AI Accurately Predicts If and When a Person Will Experience Cardiac Arrest

Sudden cardiac death caused by arrhythmia is responsible for 20% of all deaths worldwide. This type of heart attack is caused by an electrical issue that stops the heart from beating correctly. Natalia Trayanova, PhD, MS and her colleagues in the Trayanova Lab at Johns Hopkins University are conducting cutting edge research in computational cardiology to predict this type of cardiac event. They are using machine learning to find features in medical images that reveal the condition of a person's heart and to determine risk of cardiac arrest. A paper about the new method entitled Arrhythmic sudden death survival prediction using deep learning analysis of scarring in the heart was published on April 7, 2022 in Nature Cardiovascular Research.

"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 who 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."

Natalia Trayanova, PhD, Professor of Biomedical Engineering and Medicine

Study Highlights

• In the study researchers used deep learning to analyze scarring on hundreds of MRI images of damaged hearts.
• The team used contrast-enhanced cardiac images that visualize scar distribution to train an algorithm to detect patterns and relationships not visible to the human eye.
• Traditional clinical cardiac image analysis extracts only simple scar features such as volume and mass ignoring other critical data in the image.
• The approach blends neural networks and survival analysis to predict patient-specific survival curves.
• This is the first time that researchers have used neural networks to build a personalized survival assessment for patients with heart disease.
• They demonstrated that the deep learning approach - using only raw cardiac images as input - outperforms standard survival models constructed using other clinical data.
• They were able to accurately assess a person's risk of sudden cardiac arrest for up to 10 years with high accuracy.
• The algorithm's predictions were significantly more accurate on every measure than doctors' predictions.
• The algorithm's predictions were validated in tests with an independent patient cohort from 60 health centers across the US.
• The new deep learning technique called Survival Study of Cardiac Arrhythmia Risk (SSCAR) could revolutionize clinical decision making.
• Dr. Trayanova and her team are also developing personalized interventions to minimize the potential for recurrence and re-hospitalization.

Schematic overview of SSCAR ( Image source: Arrhythmic sudden death survival prediction using deep learning analysis of scarring in the heart, Nature Cardiovascular Research)

Natalia Trayanova, PhD, MS

Dr. Trayanova is the world's leading innovator in the use of modern computation and modeling approaches in cardiac arrhythmia research. Her translational research has laid the foundation for the development of first-of-their-kind personalized virtual hearts. These are clinical-imaging -based models of human hearts that realistically represent a person's diseased heart.

Dr. Trayanova is the Murray B. Sachs Professor in the Department of Biomedical Engineering at Johns Hopkins University and a Professor of Medicine at the Johns Hopkins School of Medicine. She is the first female faculty to hold an endowed professorship in the Whiting School of Engineering at Johns Hopkins University. Dr. Trayanova has published over 380 scientific papers in high impact journals and is an inventor on 43 patents for new technologies for predicting risk of sudden cardiac death.

References

Arrhythmic sudden death survival prediction using deep learning analysis of scarring in the heart, Nature Cardiovascular Research, April 7, 2022

Dan M. Popescu,?Julie K. Shade,?Changxin Lai,?Konstantinos N. Aronis,?David Ouyang,?M. Vinayaga Moorthy,?Nancy R. Cook,?Daniel C. Lee,?Alan Kadish,?Christine M. Albert,?Katherine C. Wu,?Mauro Maggioni?&?Natalia A. Trayanova, ?

Subscribe and Comment

I'm interested in your feedback - please leave your comments. To subscribe please click subscribe at the top of this article.

Copyright ? 2022 Margaretta Colangelo. All Rights Reserved.

This article was written by?Margaretta Colangelo.?Margaretta is Co-founder of Jthereum. She serves on the advisory board of the AI Precision Health Institute at the University of Hawai?i?Cancer Center. She's based in San Francisco?

Twitter?@realmargaretta