AI-enabled qualitative research is the use of AI tools to accelerate transcription, coding, thematic synthesis, and cross-segment analysis of interviews, observations, and documents. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. This post refracts the PLOS One protocol "Moving Kindergartens: Protocol for a 10-week feasibility study" through the lens of the primary keyword AI-enabled qualitative research, showing where AI speeds feasibility trials and where human judgment still matters.
Key Takeaways
According to the PLOS One protocol, the Moving Kindergartens feasibility study will test a co-designed, 10-week intervention across 10 Danish kindergartens to assess acceptability, recruitment, measurement, and implementation strategies (PLOS One).
According to Bandak et al. (PLOS One, published August 10, 2026), the intervention runs from March 2, 2026 to May 8, 2026 and the study plans to generate results by December 31, 2026.
- The protocol aims to recruit 10 kindergartens between November 15, 2025 and January 31, 2026, representing urban and suburban areas (PLOS One).
- The protocol estimates approximately 450–650 children aged 3–6 years and 80–120 pedagogical staff across the 10 kindergartens (PLOS One).
- The protocol reports that the intervention was co-designed during January–December 2025 with stakeholders from five kindergartens and will be evaluated with mixed methods in March–May 2026 (PLOS One).
What Happened: Moving Kindergartens feasibility protocol
The PLOS One protocol describes a mixed-methods feasibility study that will run for 10 weeks and enroll 10 kindergartens in the Zealand region of Denmark (PLOS One).
The protocol states, "The primary aim of this study is to evaluate the feasibility of a proposed intervention designed to support the daily movement practices and fostering joy of movement in Danish kindergartens, " a co-designed objective attributed to Bandak et al. (PLOS One, 2026).
The protocol documents that the intervention was developed through a co-design process from January to December 2025 involving stakeholders from five kindergartens and iterative design experiments (PLOS One).
The protocol notes, "The intervention period is 10 weeks, " and specifies the feasibility window as March 2, 2026 to May 8, 2026 (PLOS One).
The PLOS One team plans mixed data collection: semi-structured interviews with staff and parents, participatory field observations, staff and parent surveys (AIM/IAM/FIM measures), accelerometer data for children, SOPLAY observations, BOT-2 short form motor testing, and implementation logs (PLOS One).
The protocol reports that interviews will be transcribed using the AI-transcription tool Good Tape and then manually corrected, a workflow the authors describe in the Methods section (PLOS One).
The PLOS One protocol states, "Results are expected to be generated by December 31, 2026, " establishing a concrete timeline for dissemination (PLOS One).
Findings Snapshot
| Date / Period | Metric | Value (from protocol) | Implication |
|---|---|---|---|
| August 10, 2026 | Protocol publication | PLOS One | Public protocol to guide feasibility execution and transparency (PLOS One) |
| March 2, 2026 – May 8, 2026 | Intervention duration | 10 weeks | Feasibility window for mixed-methods data collection (PLOS One) |
| Nov 15, 2025 – Jan 31, 2026 | Site recruitment period | 10 kindergartens targeted | Recruitment logistics and response-rate monitoring required (PLOS One) |
| Study planning (protocol estimates) | Sample size range | Approximately 450–650 children; 80–120 staff; 10 leaders | Enables stratified analysis and cross-segment coding (PLOS One) |
| Dec 31, 2026 | Results expected | Results expected to be generated by this date | Feasibility outputs will inform progression to RCT phase (PLOS One) |
Implications for qualitative researchers running feasibility trials
Treat the Moving Kindergartens protocol as an exemplar that embeds co-design, multi-methods, and explicit progression criteria to inform a later RCT (PLOS One).
Plan for data volume and heterogeneity: the PLOS One protocol expects 10 sites and roughly 450–650 children, which implies dozens of staff interviews, 1–2 days of observation per site, and accelerometer datasets that require synchronized metadata (PLOS One).
Use validated implementation measures: Bandak et al. specify AIM, IAM, and FIM survey instruments for staff and leaders, which supports comparability and forms part of progression criteria (PLOS One).
Anticipate transcription workflow needs: the PLOS One team used AI-transcription (Good Tape) followed by manual correction, indicating that AI speeds turnaround but human verification is required for accuracy and confidentiality (PLOS One).
Ethics note: the study is approved by a Research Ethics Committee and follows GDPR; qualitative researchers should treat child-level data as sensitive and design secure storage, in line with the PLOS One protocol (PLOS One).
How Evidano Helps
Problem: Large interview and observation volume slows synthesis → Solution: Thematic automation and cross-segment analysis
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Evidano feature: automated thematic extraction and hierarchical code trees speed initial synthesis so teams can spend human time on interpretation rather than basic sorting (Evidano features).
