AI system being developed to tell which COVID patients are in threat of cardiac events
Scientists in america are employing artificial intelligence (AI) algorithms to recognize which COVID-19 patients are in risk of adverse cardiac events such as heart failure, sustained abnormal heartbeats, heart attacks, and death. The researchers from Johns Hopkins University in america said they have recently received a USD 195,000 grant from the National Science Foundation for the analysis.
They noted that increasing evidence of COVID-19’s negative impacts on the heart highlights a great need for identifying COVID-19 patients at risk for heart problems.
However, the researchers said no such predictive functions currently exist.
“This project will provide clinicians with early indicators and make certain that resources are assigned to patients with the best need,” said Natalia Trayanova, a professor at the Johns Hopkins University, and the project’s principal investigator.
The first phase of the one-year project will gather the data from a lot more than 300 COVID-19 patients admitted to Johns Hopkins Health System (JHHS).
The info includes electrocardiogram (ECG), cardiac-specific laboratory tests, continuously-obtained essential signs like heartrate and oxygen saturation, and imaging data such as for example CT scans, and echocardiography.
The researchers said this data will be utilized to teach the algorithm using machine learning, a field of AI which allows machines to understand from past data or experience without having to be explicitly programmed.
They'll then test the algorithm with data from COVID-19 patients with heart injury at JHHS, other close by hospitals plus some in New York City.
The researchers said they hope to create a predictive risk score that may determine up to 24 hours in advance which patients are in threat of developing adverse cardiac events.
For new patients, the model will perform a baseline prediction that's updated each time new health data becomes available, they said.
According to the researchers, their approach would be the first to predict COVID-19-related cardiovascular outcomes.
“As a clinician, major knowledge gaps exist in the perfect approach to risk stratify COVID-19 patients for new heart problems that are common and could be life-threatening,” said Allison G. Hays, Associate Professor at the Johns Hopkins University.
“These patients have varying clinical presentations and an extremely unpredictable hospital course,” Hays said.
The researchers explained that similar studies exist, but limited to predictions of general COVID-19 mortality or a patient’s dependence on ICU care.
The approach is drastically more advanced, since it will analyse multiple resources of data, and will create a risk score that is updated as new data is acquired, they said.
The researchers said the project will shed more light about how COVID-19-related heart injury could cause heart dysfunction and sudden cardiac death, which is crucial in the fight against COVID-19.
It will also help clinicians determine which biomarkers are most predictive of adverse clinical outcome, they noted.
Once the research team creates and tests their algorithm, they plan to make it widely available to any interested healthcare institution to implement.
“By predicting who’s at risk for developing the worst outcomes, health care professionals should be able to undertake the very best routes of therapy or primary prevention and save lives,” Trayanova added.
