What Do I Do with All This Data?!

Interprofessional education (IPE) assessment is inherently complex and prickly. Challenges arise from the need to analyze data across diverse health professions, various levels of learners, numerous learning environments (e.g. classroom, simulation, clinical practice) and in contexts where competence in teams and teamwork, rather than individual performance, are the focus of evaluation. This complexity is compounded by the wide range of learning activities used to meet interprofessional competencies and the substantial time required for faculty to meaningfully review large volumes of data. At our institution, post-activity evaluations are collected for every IPE event, each of which includes rich qualitative responses. To manage this data efficiently and ensure its alignment with program outcomes, we piloted several AI tools to assist in the identification of themes and patterns across student feedback. Through this process, we developed a scalable method for analyzing qualitative data, mapping findings to interprofessional competencies, and creating visual summaries that support program evaluation and improvement. Intentional formatting of assessment outputs allow for the dissemination of data to vested partners, supporting accreditation, ensuring accountability for interprofessional learning outcomes, and informing curricular improvements that facilitate the transition of learners from education to interprofessional practice. In this session, we will share our process, tools, and lessons learned in hopes that others may adapt this approach to support their own IPE assessment efforts.

By the end of this presentation, participants will be able to…
1. Identify common challenges of assessing interprofessional education evaluation data across multiple professions, learner levels, and learning environments.
2. Describe a practical, AI-assisted process for analyzing qualitative evaluation data and aligning findings with interprofessional program outcomes.
3. Discuss benefits and risks of utilizing AI-assessed processes for analyzing qualitative data.