[Adobe Stock Image of a heart by NgoHong]
The researchers published an open-access paper in Nature Communications Medicine introducing their approach that analyzes electrocardiogram (ECG) signals to accurately predict a patient’s risk of developing heart failure. A clinical trial demonstrated accuracy comparable to the gold-standard, more invasive procedures available.
Senior author Collin Stultz, director of the Harvard-MIT Program in Health Sciences and Technology and affiliate of the MIT Abdul Latif Jameel Clinic for Machine Learning in Health (Jameel Clinic), said in an MIT blog post that the researchers aimed to identify those who are starting to get sick even before they have symptoms to intervene early enough to prevent hospitalization.
Currently, the gold standard for measuring left atrial pressure — right heart catheterization (RHC) — is an invasive procedure that requires a catheter attached to a pressure transmitter to be inserted into the right heart and pulmonary arteries. MIT says physicians often prefer to assess risk noninvasively before resorting to RHC. They can do so by examining the patient’s weight, blood pressure and heart rate.
According to Stultz, one in four heart failure patients experiences readmission to the hospital within 30 days because of the shortcomings of these methods.
“What we are seeking is something that gives you information like that of an invasive device, other than a simple weight scale,” Stultz said.
Rather than a typical 12-lead ECG — only accessible in clinical settings and typically not used to assess heart failure risk — Stultz and the team propose a Cardiac Hemodynamic AI monitoring System (CHAIS). This deep neural network can analyze ECG data from a single lead. This means a patient only requires a single adhesive, commercially available patch on their chest. They can wear it outside the hospital, too, untethered to a machine.
The researchers selected patients already scheduled for a catheterization and asked them to wear the patch 24 to 48 hours before the procedure to compare CHAIS with RHC. They asked the patients to remove the patch before catheterization took place.
“Every cardiologist understands the value of left atrial pressure measurements in characterizing cardiac function and optimizing treatment strategies for patients with heart failure,” said Aaron Aguirre, a cardiologist and critical care physician at MGH. “This work is important because it offers a noninvasive approach to estimating this essential clinical parameter using a widely available cardiac monitor.”
According to MIT, Aguirre expects CHAIS to offer benefits in helping to select patients who will most benefit from more invasive cardiac testing via RHC, then enable serial monitoring and tracking of left atrial pressure in patients with heart disease. Aguirre says a noninvasive, quantitative method could help optimize treatment strategies for patients both at home and in the hospital.
Additionally, the researchers have another ongoing clinical trial using CHAIS with MGH and Boston Medical Center that they hope to conclude soon to begin an analysis of the data.
“In my view, the real promise of AI in health care is to provide equitable, state-of-the-art care to everyone, regardless of their socioeconomic status, background, and where they live,” Stultz said. “This work is one step towards realizing this goal.”
