Mount Sinai researchers peg big data for disease diagnosis

Taking all the risk factors for a certain disease and coming up with forecasting models based on those factors is the goal of a case study conducted by Mount Sinai Director of Cardiac Ultrasound Research Partho Sengupta.

Sengupta, in an interview with HealthITAnalytics.com, discussed efforts to take big data and use it in real-time patient care scenarios. He said that he and his team focused on taking information coming from different sources and merging it together.

"Diseases come in clusters, so heart disease, cancer, Alzheimer's, they don't come independently," Sengupta said. "So my hope is that in future we will be able to take all the risk factors ... and we will be able to deliver forecasting models based upon them."

Sengupta's case study looked at two cardiology diseases: Cardiomyopathy and pericarditis. He and his team took ultrasound information and, using a natural intelligence platform, looked to see if they could find unique characterization of each disease. He said he wanted to see how processing the data through clinical analytics can provide better decision support.

Sengupta's vision, he said, is to have risk modeling to see, for example, if someone goes in for a certain kind of surgery, what are the chances they will have a heart attack when they come out?

There are other healthcare professionals who share aspects of Sengupta's vision. A team led by Cynthia Rudin, a professor at the Massachusetts Institute of Technology Sloan School of Management, has created a data tool that enables patients to obtain predictions for surgical recoveries.

And at California's Kaiser Permanente, an online calculator has been created that uses datasets to determine the risk of sepsis in preterm and newborn babies, as FierceHealthIT reported.

To learn more:
- read the interview

Suggested Articles

With the promotion of Don Trigg, Cerner has named its first new president since 2018.

ONC head Donald Rucker, M.D. said Wednesday that regulators are trying to strike a balance between privacy and transparency with upcoming rule.

Executives are bullish on the potential of artificial intelligence to improve healthcare but think adoption needs to happen faster.