New Study Validates Automated Decision-Making Systems for Analyzing Ultrasound Images

Researchers have presented the results of a study that evaluated the use of automated echocardiography decision-making systems to help clinicians assess heart disease.

Researchers designed an automated machine learning algorithm that analyzes information from a large number of (Two-dimensional) 2-D ultrasound images and were able to differentiate between athlete’s hearts that were enlarged as a result of Hypertrophic Cardiomyopathy (HCM) from those that were enlarged by normal thickening of the heart muscle. HCM is one of the most common causes of sudden cardiac death in athletes.

Researchers at the Icahn School of Medicine at Mount Sinai Hospital (SMMS; New York, NY, USA) carried out the research. The study titled, “Automated Morphological and Functional Phenotyping of Human Heart with Feature Tracking of 2-D Echocardiographic Images Using Machine Learning Algorithms,” was presented at the 26th Annual Scientific Sessions of the American Society of Echocardiography (ESA).

Primary investigator Sukrit Narula, medical student at Icahn School of Medicine at Mount Sinai, said, “I am confident that the use of machine learning algorithms will help create a real-time clinical guidance system for interpreting echocardiographic images and this will be crucial for standardization of interpretation for novice readers and new users of cardiac ultrasound. I am fortunate to be part of Dr. Sengupta's team and their efforts in this project, especially senior investigators like Dr. Dudley, Dr. Khader and Dr. Omar who have helped bring the first steps of this effort to fruition.”

Related Links:
Icahn School of Medicine at Mount Sinai Hospital
American Society of Echocardiography