Ecosystem Insights: AI Qualitative Analysis of IENs

Health-system leaders and qualitative researchers need fast, defensible synthesis of focus-group evidence about internationally educated nurses. The primary keyword for this piece is AI qualitative analysis internationally educated nurses, because this post explains how AI-enabled workflows can reproduce and extend the PLoS One (Ryan et al., 2026) ecosystem analysis of IEN integration and retention. The PLoS One study used four face-to-face semi-structured focus groups and reflexive thematic analysis to show how national policy, recruitment practices, organisational leadership, and day-to-day team dynamics interact to shape retention outcomes. This post explains the study methods, extracts the concrete statistics you can cite, and shows practical ways AI tools speed transcription, coding, cross-segment comparisons, and policy-ready reporting for HR and researcher audiences.

Key Takeaways

According to the PLoS One study (Ryan, Berkery, Makowski, 2026) PLoS One, a multisystem ecosystem explains why internationally educated nurses (IENs) are attracted to but not always retained in Ireland: national visa, housing and childcare policies, exosystem recruitment gaps, and microsystem management practices together drive integration and turnover.

The PLoS One study reported N = 21 participants across four focus groups run between June 8 and June 29, 2023, providing rich, reflexive qualitative data.
The PLoS One authors note Ireland had 51.8% of its nursing population internationally educated in 2023 and that 78% of new entrants on the nursing register in 2023 were IENs, highlighting scale (OECD data cited in PLoS One, 2026).
The PLoS One study was published on August 20, 2026, and used NVivo™ version 14 and Braun and Clarke’s reflexive thematic analysis to generate 206 initial codes before theme development.
Participant testimony in PLoS One captures concrete constraints, for example: "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).

What happened and how the PLoS One study analysed IEN focus groups

The study collected four face-to-face semi-structured focus groups with 21 internationally educated nurses between June 8 and June 29, 2023, as reported in PLoS One (Ryan et al., 2026).

According to PLoS One (Ryan et al., 2026), the recordings were professionally transcribed, managed in NVivo™ version 14, and analysed using Braun and Clarke’s six-phase reflexive thematic analysis to produce ecosystem-level themes across macro, exo, meso, and microsystems.

The study generated 206 initial codes in the coding phase, then clustered and refined those into themes through team reflexive memos and peer debriefs, a process designed to preserve analytic transparency and researcher reflexivity as described in PLoS One (Ryan et al., 2026).

Findings snapshot table

Date	Metric	Value	Implication (from PLoS One)
August 20, 2026	Publication	PLoS One article (Ryan et al., 2026)	Peer-reviewed synthesis of IEN ecosystem barriers and recommendations
June 8-29, 2023	Data collection	4 focus groups, N = 21	Small, information-rich sample used for reflexive thematic analysis
2023	Share of nurses in Ireland who are internationally educated	51.8%	Macro-level reliance on IENs increases urgency for retention-focused policy
2023	Share of new nursing registrants who were IENs	78%	Recruitment volume is high, but retention risks create sustainability issues
2026	Initial qualitative codes reported	206	Extensive inductive coding supports multi-layered theme construction

Implications for HR leaders and qualitative researchers

Clinician retention requires coordinated interventions across policy, recruitment, organisational practice, and frontline management, according to PLoS One (Ryan et al., 2026).

HR leaders should measure cross-level outcomes: PLoS One (Ryan et al., 2026) links visa and childcare policy (macrosystem) to day-to-day turnover intentions (microsystem), so include family reunification and housing metrics in retention dashboards.
Qualitative researchers should plan mixed-level data collection: PLoS One (Ryan et al., 2026) combined participant narratives with reflexive coding (206 initial codes) to reveal system interactions; replicate by capturing policy documents, HR records, and focus groups.
Policy teams need to track the scale of recruitment vs retention: PLoS One (Ryan et al., 2026) cites 51.8% IEN share in 2023 and 78% new-entrant IENs in 2023, signaling that recruitment without retention threatens sustainability.

Ethics note: PLoS One (Ryan et al., 2026) followed COREQ and local ethics approvals; this blog’s methods commentary is research-focused and non-diagnostic.

How Evidano helps translate IEN focus groups into multisystem insights

Problem: Slow transcription and inconsistent transcripts → Solution: Fast accurate transcripts

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.

