Primary readers: qualitative researchers, hospital workforce analysts, and HR leaders who need fast, defensible syntheses of interview and focus-group data. The primary keyword for this article is "AI qualitative analysis focus groups" and this post explains how AI-enabled methods can reproduce and extend the reflexive thematic analysis used in the PLOS One study by Ryan, Berkery, and Makowski (2026). According to the PLOS One article, the study analysed four focus groups involving 21 internationally educated nurses (IENs) and used NVivo 14 plus Braun and Clarke’s reflexive thematic analysis to generate ecosystem-level themes; this post shows how an AI-first pipeline can make those same steps faster, auditable, and cross-segment ready.
Key Takeaways
The PLOS One study finds that multisystem barriers across macrosystem, exosystem, mesosystem, and microsystem layers undermine the integration and retention of internationally educated nurses (PLOS One).
- According to PLOS One, the researchers ran four face-to-face focus groups with a total sample of 21 IENs between June 8 and June 29, 2023, with a mean session length of 56 minutes.
- According to PLOS One and OECD data cited in the article, Ireland had 51.8% of its nursing population internationally educated in 2023, and 78% of new nursing registrants in 2023 were IENs, underscoring national reliance on migrant nurses.
- Using NVivo 14 and Braun and Clarke’s reflexive thematic analysis, the PLOS One authors generated 206 initial codes before clustering into ecosystem themes, a workflow that AI-assisted tools can accelerate while preserving reflexivity.
What happened and how the PLOS One study worked
Answer: The PLOS One study used reflexive qualitative methods to map how host-country ecosystem layers shape talent management for IENs.
According to PLOS One, Ryan et al. (2026) conducted four purposive, homogeneous focus groups across one Irish hospital group between June 8 and June 29, 2023, recruiting 21 IENs from countries including India and the Philippines, Poland, Croatia, Latvia, Zimbabwe, and Nigeria.
According to PLOS One, the researchers audio-recorded sessions, used a certified third-party for verbatim transcription, managed data in NVivo™ version 14, and followed Braun and Clarke’s six-phase reflexive thematic analysis, during which 206 initial codes were generated before theme development.
According to PLOS One, key methods safeguards included ethical approvals (REC REF: 104/2021), reflexive memos, peer debriefs, and participant anonymisation to protect a vulnerable sample.
Findings Snapshot
| Date / Source | Metric | Value | Implication |
|---|---|---|---|
| June 8–29, 2023 (PLOS One) | Focus groups | 4 groups, N = 21 participants, mean session 56 minutes | Sufficient conversational depth for reflexive thematic analysis but limited cross-site generalisability |
| 2023 (OECD cited in PLOS One) | Share of IENs in Irish nursing population | 51.8% | High national reliance on internationally educated nurses demands retention-focused talent management |
| 2023 (NMBI cited in PLOS One) | New nursing registrants who were IENs | 78% of new entrants | Indicates recruitment is front-loaded; retention and integration systems are critical |
Implications for qualitative researchers and workforce analysts
Answer: The PLOS One study shows qualitative teams must capture ecosystem-level context and link micro narratives to macro policy evidence.
According to PLOS One, participants reported visa delays, housing shortages, childcare gaps, role mismatch, rushed induction, and unclear promotion pathways; these concrete issues map to policy levers and HR interventions.
According to PLOS One, participant quotes illustrate severity: one nurse said, "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), and another reported, "we know that in the last two to three months nearly 20 families moved to Australia [...] And they were here maybe 15, 16 years" (P2, FG1).
For researchers, this implies that focus-group transcripts require: rigorous transcript QA (time-stamped, speaker-tagged), systematic coding that preserves context, and cross-layer mapping to policy data like the OECD 2023 figures cited in the article.
How Evidano helps: mapping problems in IEN research to AI-enabled solutions
Problem: slow, manual transcription and QA
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Solution: Evidano provides secure automated transcription with custom dictionaries and PII redaction to match the PLOS One workflow that used certified verbatim transcripts; teams can import audio and get time-stamped, speaker-attributed transcripts ready for coding.
How it fits PLOS One: where Ryan et al. used a third-party transcription service, Evidano can reduce turnaround time while preserving transcript quality for reflexive analysis.
