The traditional Greek philosopher and polymath Aristotle once concluded that the human heart is tri-chambered and that it was the only most significant organ in your complete body, governing motion, sensation, and thought.
Today, we all know that the human heart actually has 4 chambers and that the brain largely controls motion, sensation, and thought. But Aristotle was correct in observing that the guts is a crucial organ, pumping blood to the remaining of the body to succeed in other vital organs. When a life-threatening condition like heart failure strikes, the guts step by step loses the flexibility to provide other organs with enough blood and nutrients that allows them to operate.
Researchers from MIT and Harvard Medical School recently published an open-access paper in , introducing a noninvasive deep learning approach that analyzes electrocardiogram (ECG) signals to accurately predict a patient’s risk of developing heart failure. In a clinical trial, the model showed results with accuracy comparable to gold-standard but more-invasive procedures, giving hope to those vulnerable to heart failure. The condition has recently seen a pointy increase in mortality, particularly amongst young adults, likely as a consequence of the growing prevalence of obesity and diabetes.
“This paper is a culmination of things I’ve talked about in other venues for several years,” says the paper’s senior creator Collin Stultz, director of Harvard-MIT Program in Health Sciences and Technology and affiliate of the MIT Abdul Latif Jameel Clinic for Machine Learning in Health (Jameel Clinic). “The goal of this work is to discover those that are beginning to get sick even before they’ve symptoms so you can intervene early enough to stop hospitalization.”
Of the guts’s 4 chambers, two are atria and two are ventricles — the best side of the guts has one atrium and one ventricle, and vice versa. In a healthy human heart, these chambers operate in a rhythmic synchrony: oxygen-poor blood flows into the guts via the best atrium. The suitable atrium contracts and the pressure generated pushes the blood into the best ventricle where the blood is then pumped into the lungs to be oxygenated. The oxygen-rich blood from the lungs then drains into the left atrium, which contracts, pumping the blood into the left ventricle. One other contraction follows, and the blood is ejected from the left ventricle via the aorta, flowing into veins branching out to the remaining of the body.
“When the left atrial pressures turn out to be elevated, the blood drain from the lungs into the left atrium is impeded since it’s a higher-pressure system,” Stultz explains. Along with being a professor of electrical engineering and computer science, Stultz can also be a practicing cardiologist at Mass General Hospital (MGH). “The upper the pressure within the left atrium, the more pulmonary symptoms you develop — shortness of breath and so forth. Because the best side of the guts pumps blood through the pulmonary vasculature to the lungs, the elevated pressures within the left atrium translate to elevated pressures within the pulmonary vasculature.”
The present gold standard for measuring left atrial pressure is true heart catheterization (RHC), an invasive procedure that requires a skinny tube (the catheter) attached to a pressure transmitter to be inserted into the best heart and pulmonary arteries. Physicians often prefer to evaluate risk noninvasively before resorting to RHC, by examining the patient’s weight, blood pressure, and heart rate.
But in Stultz’s view, these measures are coarse, as evidenced by the indisputable fact that one-in-four heart failure patients is readmitted to the hospital inside 30 days. “What we’re searching for is something that provides you information like that of an invasive device, aside from a straightforward weight scale,” Stultz says.
To be able to gather more comprehensive information on a patient’s heart condition, physicians typically use a 12-lead ECG, during which 10 adhesive patches are stuck onto the patient and linked with a machine that produces information from 12 different angles of the guts. Nevertheless, 12-lead ECG machines are only accessible in clinical settings they usually are also not typically used to evaluate heart failure risk.
As an alternative, what Stultz and other researchers propose is a Cardiac Hemodynamic AI monitoring System (CHAIS), a deep neural network able to analyzing ECG data from a single lead — in other words, the patient only must have a single adhesive, commercially-available patch on their chest that they will wear outside of the hospital, untethered to a machine.
To check CHAIS with the present gold standard, RHC, the researchers chosen patients who were already scheduled for a catheterization and asked them to wear the patch 24 to 48 hours before the procedure, although patients were asked to remove the patch before catheterization took place. “While you get to inside an hour-and-a-half [before the procedure], it’s 0.875, so it’s very, superb,” Stultz explains. “Thereby a measure from the device is equivalent and offers you a similar information as should you were cathed in the following hour-and-a-half.”
“Every cardiologist understands the worth of left atrial pressure measurements in characterizing cardiac function and optimizing treatment strategies for patients with heart failure,” says Aaron Aguirre SM ’03, PhD ’08, a cardiologist and important care physician at MGH. “This work is significant since it offers a noninvasive approach to estimating this essential clinical parameter using a widely available cardiac monitor.”
Aguirre, who accomplished a PhD in medical engineering and medical physics at MIT, expects that with further clinical validation, CHAIS shall be useful in two key areas: first, it is going to aid in choosing patients who will most profit from more invasive cardiac testing via RHC; and second, the technology could enable serial monitoring and tracking of left atrial pressure in patients with heart disease. “A noninvasive and quantitative method will help in optimizing treatment strategies in patients at home or in hospital,” Aguirre says. “I’m excited to see where the MIT team takes this next.”
But the advantages aren’t just limited to patients — for patients with hard-to-manage heart failure, it becomes a challenge to maintain them from being readmitted to the hospital with no everlasting implant, taking over extra space and more time of an already beleaguered and understaffed medical workforce.
The researchers have one other ongoing clinical trial using CHAIS with MGH and Boston Medical Center that they hope to conclude soon to start data evaluation.
“For my part, the actual promise of AI in health care is to offer equitable, state-of-the-art care to everyone, no matter their socioeconomic status, background, and where they live,” Stultz says. “This work is one step towards realizing this goal.”
