This post explains how to turn the PLOS One focus-group dataset on internationally educated nurses into reproducible themes using AI-enabled qualitative research methods. According to the PLOS One study (Ryan et al., 2026), researchers ran four semi-structured focus groups with 21 internationally educated nurses between June 8 and June 29, 2023 and published the findings on August 20, 2026. This article is for qualitative researchers, HR and nursing workforce analysts who want a faster, auditable path from transcripts to policy-ready themes using AI qualitative analysis of focus groups.
Key Takeaways
According to PLOS One, the study of internationally educated nurses (IENs) in Ireland shows multi-layered ecosystem barriers to retention that span visa rules, housing, childcare, induction gaps, and day-to-day management.
- 21 participants were interviewed across four focus groups conducted between June 8 and June 29, 2023, according to PLOS One (Ryan et al., 2026).
- In 2023, 51.8% of Ireland’s nursing population were internationally educated nurses and 78% of new nursing registrants in 2023 were IENs, according to PLOS One citing OECD and NMBI statistics.
- Participants told the authors in PLOS One (Ryan et al., 2026) that visa and family reunification delays of “more than a year” and housing shortages were key push factors: “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).
- The PLOS One team coded 206 initial codes using NVivo™ and Braun and Clarke’s reflexive thematic analysis, showing a rigorous, software-supported thematic workflow reported by Ryan et al., 2026.
What Happened: Study design and analytic approach
Answer: The PLOS One study used four face-to-face semi-structured focus groups with 21 IENs to explore how macro, exo, meso and microsystem layers affect talent management (Ryan et al., 2026).
According to PLOS One (Ryan et al., 2026), participants came from Poland, India, Croatia, Latvia, the Philippines, Zimbabwe and Nigeria and each focus group lasted about 56 minutes on average.
According to PLOS One (Ryan et al., 2026), the authors transcribed recordings with a certified third-party service, managed the transcripts in NVivo™ version 14, generated 206 initial codes, and applied Braun and Clarke’s six-phase reflexive thematic analysis to build the final themes.
According to PLOS One (Ryan et al., 2026), the study followed COREQ reporting guidelines and ethical approvals (REC REF: 104/2021; KBS Research Ethics Application: 2021_12_KBS_15).
Findings Snapshot
| Date / Source | Metric | Value | Implication |
|---|---|---|---|
| June 8–29, 2023 (PLOS One data collection) | Focus groups | 4 groups, N = 21 participants | Qualitative saturation judged sufficient by the authors; data richness supported reflexive TA |
| 2023 (cited in PLOS One) | Share of IENs in Ireland | 51.8% of nursing population in 2023 | High national reliance on internationally educated nurses; retention is strategically important |
| 2023 (cited in PLOS One) | New nursing registrants who were IENs | 78% of new entrants in 2023 | Recruitment inflow concentrated in internationally educated hires rather than domestic training |
| Analysis process (Ryan et al., 2026) | Initial codes | 206 codes generated in phase 2 | Code volume indicates granular, inductive coding before thematic synthesis |
Implications for qualitative researchers and HR teams
Answer: The PLOS One findings imply that qualitative teams must capture cross-level (macro→micro) context and preserve participant voice to inform retention policy, according to Ryan et al., 2026.
Qualitative researchers should plan for multi-level coding because, according to PLOS One (Ryan et al., 2026), participants linked national policies such as visas and childcare to bedside retention decisions.
HR teams and workforce planners should note the statistics cited in the study: Ireland’s 51.8% IEN share and 78% of new registrants in 2023, as reported in PLOS One, indicate that recruitment without systemic retention measures risks chronic turnover.
Practically, include prompts in interview guides that elicit macrosystem effects (housing, family, visa timelines) as PLOS One (Ryan et al., 2026) showed these themes emerged organically from participant narratives.
How Evidano Helps: from transcripts to ecosystem themes
Problem: Large, multi-layered focus-group datasets are slow to synthesise
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Solution: Evidano ingests transcripts, supports custom dictionaries, and produces thematic maps and code co-occurrence networks to speed reflexive thematic analysis while preserving audit trails for decisions.
