnetic resonance imaging (MRI) as the imaging modality (57%). The quality assessment of the studies had an average of 86% compliance in all of the tool's sections.

Conclusions:

The review showed the potential of imaging-AI in improving clinical outcomes and early detection of cardiovascular occurrences in cancer patients undergoing treatment. As promising as these studies sound, further research is needed to validate the integration of AI into medical imaging and its deployment in routine practice.