Johns Hopkins University

Johns Hopkins Researchers to Use Machine Learning to Predict Heart Damage in COVID-19 Victims

18-May-2020 8:00 AM EDT, by Johns Hopkins University

Newswise — Johns Hopkins researchers recently received a $195,000 Rapid Response Research grant from the National Science Foundation to, using machine learning, identify which COVID-19 patients are at risk of adverse cardiac events such as heart failure, sustained abnormal heartbeats, heart attacks, cardiogenic shock and death.

Increasing evidence of COVID-19’s negative impacts on the cardiovascular system highlights a great need for identifying COVID-19 patients at risk for heart problems, the researchers say. However, no such predictive capabilities currently exist.

“This project will provide clinicians with early warning signs and ensure that resources are allocated to patients with the greatest need,” says 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, which just received IRB approval for Suburban Hospital and Sibley Memorial Hospital within the Johns Hopkins Health System (JHHS), will collect the following data from more than 300 COVID-19 patients admitted to JHHS: ECG, cardiac-specific laboratory tests, continuously-obtained vital signs like heart rate and oxygen saturation, and imaging data such as CT scans and echocardiography. This data will be used to train the algorithm.

The researchers will then test the algorithm with data from COVID-19 patients with heart injury at JHHS, other nearby hospitals and perhaps some in New York City. The hope is to create a predictive risk score that can determine up to 24 hours ahead of time which patients are at risk of developing adverse cardiac events.

For new patients, the model will perform a baseline prediction that is updated each time new health data becomes available.

As far as the researchers are aware, their approach will be the first to predict COVID-19-related cardiovascular outcomes.

"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," says 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.”

Similar studies exist, but only for predictions of general COVID-19 mortality or a patient’s need for ICU care. Furthermore, this approach is significantly more advanced, as it will analyze multiple sources of data and will produce a risk score that is updated as new data is acquired.

This project will shed more light on how COVID-19-related heart injury could result in heart dysfunction and sudden cardiac death, which is critical in the fight against COVID-19. The project will also help clinicians determine which biomarkers are most predictive of adverse clinical outcome.

Once the research team creates and tests their algorithm, they will make it widely available to any interested health care institution to implement.

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

Trayanova, whose work focuses on bringing engineering approaches to the clinical realm, is hopeful that this project will augment the role of engineering in helping patients live longer and lead healthier lives.




Filters close

Showing results

110 of 3395
Newswise: Historical Racial & Ethnic Health Inequities Account for Disproportionate COVID-19 Impact
22-Sep-2020 4:00 PM EDT
Historical Racial & Ethnic Health Inequities Account for Disproportionate COVID-19 Impact
American Thoracic Society (ATS)

A new Viewpoint piece published online in the Annals of the American Thoracic Society examines the ways in which COVID-19 disproportionately impacts historically disadvantaged communities of color in the United States, and how baseline inequalities in our health system are amplified by the pandemic. The authors also discuss potential solutions.

Released: 24-Sep-2020 5:05 PM EDT
In-person college instruction leading to thousands of COVID-19 cases per day in US
University of Washington

Reopening university and college campuses with primarily in-person instruction is associated with a significant increase in cases of COVID-19 in the counties where the schools are located.

Newswise: Some Severe COVID-19 Cases Linked to Genetic Mutations or Antibodies that Attack the Body
Released: 24-Sep-2020 3:25 PM EDT
Some Severe COVID-19 Cases Linked to Genetic Mutations or Antibodies that Attack the Body
Howard Hughes Medical Institute (HHMI)

Two new studies offer an explanation for why COVID-19 cases can be so variable. A subset of patients has mutations in key immunity genes; other patients have auto-antibodies that target the same components of the immune system. Both circumstances could contribute to severe forms of the disease.

access_time Embargo lifts in 2 days
Embargo will expire: 25-Sep-2020 6:30 PM EDT Released to reporters: 24-Sep-2020 3:20 PM EDT

A reporter's PressPass is required to access this story until the embargo expires on 25-Sep-2020 6:30 PM EDT The Newswise PressPass gives verified journalists access to embargoed stories. Please log in to complete a presspass application. If you have not yet registered, please Register. When you fill out the registration form, please identify yourself as a reporter in order to advance to the presspass application form.

17-Sep-2020 1:15 PM EDT
Accuracy of commercial antibody kits for SARS-CoV-2 varies widely
PLOS

There is wide variation in the performance of commercial kits for detecting antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), according to a study published September 24 in the open-access journal PLOS Pathogens by Jonathan Edgeworth and Blair Merrick of Guy’s and St Thomas’ NHS Foundation Trust, Suzanne Pickering and Katie Doores of King's College London, and colleagues. As noted by the authors, the rigorous comparison of antibody testing platforms will inform the deployment of point-of-care technologies in healthcare settings and their use in monitoring SARS-CoV-2 infections.

24-Sep-2020 9:25 AM EDT
Loneliness levels high during COVID-19 lockdown
Newswise Review

During the initial phase of COVID-19 lockdown, rates of loneliness among people in the UK were high and were associated with a number of social and health factors, according to a new study published this week in the open-access journal PLOS ONE by Jenny Groarke of Queen’s University Belfast, UK, and colleagues.

Newswise: Genetic, immunological abnormalities in Type I interferon pathway are risk factors for severe COVID-19
24-Sep-2020 12:35 PM EDT
Genetic, immunological abnormalities in Type I interferon pathway are risk factors for severe COVID-19
Uniformed Services University of the Health Sciences (USU)

Individuals with severe forms of COVID-19 disease can present with compromised type I interferon (IFN) responses based on their genetics, according to results published in two papers today in the journal Science. Type I IFN responses are critical for protecting cells and the body from more severe disease after acute viral infection.

Newswise: Talking Alone: Researchers Use Artificial Intelligence Tools to Predict Loneliness
Released: 24-Sep-2020 1:45 PM EDT
Talking Alone: Researchers Use Artificial Intelligence Tools to Predict Loneliness
University of California San Diego Health

A team led by researchers at University of California San Diego School of Medicine has used artificial intelligence technologies to analyze natural language patterns to discern degrees of loneliness in older adults.


Showing results

110 of 3395

close
0.96216