Risk Calculator Helps Personalize Care for Heart Failure Patients

Late-stage left heart failure is an often-fatal disease that affects hundreds of thousands of people in the United States alone. A mechanical heart pump can be a life-saving procedure for these patients, but the surgery to implant the pump can be risky.

One of the most serious risks is right heart failure, in which the right side of the heart becomes unable to pump enough blood to the lungs. Identifying patients at high risk for right heart failure can help doctors better prepare patients for heart pump placement. But it proves difficult to predict who is most at risk.

A national team led by University of Utah Health researchers has now developed a way to predict a patient’s individualized risk of right heart failure after pump placement surgery. The team now uses this risk calculator to tailor care for each patient before and during heart pump placement. Their results are published in JAMA Cardiology.

Finding the Needle in the Data Haystack

For people who have surgery to implant a left heart pump, the risk of subsequent right heart failure is high: 15 to 30%. But the large number of factors that contribute to individual risk of right heart failure make personalized risk prediction “exceptionally difficult,” says Iosif Taleb, MD, currently a cardiology researcher at the University of California, San Diego and first author of the study. Taleb helped develop the risk calculator during his clinical research fellowship at U of U Health.

“Each patient is unique, with different health problems and cardiac characteristics,” says Taleb. “Heart pumps also have specific characteristics, and the combination of these factors makes predictions difficult.”

Stavros Drakos, MD, Ph.D., professor of cardiology at U Health and senior author of the publication describing the study, says that “efforts have been made in the past to predict which patients will receive a heart pump (also called a left ventricular assist device, or LVAD) and won’t work well, but they haven’t worked well in the real world. Even models that appeared to predict outcomes in one hospital often failed to provide accurate predictions in another.

In an effort to develop a more accurate and more widely usable risk calculator, researchers used patient data from 1,125 people at six health centers, including U of U Health. Taking into account variables ranging from pre-existing health conditions to medications and demographic information, they used machine learning to generate and test numerous risk models and find the one that best described patients’ health outcomes.

Their model identified several variables that are particularly useful in predicting whether a patient will develop right heart failure (RHF), such as whether patients needed additional forms of cardiac support before their initial surgery to better prepare them and obtain best results. Researchers used these factors to develop an easy-to-use online calculator that determines a patient’s percent risk of right heart failure after surgery.

The new risk calculator, called STOP-RVF, describes individual risk more accurately than previous models. Above all, it also works well in various situations.

After creating the risk calculator, the researchers “verified their work” by using it to retrospectively calculate risks for patients in another hospital system. The scientists then compared the calculator’s predictions to the patients’ actual results, finding that their tool was still able to accurately model the risk of patients later developing right heart failure.

Predicting results nationally

Building the model on data from a large and diverse population was essential to accurately describing patient risk on a national scale. “It’s important because we live in a very diverse country,” Drakos says.

“Basing this analysis on multiple sites across the country – the Washington, D.C. area, the Detroit area, California, Utah and the broader Mountain West region – it is representative of much of our country. It reinforces the generalizability of the work.”

Cardiologists, surgeons and nurse coordinators on U of U Health’s heart failure and LVAD team have already begun using the calculator in their own clinical practice to personalize care.

“This makes it possible to adapt the risk assessment to each patient, thus allowing better preparation before surgery,” explains Taleb. For patients at high risk of right heart failure, doctors may delay surgery, use different medications to improve patients’ chances of recovery, or consider alternative treatments.

Because the calculator has only been in clinical use for a short time, it is too early to say whether it will improve patient outcomes. But Drakos expects it to be more useful than previous models because it was developed using patient populations from multiple hospitals.

“We validated it in other hospitals and it worked very well,” he says. “But of course, time will tell how significant its impact on patient outcomes will be.”