Machine Learning Helps Detect Heart Damage in COVID-19 Patients

Source: healthitanalytics.com

A team at Johns Hopkins University has received a $195,000 Rapid Response Research grant from the National Science Foundation to use machine learning to detect which COVID-19 patients are at high risk of heart damage.

For more coronavirus updates, visit our resource page, updated twice daily by Xtelligent Healthcare Media.

Evidence has shown that COVID-19 can have a negative impact on the cardiovascular system, leaving patients at risk for adverse events such as heart failure, sustained abnormal heartbeats, heart attacks, and death. Because of the increased risk for these complications, there is a significant need to identify COVID-19 patients at high risk for heart problems, but these predictive capabilities don’t currently exist.

With this grant, Johns Hopkins researchers will aim to develop these capabilities using machine learning.

“This project will provide clinicians with early warning signs and ensure that resources are allocated to patients with the greatest need,” said Natalia Trayanova, the Murray B. Sachs Professor in the Department of Biomedical Engineering at The Johns Hopkins University Schools of Engineering and Medicine and the project’s principal investigator.

The first phase of the one-year project just received IRB approval for Suburban Hospital and Sibley Memorial Hospital within the Johns Hopkins Health System (JHHS).

In this first phase, researchers will collect data from more than 300 COVID-19 patients admitted to JHHS, including cardiac-specific laboratory tests, continuously-obtained vital signs, and imaging data like CT scans echocardiography. The team will use this data to train the machine learning algorithm.

Researchers will then test the algorithm using data from COVID-19 patients with heart injury at JHHS, other hospitals nearby, and maybe some in New York City. The overarching goal is to create a predictive risk score that can determine which patients are at high risk of developing adverse cardiac events up to 24 hours ahead of time. For new patients, the model will perform a baseline prediction that is updated each time new health data becomes available.

According to the research team, this will be the first approach to predict COVID-19-related cardiovascular outcomes. While similar studies exist, previous research has focused on predictions of general COVID-19 mortality or a patient’s need for ICU care.

This new machine learning approach will analyze multiple sources of data to produce a risk score that is continually updated as researchers acquire new data.

The project will also help providers understand how COVID-19-related heart injury could lead to heart dysfunction and sudden cardiac death. The study will also help clinicians determine which biomarkers are most predictive of adverse clinical outcomes. After creating and testing the algorithm, researchers will make the tool widely available for healthcare institutions to implement.

“As a clinician, major knowledge gaps exist in the ideal approach to risk stratify COVID-19 patients for new heart problems that are common and may be life-threatening. These patients have varying clinical presentations and a very unpredictable hospital course,” said Allison G. Hays, Associate Professor of Medicine in the Johns Hopkins University School of Medicine’s Division of Cardiology and the project’s clinical collaborator.

“This project aims to help clinicians quickly risk stratify patients using real time clinical data, with the goal of widely disseminating this knowledge to help medical practitioners around the world in their approach to treating and monitoring patients suffering from COVID-19.”

This project will help researchers obtain information critical to fighting COVID-19.

“By predicting who’s at risk for developing the worst outcomes, healthcare professionals will be able to undertake the best routes of therapy or primary prevention and save lives,” said Trayanova.

Related Posts

Subscribe
Notify of
guest
0 Comments
Inline Feedbacks
View all comments
0
Would love your thoughts, please comment.x
()
x
Artificial Intelligence