Left ventricular (LV) systolic dysfunction is a medical condition characterized by a weakness in the heart's major chamber that significantly diminishes the heart's pumping capacity, often leading to frequent hospitalizations and doubling the risk of premature death. While this condition can be prevented with early detection and timely medication initiation, identifying the disease before the onset of symptoms has remained a challenge. Without the aid of an echocardiogram or magnetic resonance imaging (MRI) scan, a cardiologist cannot diagnose patients with LV dysfunction. Broad screening for this disorder is often limited due to technological constraints and the availability of expertise. However, the electrocardiogram (ECG) is the most globally accessible diagnostic test in cardiovascular clinical practice. Now, a novel deep-learning application offers an automated screening method for LV systolic dysfunction.

A team of researchers at the Yale School of Medicine (New Haven, CT, USA) has devised a new artificial intelligence (AI)-based method for ECG interpretation intended for worldwide use. Their design incorporated nearly 400,000 ECGs paired with data on heart dysfunction from imaging tests. The algorithm was tested across various formats using data from several US clinics and hospitals, as well as from a large community cohort in Brazil.

“We demonstrate that a simple photo or scanned image of a 12-lead ECG, the most well-recognized and easily obtained cardiac test, can provide key insights on cardiac structure and function disorders,” said Rohan Khera, MD, MS, and his team from the Cardiovascular Data Science Lab (CarDS) Lab. "This opens up the possibility to finally bring a screening tool for such disorders that affect up to one in 20 adults globally. Their diagnosis is frequently delayed as advanced testing is either unavailable or only reserved for those with symptomatic disease. Now we can identify these patients with a simple web-based or smartphone application.”

“Our AI tool allows early diagnosis and treatment and also identifies those at future risk of developing LV dysfunction,” added Khera. “The findings represent our ongoing effort to make application of AI-driven advanced ECG inference accessible.”

“Our approach creates a super-reader of ECG images - identifying signatures of LV systolic dysfunction, which the human eye cannot accurately decipher,” said Veer Sangha, the first author of the study, a member of the CarDS Lab, and a Rhodes Scholar. 

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