IBM to help doctors fight heart disease with smarter use of data

Credit: U.S. Navy via Wikimedia

How do you know if you're at risk for heart failure?

The answers might be right there in a doctor's records, said Shahram Ebadollahi, a director in the healthcare informatics group at IBM Research told CITEworld. They just need to dig through all their data and connect the dots.

IBM Research, Sutter Health, and Geisinger Health System have been granted $2 million for a joint research from the National Institutes of Health (NIH) to develop a new type of analytics and application methods that could help doctors detect heart failure years earlier than they do now.

IBM and its health care partners hope to develop methods that will catch signs of heart failure anywhere from six to 24 months ahead of time. With enough time, the patient might be able to fix it with lifestyle changes, or get on the proper medications.

The project is dependent on doctors using electronic health records. If they still do everything on paper, it won't do any good, said Ebadollahi. The system will examine health records to help detect heart failure earlier, identify best practices that help health systems nationwide integrate analytics into primary care, and take an expansive view of a patient's health history.

A patient might experience a symptom of heart trouble, be put on a drug, get better, but then show another symptom. On their own, they are non-specific or weak indicators. Having observed the combination of these weak signals, that becomes a strong indicator of heart failure.

The doctor may notice this, he or she may not. Doctors don't always have the time to make such careful study of a patient's records over time. A computer does. That's why electronic records are so important.

What this means is doctors are going to have to expand the tests they do and the amount of data they keep. Otherwise, the data isn't so Big. This means more tests and more questions to give the analytics software data points to process. Once patients are identified as at high risk for heart failure, physicians can better monitor their status, help motivate a patient to make lifestyle changes and test clinical interventions to potentially slow or possibly reverse heart failure progression.

"What we're trying to do here is essentially use longitudinal records of patients, look at patterns of ups and downs of data across of time if there is a strong indication among those signatures we can mine that such a thing is happening to the patient," said Ebadollahi.

Heart disease is the leading cause of death, disability and costly hospitalizations in the United States and it tends to be a silent killer. Most doctors don't detect it until it's well advanced, and about half of people who have heart failure die within five years of diagnosis.

Free Insider Download: CITE presentations now available
Join the discussion
Be the first to comment on this article. Our Commenting Policies