Evidano’s automated transcription with a custom dictionary reduces the lag between recording and analysis, which addresses the PLoS One workflow where audio was professionally transcribed before NVivo import (PLoS One, 2026).

Use Evidano speech-to-text to perform faster verbatim transcription, add custom medical terms, and redact PII to meet ethics requirements.

Problem: Manual coding and siloed themes → Solution: Thematic + cross-segment analysis

When PLoS One authors generated 206 initial codes and then clustered themes (Ryan et al., 2026), that process required iterative team reflexivity; Evidano automates initial code generation and then supports researcher-led refinement.

Evidano’s thematic, content-frequency, and cross-segment analyses let teams quickly compare macrosystem, exosystem, mesosystem, and microsystem themes and produce the same multisystem narratives PLoS One recommends.

Problem: Lost context across datasets → Solution: AI chat and visual analytics

PLoS One used NVivo cluster maps as visual heuristics (Ryan et al., 2026); Evidano provides word clouds, co-occurrence networks, and hierarchical code→subcode visualizations to expose cross-level linkages faster.

Evidano’s AI chat over your documents and analyses helps policy teams ask natural-language questions like, "Which macrosystem barriers correlate with intent to leave? " and get extractable answers.

Problem: Multi-language, multi-origin samples → Solution: Translation + consistent dictionaries

PLoS One sampled nurses from Poland, India, Croatia, Latvia, the Philippines, Zimbabwe, and Nigeria (Ryan et al., 2026), which can introduce translation and term alignment issues.

Evidano supports translation with custom dictionaries to keep coding consistent across languages and locales, helping preserve meaning in cross-country IEN analyses.

Problem: Turning analysis into policy-ready outputs → Solution: Exportable evidence and tables

PLoS One authors produced an action grid for policy and practice; Evidano exports reproducible tables, quotable excerpts, and slide-ready visuals to speed policy brief production for HR and health system leaders.

Learn more

See Evidano features for a full list of capabilities and integrations that mirror the analytic steps used by PLoS One (Ryan et al., 2026).

FAQ: ai qualitative analysis internationally educated nurses

How can AI improve thematic analysis of focus groups like the PLoS One study?

Answer: AI accelerates transcription, suggests initial codes, and surfaces co-occurrence patterns while leaving interpretive judgments to researchers.

Supporting detail: The PLoS One study used manual reflexive thematic analysis with 206 initial codes (Ryan et al., 2026); AI can generate candidate codes and visual clusters that researchers then refine to preserve reflexivity and analytic transparency.

Can AI preserve reflexivity and rigor in qualitative research?

Answer: Yes, when AI is used as an assistive tool and researchers document decisions and reflexive memos as in PLoS One (Ryan et al., 2026).

Supporting detail: PLoS One emphasised peer debriefs and decision logs; AI platforms that allow researcher-led code refinement and audit trails can maintain the same standards of transparency.

What data and metadata do I need to reproduce the PLoS One analysis with AI?

Answer: You need verbatim transcripts, audio files, contextual notes (e.g., site), and an audit trail of coding decisions.

Supporting detail: PLoS One collected audio-recordings, transcriptions, hospital-site notes, and reflexive memos and reported COREQ alignment (Ryan et al., 2026); AI workflows should preserve those artifacts for credibility.

Is using AI tools appropriate for sensitive healthcare qualitative data?

Answer: Yes, if the tool provides encryption, PII redaction, and does not train third-party models on your data.

Supporting detail: Evidano’s platform supports PII redaction in transcription and enterprise security controls; always verify data governance before uploading health-related transcripts for analysis.

Conclusion & Next Steps

The PLoS One study (Ryan et al., 2026) shows that retaining internationally educated nurses requires multisystem evidence that links policy, recruitment practice, organisational leadership, and frontline experience.

AI-enabled qualitative analysis makes that multisystem synthesis faster and more reproducible by automating transcription, proposing inductive codes, and surfacing cross-segment links while preserving researcher reflexivity.

If you want to test an AI workflow that mirrors the PLoS One analytic steps and produces policy-ready tables and quotable extracts, Try Evidano for free.

Topics

ai qualitative analysis internationally educated nurses
qualitative analysis of IEN focus groups
AI thematic analysis healthcare
IEN retention qualitative methods

Keep reading

Browse all articles