Problem: 200+ initial codes and slow theme refinement
Solution: Evidano performs AI-assisted thematic extraction, frequency analysis, and co-occurrence mapping so researchers can see the 206 initial codes analogue quickly and explore alternative clusterings without losing the researcher-led interpretive judgment.
How it fits PLOS One: Evidano reproduces NVivo-style organisation with added cross-segment filters (e.g., country of origin, hospital site) to test which ecosystem themes hold across subgroups.
Problem: linking qualitative findings to policy metrics
Solution: Evidano supports document ingestion (policy reports, OECD statistics), enabling side-by-side citation, quote pullouts, and evidence matrices so qualitative themes from focus groups can be directly linked to macro indicators cited in PLOS One.
How it fits PLOS One: researchers can attach the OECD 2023 figures and PLOS One excerpts to evidence cards to build an actionable policy brief.
Problem: auditability and reflexivity in team coding
Solution: Evidano stores decision logs, coder notes, and versioned codebooks so reflexive thematic analysis practices (memos, peer debriefs) used by Ryan et al. can be preserved and exported for publication.
How it fits PLOS One: Evidano complements the reflexive TA approach by making analytic moves transparent and reproducible for ethics and peer review.
Relevant Evidano features
See Evidano’s features page for thematic and frequency analysis tools and speech-to-text for transcription options.
FAQ: AI qualitative analysis focus groups
Can AI reproduce reflexive thematic analysis?
Answer: AI can accelerate and surface patterns but cannot replace researcher reflexivity.
Supporting detail: According to PLOS One, the authors combined software (NVivo 14) with researcher-led reflexive steps and memos; AI tools should be used to propose codes and visualisations while researchers maintain analytic judgement.
How do I preserve participant voice when using AI?
Answer: Preserve verbatim quotes, time stamps, and speaker attribution in the dataset and export them unchanged.
Supporting detail: According to PLOS One, Ryan et al. reproduced participants’ words verbatim and annotated sensitive terms; Evidano supports export of quote extracts and decision logs for transparency.
Will AI compromise data security or ethics?
Answer: It depends on the vendor and the contractual model for data use.
Supporting detail: For responsible use, choose platforms that encrypt data, support PII redaction, and explicitly state that customer data is not used to train third-party models; teams should also follow institutional ethics approvals as PLOS One did (REC REF: 104/2021).
What speed gains are realistic for a 4-group, N=21 study?
Answer: AI pipelines can cut processing time from weeks to days for transcription, code-sorting, and initial theme maps.
Supporting detail: According to the PLOS One workflow, generating 206 initial codes and running cluster maps was researcher-intensive; an AI-enabled pipeline can produce candidate codes and co-occurrence networks within hours for researcher review.
Conclusion & Next Steps
Answer: An AI-enabled qualitative pipeline can preserve the reflexive integrity of the PLOS One study while delivering faster, auditable insights for workforce policy.
According to PLOS One, Ryan et al. (2026) show that system-level barriers (from visa delays to role mismatch) are measurable in focus-group data and actionable for policy and HR.
Next steps: researchers should combine careful ethical practice with AI-assisted transcription and thematic tools to scale evidence synthesis across sites and cohorts.
If you want to test an AI-first pipeline that supports secure transcription, thematic coding, and evidence export, Try Evidano for free.
Topics
- AI qualitative analysis focus groups
- qualitative analysis internationally educated nurses
- AI thematic analysis nursing
- focus group transcription AI
Keep reading
- Commentary on NewsRetention Signals: Qualitative Analysis of IENsAI-ready synthesis of PLOS ONE (Aug 20, 2026) on internationally educated nurses. Qualitative analysis of internationally educated nurses with AI workflows, insights and next steps.
- Commentary on NewsQualitative Analysis of Internationally Educated NursesPractical guide for researchers and HR: how a PLOS One qualitative study (N=21, June 2023) reveals ecosystem drivers of IEN retention and how AI-enabled qualitative analysis speeds insight.
- Commentary on NewsFaster Photovoice Qualitative Analysis with AIHow AI accelerates photovoice qualitative analysis: extract themes, frequencies, and policy-ready insights from community photos and narratives. Learn methods and try Evidano.