Reviewed by Danielle Ellis, B.Sc.Sep 9 2024
A study published in Circulation: Cardiovascular Quality and Outcomes by Yale School of Medicine suggests that an AI tool could use ECG images to predict the likelihood of cardiac dysfunction in cancer patients.
Image Credit: Yale School of Medicine
There are certain treatments for breast cancer and lymphomas, such as anthracyclines and trastuzumab, that have cardiotoxic effects. 1 in 10 individuals receiving these drugs individually, and nearly 1 in 3 using the drugs in combination, have adverse cardiac reactions.
Rohan Khera, MD, Study Senior Authors, Assistant Professor of Medicine and Director, Cardiovascular Data Science (CarDS) Lab, School of Medicine, Yale University
After identifying 1,550 patients who had undergone anthracyclines or trastuzumab for breast cancer or non-Hodgkin lymphoma, researchers used an AI model of left ventricular systolic dysfunction (LVSD) to classify them as low-, intermediate-, or high-risk.
According to the researchers, patients in the high-risk group had 3.4 times the chance of cardiac dysfunction following cancer treatment, as well as 13.5 times the risk of having a left ventricular ejection fraction (LVEF) less than 40%.
The novel AI-powered strategy might aid in making safe treatment decisions for patients with breast cancer or non-Hodgkin lymphoma who are at risk of heart failure, particularly for doctors in low-income settings.
Khera added, “Identifying those at heightened risk on a simple tool like an ECG can allow such risk assessment to be extended across low- and high-resource settings and substantially reduce the burden for risk assessment.”
Researchers believe AI models have the potential to improve diagnoses and care throughout this industry.
“We were able to find a way to provide information that typically required an advanced test by using AI applied to a simple and scalable diagnostic,” Khera further stated.
Evangelos K. Oikonomou, study first author and fellow in cardiovascular medicine, added, “These signatures are not discernable to even experts, highlighting the role of AI in augmenting human capacity.”
The other study authors are Veer Sangha, Lovedeep S. Dinghra, Arya Aminorroaya, Andreas Coppi, Harlan M. Krumholz, and Lauren A. Baldassarre.
Journal Reference:
Oikonomou, E. K., et. al. (2024) Artificial Intelligence-Enhanced Risk Stratification of Cancer Therapeutics-Related Cardiac Dysfunction Using Electrocardiographic Images. Circulation: Cardiovascular Quality and Outcomes. doi.org/10.1161/CIRCOUTCOMES.124.011504