Making Sense of Big Data to Improve Patient Care
The health sensors of the future will run virtual circles around today’s pedometers and heart-rate monitors, churning out enormous amounts of data about everything from biology to behavior that can explain a patient’s health status.
Those extensive details will create a need for big-data analytics to make sense of mobile and body-worn sensors’ output so clinicians can use the information to treat patients.
The Ohio State University is part of an 11-institution consortium funded by the National Institutes of Health (NIH) to fulfill these combined needs by developing tools that make it easier to gather, analyze and interpret data generated by health sensors. Products from the initiative will include open-source computing systems to crunch the data and software that can deliver useful, “actionable” information to health care practitioners.
The $10.8 million in NIH funding over four years establishes the National Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K). The University of Memphis will lead the center, which will apply new technologies to two specific health care challenges: reducing hospital readmissions among congestive heart failure patients and preventing relapse among people who have quit smoking.
Three Ohio State investigators will lend their expertise to this initiative: William Abraham, director of cardiovascular medicine at Ohio State’s Wexner Medical Center; Emre Ertin, research professor of electrical and computer engineering; and Clay Marsh, chief innovation officer for Wexner Medical Center and professor of internal medicine.
Abraham will lead clinical studies of technologies developed for heart failure care, Ertin designs novel biosensors and specializes in signal processing required to interpret sensor data, and Marsh will direct the pursuit of health care innovations enabled by the center’s initial work.
“The idea here is to take everything that could possibly be known about a patient and put it into these big-data, deep-computing analytics so we can learn about those patients, and see and anticipate things that we can’t otherwise see when we look at just bits and pieces of information,” Abraham said.
“Day-to-day data from these sensors will be analyzed and interpreted in a way that deepens a clinician’s understanding of a patient’s status. It allows for better and more personalized decisions in regard to health care and management.”
Ertin will contribute on the front end; he designs biosensors in addition to his signal processing emphasis. Among his projects are sensors that detect fluid levels in the lungs, breathing patterns and cardiac motion. These sensors do not require skin contact, but instead use radiofrequency waves to make their measurements.
“These sensors can easily blend into your daily life routine, and therefore have the potential to dramatically expand the scale of physiological data we can obtain in the field while minimizing the burden to participants,” he said.
The center’s scientists predict that the data will include measures of physical, biological, behavioral, social and environmental factors that contribute to health and disease risk.
“The sensors provide a large, noisy, complex data stream about the many facets of your life and health, and there is a gaping need for a computational engine that can transform sensor data into something useful for clinicians,” Ertin said.
Though the center will target heart failure and smoking relapse, the approach and products of MD2K will be applicable to such other complex diseases as asthma, substance abuse and obesity.
This is where Marsh, executive director of the IDEA Studio for Healthcare and Design at Ohio State, comes in. He will lead investigations into new applications of MD2K to improve health and health care, solidifying the role of mobile-sensor big data as a key player in the delivery of personalized medicine.
“This ties directly to the mission of the IDEA Studio – not just solving important problems in health care, but collaborating across multiple disciplines to produce solutions to those problems,” Marsh said, noting the M2DK center is composed of computer science, engineering, statistical and biomedical researchers – “the kind of team required to take on the massive challenge of managing big data and translating this to knowledge and solutions to help people.”
Santosh Kumar, a computer scientist at the University of Memphis and an Ohio State alumnus (computer science and engineering master’s and Ph.D.), will direct the center. The MD2K team also includes scientists from Cornell Tech, Georgia Tech, Northwestern, Rice, UCLA, UC San Diego, UC San Francisco, the University of Massachusetts Amherst and the University of Michigan, as well as the nonprofit Open mHealth.
This center is part of the NIH Big Data to Knowledge (BD2K) initiative designed to support advances in research, policy and training needed for the effective use of big data in biomedical research.
More information about the MD2K center is online at md2k.org.
by Emily Caldwell, University Communications