Researchers at the Icahn School of Medicine Quantitative Assessment of Right Ventricular Function and Size Based on ECG at Mount Sinai have improved the evaluation of the heart’s right ventricle, which pumps blood to the lungs, by utilizing artificial intelligence (AI) in a ground-breaking study.
A deep learning-based ECG analysis tool is able to identify patients at high risk for poor right ventricular function. Areas deemed important by the AI for prediction are highlighted in increasing shades of red. Image Credit: ALMA
The research, which was carried out by a team employing AI-enabled electrocardiogram (AI-ECG) analysis, shows that electrocardiograms could accurately identify issues in the right side of the heart. This makes them a less complicated option than complex imaging technologies and could even enhance patient outcomes.
The results were published in the Journal of the American Heart Association’s online edition on December 29th, 2023.
We aimed to find a better way to assess the health of the heart’s right ventricle, focusing on its ability to pump blood and its size. Traditional methods fall short, which prompted us to explore AI-ECG analysis as a potential solution. This novel method could expedite the identification of heart problems, especially in the right ventricle, and potentially lead to earlier and more effective treatment. It holds particular importance for patients with congenital heart disease, who often face issues in the right ventricle.
Son Q. Duong MD, MS, Study Co-First Author and Assistant Professor, Pediatrics (Pediatric Cardiology), Icahn School of Medicine at Mount Sinai
Using harmonized data from 12-lead ECGs and cardiac magnetic resonance imaging (MRI) scans, the study built a deep-learning ECG (DL-ECG) model. It was tested on a sizable sample from the UK Biobank and verified at numerous medical centers within the Mount Sinai Health System. Its predictive power for cardiac problems and effect on patient survival rates were assessed.
This innovative approach departs significantly from traditional methods. Unlike other studies, this research predicts something not easily quantifiable by other common tests, such as the heart ultrasound.
Akhil Vaid, MD, Study Co-First Author and Clinical Instructor of Medicine (Data-Driven and Digital Medicine), Icahn School of Medicine at Mount Sinai
Although artificial intelligence is still in its infancy and cannot completely replace modern diagnostics, the researchers note that it does enable more accurate cardiac information to be obtained from widely used techniques. To guarantee the safety and proper application of the instrument, more work is required.
Furthermore, since the study’s projections rely on pre-existing ECG and MRI data, which have inherent limitations, they could differ among groups. The researchers issued a warning, noting that further study is necessary before applying it to routine clinical practice.
Study Senior author Girish Nadkarni, MD, MPH, Irene and Dr. Arthur M. Fishberg Professor of Medicine at Icahn Mount Sinai, Director of The Charles Bronfman Institute of Personalized Medicine, and System Chief of Data-Driven and Digital Medicine added, “Our findings mark a significant leap forward in right heart health assessment, offering a glimpse into a future where AI plays a pivotal role in early and accurate diagnosis. The study stands out for applying AI to standard ECG data, predicting right ventricular function and size numerically.”
Subsequent investigations will involve the external validation of the DL-ECG models in a range of populations, with the aim of verifying their clinical value and wider application in diseases such as cardiomyopathy, pulmonary hypertension, and congenital cardiac disease.
The study is titled “Quantitative prediction of right ventricular size and function from the electrocardiogram.”
The National Center for Advancing Translational Sciences (UL1TR004419) and the National Heart, Lung, and Blood Institute (R01HL155915) of the National Institutes of Health provided funding for this study.
Vy Thi Ha My, PhD; Liam R. Butler, BS; Joshua Lampert, MD; Robert H. Pass, MD; Alexander W. Charney, MD, PhD; Jagat Narula, MD, PhD; Rohan Khera, MD, MS (Yale School of Medicine, Yale School of Public Health, Yale-New Haven Hospital); Ankit Sakhuja, MBBS, MS; Hayit Greenspan, PhD; Bruce D. Gelb, MD; and Ron Do, PhD are the remaining study authors from Icahn Mount Sinai.
Journal Reference:
Duong, S. Q., et. al. (2023) Quantitative Prediction of Right Ventricular Size and Function From the ECG. Journal of the American Heart Association. doi:10.1161/JAHA.123.031671
Source: https://www.mountsinai.org/