Problem: Maintaining participant voice and precise quotes across levels
According to PLOS One (Ryan et al., 2026), verbatim quotations such as “the toughest period of my life” (P1, FG2) are central to evidence.
Solution: Evidano preserves timestamped quotes and links extracts to codes so teams can export quotations for reports and policy briefs without losing context; see Evidano features.
Problem: Cross-segment comparisons (e.g., by country of origin or department) are tedious
According to PLOS One (Ryan et al., 2026), participants from multiple countries reported both shared and distinct barriers.
Solution: Evidano offers cross-segment frequency and co-occurrence analysis, allowing researchers to quantify theme prevalence and compare subgroups rapidly, which supports evidence-based policy recommendations.
Problem: Transcription and PII concerns when working with vulnerable participants
According to the PLOS One methods section (Ryan et al., 2026), the authors used a certified third-party transcription service and protected anonymity.
Solution: Evidano provides secure transcript ingestion with PII redaction and a custom dictionary for non-standard names or medical terms; see Evidano speech-to-text and Evidano data security.
FAQ: AI qualitative analysis of focus groups
How many focus groups are enough for a reflexive thematic analysis?
Answer: There is no universal number; the PLOS One team closed recruitment after four groups (N = 21) because additional data was unlikely to add new interpretive insights, according to Ryan et al., 2026.
Support: Ryan et al., 2026 cited Malterud et al. (2016) on information power to justify sample sufficiency.
Can AI replace the reflexive judgement required by Braun and Clarke’s method?
Answer: No, AI supports but does not replace researcher reflexivity; Ryan et al., 2026 used NVivo™ and researcher-led reflexive thematic analysis to retain interpretive control.
Support: The PLOS One authors explicitly used software as an organisational aid and emphasised that analytic judgements remained researcher-led.
How do I preserve participant quotes and audit trails for policy reports?
Answer: Export timestamped, coded extracts and a decision log alongside your final themes to preserve transparency, a practice used and recommended by Ryan et al., 2026.
Support: PLOS One (Ryan et al., 2026) documented reflexive memos, decision logs, and NVivo extracts to demonstrate transparency and rigour.
What errors should I watch for when using AI to analyse focus groups about sensitive topics?
Answer: Watch for decontextualised quotes, over-aggregated codes, and failure to account for macrosystem context, which the PLOS One study showed can change interpretation when absent.
Support: Ryan et al., 2026 demonstrated that omitting macro factors like visa delays would understate drivers of retention and misdirect recommendations.
Conclusion & Next Steps
The PLOS One study (Ryan et al., 2026) shows that retention of internationally educated nurses depends on multi-layered ecosystem factors from visas and childcare to ward-level management.
For qualitative researchers and HR teams, combining careful reflexive methods with AI-assisted coding, cross-segmentation, and secure transcription accelerates synthesis without sacrificing transparency.
If you want to pilot AI-assisted thematic workflows that preserve quotes, code histories, and cross-segment analyses, Try Evidano for free.
For product details and pricing, visit Evidano features and Evidano plans.
Topics
- AI qualitative analysis of focus groups
- AI-enabled qualitative research
- focus group thematic analysis
- qualitative analysis platform
Keep reading
- Commentary on NewsAI for Qualitative Analysis of Museum VisitorsAI turns observation notes into insights: qualitative analysis of museum visitors that finds themes, age segments, and exhibit recommendations for UX teams
- Commentary on NewsBoost Exhibit Design: AI Qualitative Analysis for MuseumsUse AI qualitative analysis for museums to convert observational studies into targeted exhibit changes. Learn from PLOS ONE findings and try Evidano to accelerate insight.
- Commentary on NewsImprove Museum Visitor Research: AI Qualitative AnalysisAI qualitative analysis for museums: convert visitor observations into themes, counts, and actionable design changes. Learn from a PLOS ONE study and see how Evidano helps.