The University of Michigan has launched a precision health initiative that will leverage big data and machine learning to discover the genetic, lifestyle and environmental factors for improving healthcare and personalizing medicine.

“Precision health brings together genomics with other big data. It involves taking millions of data points to understand what factors influence an individual’s health and wellness,” a University of Michigan announcement notes. “Researchers then apply that knowledge to make specific, personalized recommendations for prevention, diagnosis and treatment.”

Specifically, the initiative will take a “baseline of genomic and medical factors” while incorporating data from sensors and wearable technology and integrating “social and environmental factors as well as behavior and lifestyle strategies.”

The campus-wide research effort is designed to combine resources from across the university including its 19 schools and colleges, such as the College of Engineering, Medical School, and School of Public Health.

“It also includes our operational health system Michigan Medicine,” says Sachin Kheterpal, MD, co-director of the precision health initiative and associate dean for research information technology at the University of Michigan Medical School. “Our College of Engineering is a key partner in this given not just their bioengineering expertise but their presence in big data.”

Also See: U-Michigan to invest $100M in big data initiative

The initiative’s initial project will focus on opioid prescribing to manage pain from surgery by identifying risk factors for becoming a chronic opioid user, based on each patient’s health, genetics, social, environmental and lifestyle factors.

“One of the important challenges of the opioid crisis is that it forces us to pay attention to types of data and science that many precision medicine initiatives haven’t historically had the opportunity to focus on,” adds Kheterpal. “Electronic health records are one of the very important pieces of the data puzzle for improving patients’ health, but just as importantly we believe there are many things not found in EHRs that are necessary to inform health and wellness.”

Kheterpal contends that the path forward is to apply novel machine learning analytics to “all these different data streams that we’re already aggregating and new ones that we’re going to begin aggregating.”

Ultimately, when it comes to addressing the opioid epidemic, the university hopes to create guidelines to tailor pain management plans and reduce prescriptions and to share validated treatments and prevention tools.

Other projects that the initiative will tackle include cancer, mental health and metabolic diseases such as diabetes, according to Kheterpal.

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