Meeting Times

  • Wednesday, July 22, 1:30 PM - 5:00 PM
  • Thursday July 23, 9:00 AM – 5:00 PM
  • Friday July 24, 9:00 AM – 5:00 PM

Classroom: Randall Rollins Building 205 (RRR 205)

Module Summary

This module introduces key concepts in infectious disease modeling alongside core principles of human–AI teaming. Students will begin with a guided walkthrough of AI prompting using an example dataset, demonstrating how to build a full forecasting pipeline step-by-step. This demo is followed by hands-on labs where students apply the same prompting strategies to a more comprehensive dataset using AI tools and basic R. Sessions integrate brief lectures with practical exercises, emphasizing how humans guide, validate, and refine AI-generated analyses—including data cleaning, visualization, model building, and forecasting.

Prerequisites

This module assumes a basic working knowledge of the R programming language, including running scripts, installing packages, and working with data in the R environment. Students should be comfortable navigating files and folders on their computer and have familiarity with common coding workflows. Prior experience with version control systems is not required but will be beneficial.

Required Software

Software: R, RStudio, Visual Studio Code (VS Code), Git, GitHub Account, GitHub Copilot

Required Setup:

  • Install the latest versions of R and RStudio.

  • Install Visual Studio Code and the R extension.

  • Install Git and configure it for use with GitHub.

  • Create a GitHub account if you do not already have one.

  • Obtain access to GitHub Copilot.

Students planning to use GitHub Copilot should complete the registration process at least 72 hours before the module to allow sufficient time for account verification and activation. Students with a valid .edu email address are encouraged to apply for the GitHub Education Program, which includes access to GitHub Copilot benefits. Additional information can be found through GitHub Education.

Students without GitHub Education access may use the free version of GitHub Copilot, which includes usage limitations. The GitHub Copilot Pro plan is recommended for this module and includes a free trial period for eligible users. Additional details regarding software installation and configuration will be provided in the module setup materials.

Module Content

  • Overview of infectious disease forecasting and its role in public health decision-making
  • Foundations of AI and human-AI teaming, including when to use which AI tools for a given task
  • Introduction to GitHub and VS Code for reproducible, collaborative forecasting workflows
  • Data cleaning and preparation of surveillance data for forecasting
  • Effective prompting for AI-assisted coding and analysis
  • Using rules.md files to guide and constrain AI collaborators
  • Hands-on forecasting labs: fitting models and generating forecasts
  • Overview of forecast model evaluation
  • Assessing forecast calibration and performance in practice
  • AI and human-AI teaming evaluation, with iterative model refinement using AI
  • Independent free-coding, questions, and wrap-up

Data Sources

Instructors

Lior Rennert, PhD

Dr. Lior Rennert is Associate Dean for Health Sciences in the College of Behavioral, Social, and Health Sciences, Associate Professor of Biostatistics in the Department of Public Health Sciences, and Founding Director of the Clemson Center for Public Health Modeling and Response. He received his PhD degree in Biostatistics from the University of Pennsylvania’s Pearlman School of Medicine, MS degree in Statistics from the University of Chicago, and BS in Mathematics from The Pennsylvania State University. During the COVID-19 pandemic, Dr. Rennert led Clemson’s Public Health Strategy team to provide data analytics and help guide university policy. His current work focuses on the development of data-driven approaches to guide health-related decision making. His research has led to over 90 high-impact publications in the top scientific, medical, and health journals. He has procured approximately $30 million in funding as principal investigator from the National Institutes of Health and Centers for Disease Control and Prevention. His projects aim to develop a statewide network for real-time outbreak detection, forecasting, and coordinating emergency health response. In these efforts, Dr. Rennert has helped build statewide and national collaborations between state health departments, health systems, community partners, and academic institutions in order to integrate Center research into practice and ultimately improve health outcomes across the state of South Carolina and the nation.

Email: liorr@clemson.edu

Nathan McNeese, PhD

Dr. Nathan J. McNeese is the Associate Vice President for Technology & Innovation, the McQueen Quattlebaum Endowed Professor of Human-Centered Computing, the Founding Director of the Clemson University Center for Human-AI Interaction, Collaboration, & Teaming, and the Founding Director of the Team Research and Analytics in Computational Environments (TRACE) Research Group at Clemson University. In his AVP role, Dr. McNeese leads university-wide initiatives in artificial intelligence (AI) strategy, research, and innovation. He previously held the CECAS Dean’s Professorship at Clemson prior to his current AVP and endowed appointments. He received a PhD in Information Sciences & Technology from The Pennsylvania State University. A pioneer in human-AI collaboration and teaming, Dr. McNeese has been instrumental in advancing human-centered approaches to AI research and system development. He has been a principal investigator or co-principal investigator for more than 30 research grants and awards, generating over $40 million in funding. He is a recipient of the prestigious NSF CAREER Award. His research work is funded by the U.S. National Science Foundation, Air Force Office of Scientific Research, Office of Naval Research, Army Research Office, Agency for Healthcare Research and Quality, Department of Education, and several other industry and state agencies. He currently serves on multiple international/societal programs and technical committees, in addition to multiple editorial boards. He has worked with the United Nations, the North Atlantic Trade Organization (NATO), and multiple other countries and international organizations to provide guidance on human-centered AI. He is a National Academy of Science, Engineering, and Medicine (NASEM) board member on the Board of Human Systems Integration (BOHSI), a previous member of multiple National Academy of Sciences initiatives and consensus studies, and a previous member of the Army Research Lab HRED Technical Advisory Board. He is the recipient of the Clemson University Researcher of the Year, the Clemson University Research, Scholarship and Artistic Achievement Award, the HFES William C. Howell Young Investigator Award, and The Pennsylvania State University College of Information Sciences & Technology Overall Outstanding Alumni Award among additional significant honors. His research has received multiple best paper awards/nominations (9 total) and has been published in top peer-reviewed human-computer interaction and human factors venues over 200 times.

Email: mcneese@clemson.edu

TA: Amanda Bleichrodt, PhD

Dr. Amanda Bleichrodt is a postdoctoral fellow in the Center for Public Health Modeling and Response, specializing in infectious disease modeling and forecasting. She received her Master of Public Health from The Ohio State University, and a doctorate from Georgia State University in population health Sciences with a concentration in epidemiology. Her research interests include using AI for evaluating, refining and applying various statistical and mathematical modeling toolkits for forecasting disease outbreaks and developing user-friendly forecasting tools.

Email: ambleic@clemson.edu

Schedule

Time Day 1 Day 2 Day 3
9:00 - 10:30 am -

Activity 1 Recap

Lecture 4: Prompting

Activity 2: Interactive Activity & rules.md Files (begins)

 Lecture 4: Overview of Model Evaluation
10:30 - 11:00 am - Break Break
11:00 - 12:30 pm - Activity 2: Interactive Activity & rules.md Files (continued) Activity 4: Model Evaluation
12:30 - 1:30 pm - Lunch Break Lunch Break
1:30 - 3:00 pm

Introductions

Lecture 1: Overview of Forecasting

Lecture 2: Introduction to AI and Human-AI Teaming

Lecture 5 (Lab): Forecasting

Activity 3: Forecasting Lab

Lecture 5: AI/HAT Evaluation & Working with AI for Refinement

Activity 5: Refining Models
3:00 - 3:30 pm Break Break Break
3:30 - 5:00 pm

Lecture 3 (Lab): Introduction to GitHub, VS Code & Set Up

Activity 1: Data Cleaning

 Activity 3: Forecasting Lab (continued) Free-Coding, Questions & Wrap-Up