Healthcare, Latest News, WVU News

Heart doc wins data challenge

Dr. Partho Sengupta wows NHLBI with his cardiovascular research

WVU Medicine

 The WVU Heart and Vascular Institute won the National Heart, Lung, and Blood Institute’s (NHLBI) Big Data Analysis Challenge: Creating New Paradigms for Heart Failure Research for research on using machine learning to predict ventricular disease done by Dr. Partho Sengupta,  WVU Heart and Vascular Institute Cardiology division chief and director of cardiac imaging.

The five challenge winners were each awarded up to $50,000.

“This award is another opportunity for the medical community to see the incredible research we are doing here at the WVU Heart and Vascular Institute,”  Sengupta said. “We work with international researchers to develop better tools to diagnose cardiac disease in people around the world.”

According to the Centers for Disease Control and Prevention, about 6.2 million adults in the United States have heart failure, a progressive illness that can be debilitating or deadly. The goal of the NHLBI Big Data Analysis Challenge: Creating New Paradigms for Heart Failure Research is to foster innovation and address the need for new, open-source disease models that can define sub-categorizations of adult heart failure. These models will support new research hypotheses that may lead to further advancements in the management of this disorder.

Sengupta and an international team of researchers have been   using machine learning as an effective screening tool for early diagnosis of left ventricular diastolic dysfunction (LVDD), a common form of heart failure in which the heart is unable to properly relax and fill normally.

Machine learning uses algorithms that automatically improve and become more accurate over time through the continued input of data. This rigorously studied and well-documented method uses patient data to develop an automated solution for grouping patients who develop heart failure due to LVDD.

The resulting data produces an intelligent classifier that can be used to grade the severity of the heart’s dysfunction and sort patients into subgroups with predominant heart-related and other conditions where systems beyond the heart, like the arteries and kidneys, contribute to fluid buildup. The intelligent classifier specifically offers a viable solution that is easy to use in clinical practice and overcomes the limitations of the existing clinical standards that have limitations in assessing the precise mechanisms of heart failure.

As more patients are screened and their information is entered into the database, the data becomes more accurate and better able to predict the patient’s long-term outcomes with and without treatment.

“Machine learning can help internists and physicians identify heart dysfunction in the early stages when it is easier to treat and predict the progression of the disease in order to help patients take action to improve their cardiac health,” Sengupta said. “We are able to use echocardiogram data to extract information that would otherwise come from more expensive imaging tests, using the heart’s electrical signals to provide information about the speed with which the heart is squeezing and relaxing.”

This model can be used to determine the patient’s current stage of disease such that early interventions can be taken in order to halt the progress or reduce the likelihood of heart failure. It takes into account the patient’s age and sex, which can inform individualized risk estimation and interventions for men and women.