JMIR Publications

ABSTRACT

Background:

Health-care-professional (HCP) generated vignettes are commonly used to illustrate and analyze patient experiences, shaped through clinical reflection to support provider understanding, training, and practice improvement. However, this approach is limited by the subjective interpretation of narratives and the time-consuming manual process. As an alternative, patients could record video blogs (vlogs) of their experiences, which can then be transformed into vignettes using generative AI (gen-AI) and carefully designed prompts.

Objective:

This study compares the feasibility and utility of two different vignette creation methods, manual and gen-AI, from user-generated vlogs about living with chronic pain.

Methods:

Short commentary videos were recorded by a person living with chronic pain of unknown origin. These were transcribed and used to create vignettes. From 64 videos, three one-minute clips were selected, each representing a key life stream: University Student, International Traveller, and Chronic Pain Patient, based on prior thematic analysis. Three vignettes per creation method were created from a profile description, the three user-generated video clips per life stream, analytic commentary of each clip produced by a researcher with 15-years of experience in manual vignette creation for clinical use, and a short summary of each video. A comparison between manually constructed and AI-generated vignettes evaluated coherence, contextual accuracy, narrative depth, and utility in health communication and user experience research. Additionally, the person responsible for generating the raw videos (PX) provided commentary on this process, offering critical insights into the authenticity, emotional resonance, and perceived usefulness of each vignette format.

Results:

. This study demonstrates that manual and gen-AI vignette creation methods are feasible approaches for analyzing and representing user-generated vlogs about living with chronic pain. Each method offers distinct utility: manual vignettes provide rich, nuanced narratives capturing emotional and social complexities, while gen-AI vignettes offer efficient, concise summaries with some loss of detail. PX’s reflections reinforced these findings.

Conclusions:

AI-generated vignettes with human review offer an efficient way to capture chronic pain patients’ experiences. These vignettes have the potential to support training, communication, and sharing of patient insights. Clinical Trial: N/A