More than 200 attendees from across Duke University and Duke Health came together on March 20 to discuss the future of health data science at Duke. This gathering not only celebrated recent successes for the health data science community at Duke, but also kicked off new conversations and collaborations among members of the Duke community representing multiple campuses and disciplines.
As part of its efforts to support the translation of scientific innovations, the Duke Clinical and Translational Science Institute (CTSI) will help encourage and foster these growing partnerships. “Our vision is to increase collaboration of translational efforts across Duke,” said Ebony Boulware, CTSI director and associate vice dean for translational research. “I can’t think of a better place to start than data science.”
With opening remarks from Chancellor for Health Affairs Eugene Washington, Provost Sally Kornbluth, and Ebony Boulware, the support for these new efforts across Duke was evident, and Larry Carin, vice provost for research, described the activity and planning underway in multiple areas, including community building, fostering methodology leaders, and opportunities for quantitative sciences to address important challenges in health.
"It's not enough to have data. We need to use data to ask the right questions," said Eric Peterson, executive director of the Duke Clinical Research Institute. Michael Pencina, professor of biostatistics and bioinformatics and DCRI chief data scientist, described the importance of framing the right questions, applying optimal methods, and gaining actionable insights. "The answer,” he said, lies in the question.”
During the review of case studies in data science, panelists described experiences from a range of diverse initiatives and collaborations in data science at Duke. Alan Kirk, chair of surgery, illustrated the transformative potential for data to support clinical decisions, including when — or even whether — to operate. Katherine Heller, assistant professor of statistical science, described working with clinicians to apply data science to surgical complications.
“We can’t achieve our goal – improving patient care – without good information,“ commented Mark Newman, president of the Duke Private Diagnostic Clinic. Bradi Granger, professor in the School of Nursing, emphasized the importance of connecting both people and data, and Kaf Dzirasa from the Duke Institute for Brain Science gave the specific example of incorporating innovation and data science into training and opportunities for student involvement, an idea that the panel enthusiastically supported.
Although the event signifies the beginning of new efforts in health data science, the presenters emphasized that data-driven discovery has deep roots at Duke. Eric Peterson and Geoff Ginsburg, director of the Duke Center for Applied Genomics and Precision Medicine, described the pivotal leadership of Eugene Stead, Duke’s first chair of medicine, who advocated for the use of computer technology in the study of chronic diseases as far back as the 1970s.
The difference now is the world’s recognition of the importance of data science to improve patient care, precision medicine, and population health.
An expert panel of case studies, moderated by Erich Huang, assistant dean for biomedical informatics, allowed attendees to learn about current data science initiatives at Duke
Attendees and speakers expressed enthusiasm about the opportunities for collaboration the horizon. “Duke will continue to lead in health sciences!” tweeted event attendee Gina-Maria Pomann, a statistical scientist with the CTSI Biostatistics Core.
“With the level of support we see here today,” said Boulware, “I’m very confident that we’re going to make major strides in health data science.”
“There’s a lot at stake in getting health data science right, and Duke has the opportunity to lead the way. I couldn’t have imagined this kind of support for data science even five years ago,” Rob Califf, former FDA commissioner and founding director of the Duke Clinical Research Institute, said in his closing remarks. “This is a big step up from a dozen data scientists being in the basement with pizza.”