UM researchers awarded for using Big Data in medical studies


Michelle Phillips/Daily


Sunday, January 29, 2017 - 8:50pm

Researchers at the University of Michigan will be using big data — large data sets that need to be computationally analyzed — to predict when individuals will be affected by diseases like depression and Hepatitis C. Big data will also be used to understand the applications of single-cell gene sequencing — examining genetic information from individual cells — through three projects that were recently funded.

The three projects, M-CHAMP, the Michigan Center for Single-Cell Genomic Data Analysis and the Intern Health Study, are receiving $3 million in funding from the Michigan Institute for Data Science as part of the Challenge Initiatives Program, which challenges data scientists and other research investigators to solve real-world problems in areas of transportation research, learning analytics, social sciences and health sciences. The program is part of the University’s plan to invest $100 million in Data Science Initiatives and infrastructure, which was announced in September 2015.

Brahmajee Nallamothu is leading the Michigan Center for Health Analytics and Medical Prediction project, which includes research investigators from LSA, the College of Engineering, the School of Nursing, the School of Public Health and the Medical School.

Nallamothu noted the goal of all three projects was to help researchers understand the vast amounts of data that were spread throughout multiple disciplines.

“The big goals of all the projects, in my opinion, are to help us start to make sense of all the information that is currently surrounding us in a diverse set of fields,” Nallamothu said. “The stakes are really high for us to succeed, because these new tools can be transformational across all these areas: social sciences, health, transportation and learning analytics.”

M-CHAMP focuses on two areas: acute lung injury following critical illness and chronic Hepatitis C virus infection. Nallamothu explained, while there are current ongoing studies trying to predict the outcomes of patients, they aren’t as comprehensive and complex as M-CHAMP.

“Currently, most studies take a ‘snapshot’ view of how patients are doing to predict how they will do in the future,” Nallamothu said. “Longitudinal data that is collected over time often goes ignored because of the complexity of including all of this information into statistical models. We want to change that and help improve our ability to predict how patients will do over time.”

The Michigan Center for Single-Cell Genomic Data Analysis, another project receiving University funding, analyzes single-cell genomics data. The group will use this information in applications concerning cancer and cell development.

This team of researchers come from LSA, College of Engineering, School of Public Health, the Medical School, the Department of Computational Medicine and Bioinformatics and the Comprehensive Cancer Center. The project will be led by Jun Li, an associate computational medicine and bioinformatics professor, and Anna Gilbert, a mathematics professor.

The third project, the Intern Health Study, headed by Srijan Sen, a psychiatry professor, will be using data collected from mobile applications from over 1,000 medical interns to determine the relationships between circadian rhythms, mood and sleep, as well as how they might lead to depression.

Sen explained the goal of the project is to find patterns that lead to depression so measures can be taken to identify at-risk individuals and provide treatment.

“Largely, the goal of the study is to capture data about people’s sleep, activity, their cardiac function and where they’re going, so we can predict before people really descend into the depths of depression that people are at risk in the first part,” Sen said. “The second part is to come up with some kinds of intervention to prevent depression.”

Alfred Hero, a professor of electrical engineering and computer science and the co-director of Michigan Institute for Data Science, explained the efficiency of the groups in analyzing big data stems from the fact that they are composed of so many different disciplines.

“All of the projects funded by MIDAS are funded in a very multidisciplinary manner and that’s where you can make progress on these problems, because it’s not just looking at biological processes and how to sample cells and how to do sequencing,” Hero said. “It’s really how do you analyze that data to be able to segment the population into these classes of susceptibility.”