AI Sprint Grant recipient aims to help nursing students strengthen their clinical reasoning
Launched earlier this year, the CU system Artificial Intelligence (AI) Sprint Grant: AI for Teaching & Learning is focused on improving course outcomes using AI with goals of supporting and accelerating innovative teaching practices that leverage AI to enhance student learning.
The grant is designed to provide faculty with the resources and time needed to develop and implement AI-driven pedagogical strategies for the specific purpose of increasing student performance relative to the learning goals/outcomes of a single course. The ‘sprint’ structure is designed to meet the pace of AI evolution, and in doing so, foster an environment of experimentation and growth with meaningful, of-the-moment outcomes toward improving student learning.
Among the faculty receiving grants earlier this year was UCCS’ Kristen Vandenberg, Helen and Arthur E. Johnson Beth-El College of Nursing and Health Sciences, whose project is titled “Clinical Decision Validation in Advanced Child and Adolescent Psychiatric Practice.” The project will implement a structured AI-supported Clinical Decision Validation Protocol within NURS 6803 to strengthen diagnostic reasoning and child/adolescent prescribing safety. Students will complete independent case analyses and then use a secure platform, UpToDate/ UpToDate Expert AI, to compare and refine their decisions.
This project builds upon prior scholarly work examining the integration of UpToDate into graduate nursing education and extends that work into AI-supported clinical decision validation. Outcomes will be evaluated qualitatively through analysis of pre- and post-calibration narratives and student reflections to identify shifts in clinical reasoning and bias awareness.
Q&A with Kristen Vandenberg
Q. What inspired you to apply for the AI Sprint Grant?
A. I have always been interested in helping students strengthen their clinical reasoning.
As an instructor, it is difficult and extremely time-consuming to provide the feedback students need on their reasoning and decision making when working with complex cases.
Including an AI-generated response to the case study from the secure platform UpToDate/ UpToDate Expert offers students a different type of input to compare and refine their decisions prior to my instructor feedback.
Q. Can you describe your project and how you hope using AI will help students achieve learning outcomes in your course?
A. I want my students to be able to use AI as a clinical reasoning tool – not to go to AI for the answers, but to be challenged to compare AI-generated clinical reasoning with their own clinical reasoning. I want them to be able to identify feedback from AI, to consider their own cognitive biases surfaced in the comparison process, and to source more detailed justification to support their decision making. Often in psychiatric nursing, we use our own experiential learning to guide our clinical decisions, and it’s valuable to have more of an objective type of measurement in front of you.
To briefly describe the process: First, students review a series of case studies and verbally explain their clinical reasoning on Canvas. Next, the students put the case studies into UpToDate Expert AI to generate its clinical reasoning and compare their own reasoning to the AI-generated reasoning. This process of reflection is the core of the assignment – whether and how the AI-generated response helped them and strengthened their clinical reasoning. Finally, they redo their treatment plan based on the comparative process.
During their studies, students often learn how to provide ‘textbook,’ hypothetical responses to case studies. Whereas, with enough information about a patient, AI oftentimes will challenge the student’s decision making in a constructive way. For example, a student may identify the ‘perfect’ medication for a case study patient. The AI response can then point out that the student’s ‘perfect’ might be great, but it costs $500 and the case study patient earns minimum wage. This is the type of useful challenge the AI tool can offer.
Q. What ideas, research or experiences have influenced your approach to using AI in your teaching?
A. My approach comes both from clinical practice and education, which is a perspective my students value. I believe it is important that I teach students to go beyond memorizing information by thinking critically.
As a professor, I want grades, numbers, objective measurements. But as a psychiatric provider, I’m comfortable with that gray area and that’s what I like to teach my students. We are not dealing with black and white, and there isn’t often a right answer. Students are learning how to use AI as a guide while remembering their own clinical reasoning always come first.
Q. What AI tools are you using and what led you to choose those particular tools?
A. I’m using UpToDate and UpToDate Expert AI. UpToDate is a leading evidence-based clinical decision support resource that introduced the AI clinical tool, UpToDate Expert AI, in 2025. This tool is trained exclusively on UpToDate’s database of clinical evidence and expert-authored content.
Now, instead of using UpToDate to read articles, I can put in a case study and prompt it to help me work through it. Its response will pull from the literature in its database.
Part of this grant will cover student access costs for UpToDate Expert AI. In previous courses, students pay the license fee for this software in lieu of a textbook and I have presented on this at multiple nursing conferences. One goal of the project is to produce compelling evidence to support software access through the library.
Q. How will you know that your project has been successful? And what evidence will you look for to understand the impact on student learning?
A. What I’ll be looking for in the success in those reflection pieces. For example, ‘Did the AI help you discover any gaps within your treatment plan?’ ‘Did it help you see any biases that you had within its treatment plan?’ If students can reflect and then be able to modify their clinical reasoning, that’s a success to me.
I will use a slightly modified version of a reflection tool I have used it many courses in Canvas. I teach a nursing reflection course to our doctoral students that focuses entirely on the reflection process.
In this course, case studies get progressively more challenging with students progressing from minimal levels to greater levels of competency by the end. This project will measure whether the use of AI improves final student competencies to outcomes prior to AI implementation.
If successful, these improved outcomes would also complement the movement towards more competency-based education in nursing.
Q. How do you envision elements of your project being adopted or adapted by instructors in other courses, either in psychiatric nursing or across nursing or even other disciplines?
A. Even with the focus at conferences on the use of AI, I’m not seeing my peers addressing clinical reasoning in the same way as me. My hope is for this project to provide a model that other educators can use to guide students into using AI. Clinical reasoning is essential within any kind of healthcare discipline. I look forward to being able to disseminate the information nationally among nurse practitioner faculty and be able to say, you can use teaching method in any setting, it doesn't have to be psychiatric.