AI-enabled Qualitative Research: IEN Retention Insights

According to the PLOS One study (Ryan et al., published August 20, 2026), ecosystem-level barriers from national visa policy to day-to-day ward management jointly undermine IEN retention, and AI-enabled qualitative research can accelerate trustworthy thematic synthesis of such focus-group data.

• 21 IENs participated in four focus groups held between June 8 and June 29, 2023, as reported in the PLOS One study published August 20, 2026.
• The PLOS One study cites that Ireland had 51.8% internationally educated nurses in 2023 and that 78% of new nursing registrants in 2023 were IENs, highlighting scale and urgency (PLOS One, 2026).
• The PLOS One study notes prior research where 43% of IENs were considering leaving Ireland, reinforcing that retention (not only recruitment) must be measured and managed (PLOS One, 2026).
• Participants in the PLOS One focus groups used direct language: “We have colleagues who have waited for more than a year to just have your family in. That’s a very big challenge” (P2, FG2), giving qualitative anchors AI tools can extract and quantify.

Answer: The PLOS One study used semi-structured focus groups to capture lived experience and analysed transcripts with reflexive thematic analysis. According to the PLOS One article (Ryan et al., published August 20, 2026), researchers conducted four face-to-face focus groups with 21 internationally educated nurses across one Irish hospital group between June 8 and June 29, 2023.

The PLOS One study (Ryan et al., 2026) recorded audio, used a certified third-party service for verbatim transcription, managed data in NVivo™ 14, and generated 206 initial codes before developing themes mapped to Bronfenbrenner’s macrosystem, exosystem, mesosystem and microsystem framework.

The PLOS One study (Ryan et al., 2026) emphasised reflexivity and COREQ reporting standards, which makes the dataset well suited to reproducible AI-assisted coding because the transcripts, analytic memos, and code refinement logs are described in the methods.

Answer: The PLOS One study shows that multi-layered ecosystem factors require multi-source, multi-scale qualitative evidence collection and synthesis. According to the PLOS One article (Ryan et al., 2026), barriers range from visa and childcare policy at the macrosystem to poor induction and role mismatch at the exosystem and mesosystem, and to day-to-day managerial behaviours at the microsystem.

Healthcare HR teams need to measure both process and experience: the PLOS One study (Ryan et al., 2026) documents delayed inductions (“I got it after maybe six or seven months after arriving” (P3, FG4)) and role mismatch (P3, FG2), which are operational metrics HR can track and evaluate.

Researchers should collect verbatim transcripts, analytic memos, and code logs because the PLOS One methods (Ryan et al., 2026) used NVivo™ 14 and generated a 206-code set that supports reproducible theme development; AI-enabled platforms can compress this workflow while preserving reflexive decisions.

Answer: The PLOS One study (Ryan et al., published August 20, 2026) demonstrates that ecosystem-level qualitative evidence is essential to understand IEN retention and that AI-enabled qualitative research can compress time-to-insight while preserving rigor.

Practical next steps: collect verbatim transcripts, preserve analytic memos, and use AI-assisted thematic tools to produce reproducible codebooks and cross-segment tables that directly map to policy levers identified in the PLOS One paper.

If you want to pilot this workflow, you can learn how Evidano handles transcription, thematic analysis, and secure data policies on the Evidano features page; for a hands-on trial, Try Evidano for free.