Precision health pioneer named to MIT Technology Review innovator list

The national magazine recognized Jenna Wiens as one of 2017’s 35 Innovators Under 35.

Jenna Wiens portrate Enlarge
Jenna Wiens Photo: Joseph Xu/Senior Multimedia Content Producer, University of Michigan - College of Engineering

For using data science to identify hospital patients at risk of contracting an infection they didn’t check in with, a Michigan Engineering professor has been named to MIT Technology Review’s 2017 list of 35 Innovators Under 35.

Jenna Wiens, 31, is an assistant professor of computer science and engineering. The national magazine recognized her as a pioneer in her field, developing fresh and unexpected solutions. Read the story, “Her computational models identify patients who are most at risk of a deadly infection.”

Each year since 1999, the magazine recognizes exceptionally talented young innovators whose work they believe has the greatest potential to transform the world, according to the magazine.

Wiens’ primary research is in the development of data-driven predictive models needed to help organize, process, and transform data into actionable knowledge. The main focus of her work is in harnessing information about patients to improve medical outcomes. Known as precision health, this approach is expected to help doctors to customize treatments to individual patients’ genetic makeup, lifestyle, and risk factors, and to predict outcomes with significantly higher accuracy.

By targeting patients identified as high-risk through computational data-driven models, practitioners could reduce the burden of disease in a more efficient and cost-effective manner.

“Health data is going to be valuable in ways we don’t even understand yet,” Wiens said.

In 2014, she led a project to develop a data-driven hospital-specific model for estimating the probability that an admitted patient would test positive for C. difficile, a bacterium that can cause symptoms ranging from diarrhea to life-threatening inflammation of the colon. C. difficile kills more than 14,000 people a year. It’s difficult to eradicate and is often transmitted to patients in hospital environments. In contrast to previous risk models for C. difficile, Wiens’ project did not limit itself to the set of known risk factors, but instead considered more than 10,000 variables automatically extracted from electronic health record data. Using machine learning techniques, she developed the model on admissions from a single year and validated it on a held out set of admissions from the following year.

In 2016, Wiens (as a co-investigator) and research colleagues from Michigan Medicine were awarded a $9.2 million grant from the National Institutes of Health to tackle C. difficile as a government-backed effort to attack antibiotic resistant bacteria. They will spend the next four years studying this pathogen.

Wiens is an investigator at the Michigan Integrated Center for Health Analytics & Medical Prediction, which was awarded $1.25 million through the Michigan Institute for Data Science in 2017 to further develop medical prediction models that address complex clinical problems. As part of this center, Wiens seeks to address challenges such as complex unexpected changes in patient populations and clinical protocols, insufficient intelligibility of models, and absence of actionability.

In addition to her work in healthcare, Wiens develops machine learning methods to extract strategically useful information from player tracking data in the National Basketball Association.  

Wiens received her PhD in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology in 2014 and joined the Michigan Engineering faculty that year. Her research is funded by the Centers for Disease Control, the National Science Foundation, and the National Institutes of Health. She received an NSF CAREER Award in 2016 and was named one of Forbes’ 30 Under 30 in 2015.