A revolutionary deep neural network may soon replace invasive procedures for monitoring heart health, using electrocardiogram signals to predict a patient’s risk of developing heart failure.
A revolutionary deep neural network called CHAIS may soon replace invasive procedures like catheterization as the new gold standard for monitoring heart health. Developed by researchers from MIT and Harvard Medical School, this noninvasive approach analyzes electrocardiogram (ECG) signals to accurately predict a patient’s risk of developing heart failure.
Heart failure mortality rates were once on the decline, but 2012 marked a reversal, followed by a dramatic increase in 2020 and 2021. This alarming trend is attributed to the growing prevalence of obesity and diabetes among young adults. The condition has severe consequences, including hospitalization and even death.
Heart failure is a chronic condition where the heart cannot pump enough blood to meet the body's needs.
According to the American Heart Association, it affects over 6 million people in the United States alone.
The mortality rate for heart failure patients varies depending on age and other health conditions.
Studies show that nearly half of patients with heart failure die within five years of diagnosis.
In fact, heart failure is a leading cause of hospitalization and death worldwide, accounting for over 1 million deaths annually.
In a healthy human heart, four chambers operate in synchrony: two atria and two ventricles. However, when left atrial pressures become elevated, it can lead to pulmonary symptoms such as shortness of breath. The current gold standard for measuring left atrial pressure is right heart catheterization (RHC), an invasive procedure that requires a thin tube to be inserted into the right heart and pulmonary arteries.

Researchers propose a Cardiac Hemodynamic AI monitoring System (CHAIS), a deep neural network capable of analyzing ECG data from a single lead. This means patients only need to wear a single adhesive patch on their chest, which can be worn outside of the hospital. In a clinical trial, ‘results with accuracy comparable to gold-standard procedures’ were shown.
CHAIS has the potential to aid in selecting patients who will most benefit from more invasive cardiac testing via RHC. Additionally, it could enable serial monitoring and tracking of left atrial pressure in patients with heart disease. This noninvasive approach can help optimize treatment strategies in patients at home or in hospital.
The researchers’ goal is to provide equitable, state-of-the-art care to everyone, regardless of their socioeconomic status, background, and where they live. ‘This technology has the potential to revolutionize heart failure prevention and treatment.’ With further clinical validation, this technology has the potential to revolutionize heart failure prevention and treatment.
Heart failure occurs when the heart cannot pump enough 'blood' to meet the body's needs.
According to the American Heart Association, over 6 million adults in the US have heart failure.
High blood pressure is a leading cause of heart failure, affecting nearly half of all cases.
Other risk factors include diabetes, high cholesterol, smoking, and family history.
Regular exercise, a balanced diet, and stress management can help prevent heart failure.
Additionally, controlling 'blood pressure' through medication and lifestyle changes can significantly reduce the risk of developing heart failure.
The researchers are currently conducting another ongoing clinical trial using CHAIS with MGH and Boston Medical Center. They hope to conclude soon to begin data analysis. This work is a culmination of years of research and development, and its impact could be felt far beyond the medical community.