Gettin’ daggity with it: Using DAGs as Tools for Variable Selection

Ever pondered whether to include a variable in an analysis – is the variable necessary, will its inclusion/exclusion introduce bias in the analysis? Why is the variable important anyways – is it a mediator, a moderator, a confounder, or some combination of these?

This course introduces how to incorporate DAGs (Directed Acyclic Graphs) in analysis planning to help think through what variables to collect and use (or refrain from using) in an analysis.

Register

“Human-in-the-Loop” Thematic Analysis: Using R to Apply Current Recommendations for Incorporating LLMs into Qualitative Research

Do you want to explore current research recommendations in the literature on incorporating LLMs into qualitative/mixed methods data analysis, or are you interested in implementing LLMs into your qualitative/mixed methods workflow? If so, this short course is designed for you!

In this course we will examine current recommendations from the literature regarding integrating AI (specifically LLMs) into the process of qualitative coding. Acknowledging that a wide range of qualitative approaches exist, all examples and recommendations in this course will be based on the 6 Phase Thematic Analysis Framework proposed by Braun & Clarke 2006 to simplify the course scope.

No perquisites in qualitative methods or coding are required for this course – just bring your computer & your curiosity!

Register

Overview of 2026 NIH Requirements: Biosketch and Current and Pending (Other) Support

This session provides an overview of some of the upcoming changes to the National Institutes of Health (NIH) grant application requirements, including new Common Forms that will be required for due dates on or after January 25, 2026.

In particular, this presentation will focus on the Biosketch and Current and Pending (Other) Support forms, which will need to be completed using the SciENcv tool. It will include demonstrations of SciENcv as well as ORCID iD creation and linking steps. The presentation aims to prepare researchers for the new NIH requirements by providing detailed instructions and resources to ensure compliance.

This program is offered via Zoom by the Health Sciences Library and led by Katherine Howell, MSLIS.

Register

Healthcare AI

Join the TraCS Data Science Lab as we talk about the experience of implementing healthcare AI. Healthcare AI is generating unprecedented investment and regulatory momentum — yet the vast majority of AI pilots never reach frontline care.

This seminar cuts through the hype to examine why, tracing the full clinical AI deployment pipeline from model development through post-deployment monitoring and the overlooked governance, workflow, and implementation challenges that derail efforts. Using real-world case studies — including the widely-deployed Epic Sepsis Model — we'll explore how dataset shift, alert fatigue, and clinician behavior consistently outweigh algorithmic performance as barriers to impact.

Whether you're a clinician, informaticist, or health system leader, this talk will reframe how you think about AI in medicine: the future won't be decided by better models, but by better implementation.

Speaker:
David Friedlander, MD, MPH
Assistant Professor, Department of Urology
TDSL Faculty Scholar, TraCS Data Science Lab
UNC School of Medicine

register

Seminars in the NC TraCS Data Science Lab Seminar Series cover a range of topics related to health care data science, clinical data, data engineering, and working in these areas at UNC-Chapel Hill. These hybrid seminars are usually held monthly on the third Tuesday of each month from 12:30-1:30 p.m. in the NC TraCS suite on the 2nd floor of Brinkhous-Bullitt or via Zoom.

Strengthening Engagement in Research: Building and Maintaining Relationships with Patient & Community Partners

Meaningful partnerships with patients, community members, or other collaborators involved in your research are invaluable. Projects are set up for success when care is intentionally given to developing and strengthening partnerships over time.

This online training will describe best practices for building mutually beneficial partnerships. The session will also cover common challenges that researchers and patient, community, and other partners experience when working together, along with suggested solutions.

Participation in our Engagement in Research 101 or Engagement in Research Nuts and Bolts trainings are not required to attend this session; however, some knowledge of engagement, whether from prior training(s) or personal experience, may foster deeper understanding of the material in this session.

Presenters:
Alicia Bilheimer, MPH - Director of Engaged Science, NC TraCS
Veronica Carlisle, MPH, CHES - Senior Community Health Educator, UNC Lineberger Comprehensive Cancer Center (LCCC)
Nisha Datta, MS - Senior Project Manager, NC TraCS
Simone Frank, MPH - Senior Project Manager, NC TraCS
Jennifer Potter, MPH, CHES - Senior Program Coordinator for Clinical Outreach, LCCC
Members of the NC TraCS Community and Patient Advisory Board and the UNC Lineberger Community Advisory Board

Register

Engaging Patient, Community, and Other Partners in Your Research is a multi-part online training series. You may register for the entire series OR any single training session. This training series was developed collaboratively with patient, community, and researcher partners and is co-sponsored by the UNC Lineberger Comprehensive Cancer Center and NC TraCS Institute.

“Human-in-the-Loop” Thematic Analysis: Using R to Apply Current Recommendations for Incorporating LLMs into Qualitative Research

Do you want to explore current research recommendations in the literature on incorporating LLMs into qualitative/mixed methods data analysis, or are you interested in implementing LLMs into your qualitative/mixed methods workflow? If so, this short course is designed for you!

In this course we will examine current recommendations from the literature regarding integrating AI (specifically LLMs) into the process of qualitative coding. Acknowledging that a wide range of qualitative approaches exist, all examples and recommendations in this course will be based on the 6 Phase Thematic Analysis Framework proposed by Braun & Clarke 2006 to simplify the course scope.

No perquisites in qualitative methods or coding are required for this course – just bring your computer & your curiosity!

Register

Join us for an in-person workshop to learn more about AI workflows for data science with clinical applications. Large language models have rapidly moved from novelty to everyday use in teaching, research, software development, and data analysis. This workshop offers a practical framework for understanding and using modern AI systems by distinguishing among standalone large language models, chat agents, and full agents that connect models to tools and execution environments.

In this workshop, you will learn:

• Key principles that shape successful outcomes in practice
• Best practices for working effectively with chat agents
• How agents can support each phase of the data science lifecycle
• How to run agents securely and responsibly

Workshop location: Brinkhous-Bullitt Bldg., 2nd floor, room 219

The New NIH Public Access Policy: What You Need to Know

The 2024 NIH Public Access Policy includes several significant changes from the previous policy, and applies to all NIH-funded manuscripts accepted for publication on or after July 1, 2025. Learn more about what has changed, how to comply, and what to expect going forward.

This program is offered via Zoom by the Health Sciences Library and the Scholarly Communications Office, and led by Collin Drummond and Katherine Howell.

Register