Context: Bandak et al. plan dozens of group and individual interviews and field notes across 10 sites, a workload where AI-assisted coding can reduce manual tagging time while preserving audit trails (PLOS One).
Problem: Transcription and PII risk in child-focused studies → Solution: Secure transcription with PII redaction and manual review
Evidano provides speech-to-text and controlled PII redaction designed for research contexts, reducing exposure of sensitive child data while supporting human verification (Evidano speech-to-text).
Context: the PLOS One protocol transcribes interviews using an AI tool (Good Tape) and then manually corrects transcripts, showing the same hybrid workflow Evidano supports and auditing requirements for GDPR compliance (PLOS One).
Problem: Linking survey measures, implementation logs, and qualitative themes across segments → Solution: Cross-segment and frequency analysis
Evidano offers cross-segment and frequency analyses that join survey scores (for example AIM/IAM/FIM) with coded interview excerpts and observation notes to show which themes correlate with higher acceptability or fidelity.
Context: Bandak et al. collect AIM/IAM/FIM scores and implementation posters; Evidano can ingest those spreadsheets and the transcripts to produce combined thematic and quantitative summaries that accelerate progression decisions (PLOS One).
Problem: Need for transparent audit trail and reproducible synthesis → Solution: Exportable codebooks and visualization
Evidano exports hierarchical codebooks, co-occurrence networks, and frequency tables to document how conclusions were reached and to support open-access dissemination plans.
Context: the PLOS One protocol emphasizes iterative co-design and documentation; Evidano’s exports support reproducible reporting for protocol-driven feasibility milestones (PLOS One).
FAQ: AI-enabled qualitative research
How can AI help thematic analysis of feasibility study interviews?
Answer: AI can accelerate initial coding and surface candidate themes, but human researchers must validate and refine those themes.
Supporting detail: The PLOS One protocol uses thematic analysis guidance from Braun and Clarke to interpret interview data, and the authors pair AI transcription with manual correction: this hybrid approach is consistent with accepted practice for rigorous qualitative synthesis (PLOS One; Braun and Clarke 2021).
Practical tip: Use AI to produce candidate codes and frequency tables, then run a human-led thematic refinement workshop to preserve contextual meaning.
Is AI transcription reliable for interviews with staff and parents in feasibility trials?
Answer: AI transcription is fast and cost-effective but requires manual correction for accuracy in noisy or overlapping speech and for GDPR-safe handling of PII.
Supporting detail: Bandak et al. report transcribing interviews with the AI tool Good Tape and then manually adjusting errors, demonstrating that the protocol treats AI transcription as an efficiency tool rather than a final product (PLOS One).
Practical tip: Combine secure AI transcription, a custom dictionary for local terms, and spot-checking of 10–20% of passages to measure word-error rate before full reliance.
What data-quality checks matter for mixed-methods feasibility studies?
Answer: Monitor completeness, inter-rater consistency for observations, accelerometer wear-time, and survey response rates as primary data-quality indicators.
Supporting detail: The PLOS One protocol specifies assessing data quality by completeness, consistency, adherence to procedures, inter-rater variability for SOPLAY, and accelerometer wear-time criteria, then using those indicators to refine measures for an RCT (PLOS One).
Practical tip: Predefine progression thresholds and use combined qualitative and quantitative dashboards to decide green/amber/red progression outcomes.
Conclusion & Next Steps
The PLOS One "Moving Kindergartens" protocol (Bandak et al., published August 10, 2026) demonstrates a pragmatic model for co-designed, mixed-methods feasibility testing that explicitly plans progression criteria and multi-source data collection (PLOS One).
AI-enabled qualitative research workflows can cut transcription and coding time, enable faster cross-segment synthesis, and preserve audit trails when paired with human review, matching the hybrid approach used in the protocol (PLOS One).
If you run feasibility or pilot studies and need secure AI transcription, thematic automation, or cross-segment analyses, see how Evidano supports these steps in practice (Evidano features).
Next step: review the Moving Kindergartens protocol and try automating your feasibility synthesis today: Try Evidano for free.
Topics
- ai-enabled qualitative research
- qualitative analysis of feasibility studies
- thematic analysis with AI
- ai transcription for interviews
Keep reading
- Commentary on NewsFeasibility Studies: AI Qualitative AnalysisTurn feasibility-study interviews and logs into rapid, defensible insights with AI qualitative analysis for feasibility studies. Learn methods, stats, and next steps.
- Commentary on NewsEvidence-Based Insights: AI-enabled qualitative researchTurn WHO and UN timelines into verifiable qualitative insights with AI-enabled qualitative research, including 2024–2026 statistics and practical analysis steps.
- Commentary on NewsDevelopmental Assessment Ethiopia: AI Qualitative AnalysisRead a practical breakdown of barriers to child developmental assessment in Ethiopia and how AI-enabled qualitative analysis speeds insight and implementation planning.