A new artificial-intelligence-based approach can forecast if and when a patient will die of cardiac arrest far more precisely than a doctor. The system, which is based on raw images of diseased hearts and patient backgrounds, has the potential to change clinical decision-making and improve survival from abrupt and deadly cardiac arrhythmias, one of medicine’s deadliest and most perplexing disorders.
The work, led by Johns Hopkins University researchers, is detailed in Nature Cardiovascular Research.
“Sudden cardiac death caused by arrhythmia accounts for as many as 20 percent of all deaths worldwide and we know little about why it’s happening or how to tell who’s at risk,” said senior author Natalia Trayanova, the Murray B. Sachs professor of Biomedical Engineering and Medicine. “There are patients who may be at low risk of sudden cardiac death getting defibrillators that they might not need and then there are high-risk patients that aren’t getting the treatment they need and could die in the prime of their life. What our algorithm can do is determine who is at risk for cardiac death and when it will occur, allowing doctors to decide exactly what needs to be done.”
The researchers are the first to employ neural networks to construct a tailored survival assessment for each heart disease patient. These risk factors predict the likelihood of sudden cardiac death during the next ten years, as well as when it is most likely to occur.
Survival Study of Cardiac Arrhythmia Risk is the name of the deep learning technology (SSCAR). The term relates to cardiac scarring caused by heart illness, which frequently leads to fatal arrhythmias, and it’s also the key to the algorithm’s forecasts.
The team trained an algorithm to discover patterns and associations not evident to the human eye using contrast-enhanced cardiac pictures that reveal scar distribution from hundreds of real patients with cardiac scarring at Johns Hopkins Hospital. Current clinical cardiac imaging analysis extracts only basic scar properties such as volume and mass, drastically underutilizing what has been shown in this study to be important data.
“The images carry critical information that doctors haven’t been able to access,” said first author Dan Popescu, a former Johns Hopkins doctoral student. “This scarring can be distributed in different ways and it says something about a patient’s chance for survival. There is information hidden in it.”
The researchers used a second neural network to learn from ten years of conventional clinical patient data, which included 22 variables such as the patients’ age, weight, race, and prescription drug use.
The algorithms’ predictions were not only significantly more accurate than doctors on every measure but they were also validated in tests with an independent patient cohort from 60 health centers across the United States, with a variety of cardiac histories and imaging data, indicating that the platform could be used anywhere.
“This has the potential to significantly shape clinical decision-making regarding arrhythmia risk and represents an essential step towards bringing patient trajectory prognostication into the age of artificial intelligence,” said Trayanova, co-director of the Alliance for Cardiovascular Diagnostic and Treatment Innovation. “It epitomizes the trend of merging artificial intelligence, engineering, and medicine as the future of healthcare.”
The team is currently developing algorithms to detect other heart disorders. The deep-learning concept, according to Trayanova, might be applied to other sectors of medicine that rely on the visual diagnosis.
Bloomberg Distinguished Professor of Data-Intensive Computation Mauro Maggioni, Julie Shade, Changxin Lai, Konstantino Aronis, and Katherine Wu were also members of the Johns Hopkins team. Other writers include Brigham and Women’s Hospital’s M. Vinayaga Moorthy and Nancy Cook; Northwester University’s Daniel Lee; Touro College and University System’s Alan Kadish; and Cedar-Sinai Medical Center’s David Oyyang and Christine Albert.
Source: Johns Hopkins University