The University of Pittsburgh Medical Center is partnering with two local universities to expand research using advanced health data analytics. UPMC executives say the organization will pay for much of the research work and in turn hopes to commercialize new medical innovations developed through the collaboration.

Over the next six years, UPMC will fund new research centers at the University of Pittsburgh and Carnegie Mellon University under the umbrella organization, called the Pittsburgh Health Data Alliance. Jeffrey Romoff, CEO at UPMC, says the delivery system will spend $10 million to $20 million each of the six years. Hundreds of millions of dollars in existing grant funds at the institutions also will be used for the venture.

The initiative is part of a growing trend among large, widely known health organizations that are seeking to unlock information from medical records and improve IT practices. For example, Intermountain Healthcare's Homer Warner Center for Informatics Research is dedicated to the discovery and implementation of innovative information technologies for the improvement of clinical care. The center is focused on the pursuit of excellence in research, education and collaboration in the medical informatics field.

In the Pittsburgh initiative, targets for analytics research include helping clinicians and public health authorities quickly detect new disease outbreaks, smartphone apps that suggest a personalized dietary change most beneficial to an individual based on genetics and medical history, and early detection of donated organ rejection, among others.

The alliance begins work with two research and development centers. The Center for Machine Learning and Health at Carnegie Mellon will focus on big health data analytics, personalized medicine and disease modeling, privacy and security issues with big data, patient and provider education, and a new general framework for big data in the healthcare environment.

The Center for Commercial Applications of Healthcare Data at U-Pitt will analyze personalized medicine for treating certain cancers and lung diseases, genomic and imaging data, and methods for data capture and analysis to generate actionable information.

As big data expands, work is needed to better understand the roles of privacy and security, says Eric Xing, a professor and director of the Center for Machine Learning and Health at Carnegie Mellon. With big data, a patient is no longer just an example of a particular disease, but is a unique individual who has specific genetic risks, lifestyles and social environments that must be incorporated into treatment.

The challenge is to keep patients unique yet also connected to the rest of the world to get more accurate diagnoses and treatments. The "machine learning" component of Carnegie Mellon's work is somewhat similar to development of IBM's Watson computer, which learns as it is fed information, and can retrieve relevant data. But the big data initiative in Pittsburgh is looking to use technology to assess the risk and nature of disease, and provide physicians with more focused and relevant questions.

While Carnegie Mellon's expertise is in artificial intelligence and big data infrastructure, organizing and enabling use of data via texts, images, video and other media, U-Pitt brings expertise in medical science content of biology and genomics, along with other disciplines.

The project is still in development and participants are conceiving new ideas and agendas, so the project could go further, such as creating patient-assistance mobile devices and "smartifying" the entire ecosystem of healthcare, Xing says.

Register or login for access to this item and much more

All Health Data Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access