Powerful AI Risk Assessment Tool Predicts Outcomes in Heart Failure Patients

It is a progressive disease, making it crucial for healthcare providers to identify patients at high risk of worsening outcomes. Now, researchers have introduced a potent new risk assessment tool designed to predict the prognosis of patients with heart failure. This tool marks an advancement over previous methods by utilizing machine learning (ML) and artificial intelligence (AI) to assess individual risks of developing serious complications associated with heart failure.

This innovative model was developed by researchers at the University of Virginia Health System (Charlottesville, VA, USA), using anonymized data from thousands of patients who participated in heart failure clinical trials previously sponsored by the National Institutes of Health’s National Heart, Lung, and Blood Institute. When evaluated, the model proved more effective than existing predictors in forecasting outcomes for a wide range of patients, including the likelihood of requiring heart surgery or a transplant, the risk of rehospitalization, and the risk of mortality. The success of the model is attributed to the integration of ML/AI technologies and the inclusion of hemodynamic clinical data, which detail how blood moves through the heart, lungs, and other parts of the body. By applying this model, doctors can tailor treatment more precisely to each patient's needs, potentially extending and improving the quality of their lives, according to the researchers.

“Heart failure is a progressive condition that affects not only quality of life but quantity as well. All heart failure patients are not the same. Each patient is on a spectrum along the continuum of risk of suffering adverse outcomes,” said researcher Sula Mazimba, MD, a heart failure expert. “Identifying the degree of risk for each patient promises to help clinicians tailor therapies to improve outcomes.”

“This model presents a breakthrough because it ingests complex sets of data and can make decisions even among missing and conflicting factors,” added researcher Josephine Lamp, of the University of Virginia School of Engineering’s Department of Computer Science. “It is really exciting because the model intelligently presents and summarizes risk factors reducing decision burden so clinicians can quickly make treatment decisions.”

Related Links:
UVA Health