Jonathan Lifshitz, PhD, is renowned for his research on traumatic brain injury. He leads a neurotrauma and social impact research team that advances the national conversation on domestic violence-induced traumatic brain injury and related topics. The success of the team’s research projects and the data obtained for these studies led to an unexpected problem.
“I have a few projects that have been put on the back burner,” admitted Dr. Lifshitz, professor of child health at the University of Arizona College of Medicine – Phoenix. “I had to rely on the goodwill of my colleagues to manage the level of data science required by these projects. But sometimes it’s hard to find people who have the time to help, even if they want to.
Dr. Lifshitz’s experience is not unlike that of many university researchers.
“We had more people sitting with data ready to process than people helping them process their data,” explained Merchant from Nirav, MSdirector of the UArizona Data Science Institute and leader of the Health Analytics Powerhouse, an initiative of UArizona Health Sciences.
A key component of the Health Analytics Powerhouse initiative is the Data Science Fellows program, which provides training and mentorship to postdoctoral scientists and doctoral students at UArizona focused on the health sciences.
“The goal of the program is workforce development,” said Merchant, who is a member of the university’s BIO5 Institute. “We want the workforce to be literate in software, data and machine learning so that as we grow we can reduce the pressure on researchers.”
What is Data Science?
Data science is not limited to dealing with large amounts of data.
“If you’re working with a lot of data, you’re just doing science,” Merchant explained. “Data science combines data sets and methods that allow you to connect things that would otherwise not be easily connected.”
For example, a researcher may want to develop software to assess and train healthcare providers on their interactions with consenting patients. One way to design the software is to analyze audio recordings of patient interactions, Merchant said.
Researchers with medical and clinical expertise could collaborate with speech and hearing specialists, who can help with natural language models, but either group is unlikely to have the expertise. technique to work with a software developer to create the program.
However, someone trained in data science can fill these expertise gaps. A data scientist has the tools to organize and analyze large amounts of data, such as that which might be collected over thousands of hours of audio recordings. They can train the researcher to better collect and organize the data upstream and to interpret the data produced.
“A lot of what happens in data science is team science,” Merchant said. “Expertise is so broad that you cannot expect one person to know everything. The diversity of expertise really elevates the kind of science we can do.
With the help of Luisa RojasA doctoral candidate in UArizona’s Clinical Translational Health Sciences graduate program, Dr. Lifshitz has found someone capable and willing to take on his “mothballed” projects.
Rojas, originally from Colombia, is part of the second cohort of data science fellows that began in January. She quickly acquires expertise and shares her knowledge with Dr. Lifshitz and his fellow researchers. Rojas even created a Slack channel called “Data Science” to share the information she learns with her peers.
“She inspires others to embrace data science,” Dr. Lifshitz said. “Perhaps we can now move forward projects that have been stalled because we didn’t have a capable or available analyst to do the work required.”
Dr. Lifshitz includes Rojas in meetings with her research teams so she can listen and provide insightful feedback when she sees opportunities to implement data science principles. Rojas also applies data science techniques to his own research. For her translational thesis, she is conducting research using the fecal microbiome to track the effects of therapeutic drugs on traumatic brain injury.
“I’m grateful for the scholarship because I now have a different mindset about data science, the need to think about all the tools and how we apply them to research projects,” Rojas said.
An eye to the future
The second class of fellows also includes Lydia Jennings, Ph.D., postdoctoral fellow in the Department of Community, Environment, and Policy at UArizona Mel and Enid Zuckerman College of Public Health. Dr. Jennings’ research focuses on data policy and environmental database governance in relation to Indigenous communities.
Just months into the fellowship, Dr. Jennings is already seeing the benefits of the data science tools she is acquiring that go far beyond organizing data.
“I didn’t learn those skills in my PhD program, but I really feel like that’s the direction research is going,” Dr Jennings said. “If you want to be at the cutting edge of research, I think it’s important to have these skills because they will be needed for most future funding opportunities.”
“A lot of what happens in data science is team science.”
Merchant from Nirav, MS
Dr. Jennings also offers a unique perspective to her peers in the Data Science Fellows program, according to her postdoctoral advisor, Stephanie Russo Carroll, DrPH, MPHassistant professor of public health policy and management at Zuckerman College of Public Health.
“I think she contributes more than most students can, in terms of thinking about the larger sets of principles that must affect not only our behavior as data scientists, but how we create a cyberinfrastructure and for which we establish interaction policies. with this infrastructure,” Dr. Carroll said.
Build a network
Data science fellows are trained and mentored for a year, during which they meet twice a week for formal lectures and lab time.
They are expected to spend some of their time in the data science learning space of bioscience research labs, where they work with fellow fellows, participate in special projects, develop their data science and domain expertise, develop training materials, and host workshops and webinars. They spend the rest of their time applying the tools and concepts to their labs and research projects.
The program already has its first success story. Gustavo de Oliveira Almeida, PhD, coordinator of the Health Sciences Sensor Lab at the University of Arizona, was among the first cohort of data science fellows. His fellowship has focused on how multiple streams of data can be collected in real time to drive action. The experience prepared Dr. Almeida for his new position at the UArizona Sensor Lab, and now he helps others on campus.
“We haven’t lost that talent,” Merchant said. “That’s our goal with every cohort. We want to find them a home at university, where they can help many people. We hope to build a network of people across campus to collectively elevate data science and best practices for research analytics.