Traditional methods to assess the health of the heart’s right ventricle which sends blood to the lungs usually fall short. In a milestone study, researchers have leveraged the power of artificial intelligence (AI) to enhance the assessment of the heart’s right ventricle.

Researchers from the Icahn School of Medicine at Mount Sinai (New York, NY, USA) examined the efficacy of AI-enabled electrocardiogram (AI-ECG) analysis in detecting right-side heart complications. The study utilized a deep-learning ECG (DL-ECG) model, which was trained with harmonized data from 12-lead ECGs and cardiac magnetic resonance imaging (MRI) measurements. Conducted on an extensive dataset from the UK Biobank, the study's findings were further validated across various centers within the Mount Sinai Health System. The research focused on gauging the model's precision in identifying heart ailments and its influence on the survival rates of patients.

According to the researchers, while AI provides enhanced cardiac insights from widely used tools like ECGs, this approach is still in its infancy and isn't meant to substitute more advanced diagnostic methods. They have emphasized the need for additional studies to confirm the tool's efficacy and safe integration into clinical practices. Moreover, the team highlighted that the predictive results could vary among different demographics, depending on the quality and scope of the ECG and MRI data employed. The researchers plan to perform comprehensive validations of the DL-ECG models across diverse populations to ensure its widespread relevance and to verify its clinical effectiveness in diagnosing conditions such as pulmonary hypertension, congenital heart defects, and various cardiomyopathies.

“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,” said senior author Girish Nadkarni, MD, MPH, Irene and Dr. Arthur M. Fishberg Professor of Medicine at Icahn Mount Sinai.

“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,” added co-first author Son Q. Duong MD, MS, Assistant Professor of Pediatrics (Pediatric Cardiology) at Icahn Mount Sinai. 

http://www.gzjiayumed.com/en/index.asp