JMIR Publications

ABSTRACT

Background:

Despite growing emphasis on open science and equity in research, qualitative data capturing diverse human experiences and perspectives are rarely reused beyond the original study. Increasingly data repositories are utilized to make this data publicly available, but it is unclear whether this data can effectively be identified by researchers interested in secondary data analysis.

Objective:

We describe a protocol for identifying and characterizing archived qualitative datasets in leading public repositories, developing an AI-based tool to enhance qualitative data reuse, and validating that tool using existing data.

Methods:

We will search 4 leading repositories to assess the scope and identifiability of existing publicly available qualitative data sets. We will subsequently build the HEARs Archive, a directory of de-identified study data that is only accessible indirectly through the use of the HEARs Portal. The HEARs Portal will be supported by large language model (LLM)-based tools using retrieval-augmented generation (RAG). The AI tools’ performance will be assessed across 3 domains: relevance of identified studies, validity as evaluated by comparison with human qualitative data analysis, and robustness against the addition of irrelevant information.

Results:

Preliminary review of existing data repositories has begun. Anticipated study completion is December 31, 2026.

Conclusions:

The proposed project intends to fill important gaps related to improving capacity for qualitative data dissemination and reuse. Clinical Trial: This is not a trial; not applicable.