Skip to main content

Renaissance Computing Institute (RENCI) – 

Notes, takeaways, and resources from our January 2023 event

On January 26, 2023, Carolina Data Science Now hosted the tenth iteration of its seminar series, which will strive to link the people, research, and resources by highlighting the many faces of data science across our campus and demonstrating the integral role data science can play in all disciplines.

This Month’s Speakers

The theme of the event was “Advancing Education, Training, and Care.” The event was moderated by Robert Hubal, and the speakers were selected to provide insight on how data science is used to improve the experiences of students, trainees, and patients.

Matthew Bernacki | School of Education

Matthew Bernacki discussed his team’s current work to improve undergraduate success in STEM courses. The team uses campus data systems to provide targeted support for self-regulated learning.
Read more about the lightning talk here.

Saif Khairat | School of Nursing

Saif Khairat uses data science to improve healthcare delivery, access, and outcomes through two projects. One seeks to understand and address geographic access disparities, and the other seeks to improve physician and nurse electronic health record (EHR) access and use.

Read more about the lightning talk here.

Adam Kiefer | Exercise and Sport Science

Adam Kiefer is working on two projects that use data science to help enhance athlete performance, prevent injuries, and assist with injury recovery through AI and behavioral dynamics that analyze, measure, and model complex human health and performance.

Read more about the lightning talk here.

Speaker Q&A

Questions for the speakers were collected through an EasyRetro board. Topics during this section included:

  • Data modeling for educational purposes is based on ingesting any information students consent to. It harnesses on and off-campus computer solutions. Future educational data modeling solutions may involve Google Classroom and other K-12 learning management systems to assist K-12 students and teachers.
  • Athletic modeling, simulation, and training software may have applications beyond sports, possibly aiding training, learning, and rehabilitation. To date, however, Keifer’s team has worked with campus football and basketball and licensed the technology with a startup contracted with a major league baseball team.
  • Creating a context-specific detection model for each sport is a large challenge, but about 80% of Keifer’s platform is modular, so they can spend time building these models while everything else remains the same.
  • One-on-one coaching sessions (as opposed to group classroom-style training) tend to make the physicians more effective in their documentation and improve their ability to use EHR systems.
  • North Carolina has several neighborhoods and entire counties that are being left behind in healthcare. For some, there is no physical primary care service present — for example, Gates County has 10,000 people and zero primary care providers. Understanding this may help lawmakers understand where to invest resources and effort.
  • Bernacki’s educational modeling is primarily informed by the instructors and the flow of a course, incorporating factors such as when assignments are most challenging and where the most effort is needed. Therefore, it can be used to track potential student progress throughout the semester. The team currently uses the model to understand behavioral changes and see how different interventions impact how students believe things about the course and themselves, how they behave, and what outcomes they achieve in various circumstances. They are working to make models more responsive to better support students over time.
  • According to Keifer, with Amazon Web Service (AWS) infrastructure, it is easier to bring in students with little-to-no data science experience and quickly onboard them into the workflow, and having them help with more remedial tasks like hand coding. From there, they can scale these interactions to work with AWS microservices. As an added benefit, AWS also allows the team to provide remote jobs for traveling student athletes.
  • Much of the data used in these projects can be used for data science classes. In fact, data from these projects are already in use in various courses across UNC-Chapel Hill.

During the event, several attendees shared resources relevant to the conversation. A full list of educational programs, funding opportunities, on-campus support services, tools and software, and more shared during Carolina Data Science Now seminars can be found on our Resources page.

Next Seminar

Our next seminar will be held on November 10 at 12 PM (ET). Please stay tuned to our website for the most updated information.

Check out a playlist of our previous events here.

Comments are closed.