Nursing Initiatives

Future-FLO

Generative AI Research Lab

Sketch of woman in nurse uniform holding a lighted lightbulb. Schematics and calculations are on the backround behind her.

Proposed by Regina Russell, PhD, Julia Phillippi, PhD, and Patricia Sengstack, DNP, Future-FLO is a research and chatbot development project that stands for Feedback Loops and Outcomes (FLO). The FLO Team is standing on the shoulders of nursing history, including Florence Nightingale's tradition of shining light on standard processes through innovative data analysis and statistics. (You can read more about Nightingale’s health care data visualizations and her election as the first female member of the Royal Statistical Society in 1858 at the UK Science Museum here.)

Our goal is to test the use of large language models in grant evaluation for nursing education. The Future-FLO team is partnered with Vanderbilt University internal generative AI – Amplify.

Funding

Vanderbilt University Chancellor’s Seed Grant for Generative Artificial Intelligence (February 2024-Augest 2025)

VUSN Health Equity Faculty Fellowship (August 2024-August 2025)

Faculty & Staff

Students

  • Md. Mashiur Rahman Khan

    Md. Mashiur Rahman Khan

    Vanderbilt University Computer & Cognitive Science
    Undergraduate Student Research Assistant and Lead Chatbot Trainer

  • Lia Nagge

    Lia Nagge

    Master of Public Health Candidate at Vanderbilt University
    Health Equity Research Assistant

Publications

Conference Posters & Presentations

Publications (in Progress)

  • Russell RG, Wang M, Khan MM, LaNoue MD, McGrew H, Swift S, Sengstack P, Phillippi J. Assessing Artificial Intelligence to Support Grant Evaluation in Nursing Education. (Under Review, August 2024)

Lab Alumni

  • Patricia Sengstack, DNP, RN-BC, FAAN, FACMI, Vanderbilt University Medical Center
  • Mike Wang, MEd, University of North Carolina Wilmington

Please note that all content generated by the Future-FLO chatbot is created by Vanderbilt University's internal generative AI - Amplify. Performance may vary, and the results may vary across all conditions. We strongly recommend double-checking the results before implementation. The output should not be directly used in education, healthcare, or any other field that requires precise and reliable data for decision-making.