Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. The PLOS One protocol by Bandak et al. (2026) for the Moving Kindergartens feasibility study shows how mixed-methods feasibility work collects interviews, observations, implementation logs, and accelerometer data across 10 kindergartens, and therefore illustrates where AI qualitative analysis adds the most value. The primary keyword for this post is "AI qualitative analysis for feasibility studies" and this post explains concrete steps, dates, and sample sizes from the protocol alongside practical AI-enabled workflows that shorten time to insight.
Key Takeaways
Yes: the PLOS One protocol (Bandak et al., PLOS One, 2026) demonstrates a 10-week mixed-methods feasibility study that collects rich qualitative data across multiple sites and therefore benefits from AI-assisted transcription and thematic analysis (PLOS One).
- Bandak et al., PLOS One (2026) plan a 10-week intervention delivered from March 2, 2026 to May 8, 2026 in 10 Danish kindergartens.
- Bandak et al., PLOS One (2026) estimate approximately 450–650 children aged 3–6 years and 80–120 pedagogical staff will be enrolled in the feasibility study.
- Bandak et al., PLOS One (2026) recruited kindergartens between November 15, 2025 and January 31, 2026 and used mixed data: semi-structured interviews, participatory observations, implementation posters, surveys, and AX3 accelerometers.
- Bandak et al., PLOS One (2026) state "The primary aim of this study is to evaluate the feasibility of a proposed intervention" and they transcribe interviews using an AI tool (Good Tape) before thematic analysis.
- Bandak et al., PLOS One (2026) describe that "children will be exposed to multiple daily opportunities for physical activity and active play" which creates time-stamped events and fidelity logs ideal for AI-assisted cross-linking of qualitative and quantitative records.
What Happened and how the Moving Kindergartens protocol works
The PLOS One protocol (Bandak et al., PLOS One, 2026) describes a 10-week feasibility phase that ran from March 2, 2026 to May 8, 2026 across 10 kindergartens in Zealand, Denmark.
Bandak et al., PLOS One (2026) recruited participating kindergartens between November 15, 2025 and January 31, 2026 and targeted urban and suburban centres to reach diversity in socio-economic uptake areas.
Bandak et al., PLOS One (2026) designed the intervention via a co-design process during January–December 2025 involving stakeholders from five kindergartens (n = 19 pedagogues, n = 2 researchers in the first workshop) and iterated through design experiments, workshops, and reflection phases.
Bandak et al., PLOS One (2026) collect mixed data types: semi-structured group and individual interviews, 1–2 day participatory field observations with deeper 1–2 week observations in two sites, staff and parental surveys (AIM/IAM/FIM constructs), implementation posters as daily fidelity logs, and objective physical activity via AX3 accelerometers worn for seven days.
Bandak et al., PLOS One (2026) transcribe interviews with an AI-transcription tool (Good Tape) and plan a thematic analysis framework guided by Braun and Clarke (2021); the protocol lists progression criteria to decide whether to proceed to a cluster RCT after the feasibility phase.
Findings Snapshot
| Date or Window | Metric | Value | Implication |
|---|---|---|---|
| Published Aug 10, 2026 | Protocol citation | PLOS One (Bandak et al., 2026) | Open access protocol with detailed methods and timelines |
| Nov 15, 2025 – Jan 31, 2026 | Recruitment window | Kindergartens recruited in this period (Bandak et al., PLOS One, 2026) | Prepare onboarding materials and consent workflows before trials |
| Mar 2, 2026 – May 8, 2026 | Intervention period | 10-week feasibility implementation across 10 kindergartens (Bandak et al., PLOS One, 2026) | High-frequency events and daily fidelity logs require automated processing |
| Sample estimate | Children and staff | Approx. 450–650 children and 80–120 staff (Bandak et al., PLOS One, 2026) | Substantial qualitative volume: multiple group interviews and observations |
| Data types | Instruments | Interviews (group and individual), SOPLAY observations, AX3 accelerometers, BOT-2 short form, implementation posters (Bandak et al., PLOS One, 2026) | Multimodal data needs cross-linking for implementation fidelity and thematic coding |
Implications for qualitative researchers running feasibility studies
For feasibility-study researchers, the Bandak et al. protocol (PLOS One, 2026) shows that projects generate high volumes of semi-structured interviews, observational field notes, and daily fidelity logs that must be integrated with timestamps from objective sensors.
Bandak et al., PLOS One (2026) require transcripts from multiple informants (staff, leaders, parents) and note that interviews are transcribed using an AI tool before manual correction, indicating a practical workflow where AI speeds initial transcription and human reviewers ensure quality.
Bandak et al., PLOS One (2026) use implementation posters as a daily quantitative fidelity log, which means qualitative analysts will need to merge poster counts with interview themes and accelerometer bursts to evaluate adoption and adherence.
Bandak et al., PLOS One (2026) expect results by December 31, 2026, and they set explicit progression criteria; qualitative analysts should therefore prioritize time-to-insight metrics and produce interim summaries that map to the protocol's progression thresholds.
How Evidano helps (problem → solution)
Problem: Slow transcription and messy speaker labeling
Solution: Evidano offers automated speech-to-text with a custom dictionary and speaker diarization to reduce manual cleanup time, matching the protocol choice to use AI transcription (Bandak et al., PLOS One, 2026).
Evidano's speech-to-text features are documented on the platform: Speech-to-Text.
Problem: High-volume interview coding across multiple sites
Solution: Evidano performs thematic and content-frequency analyses across transcripts, enabling rapid codebook creation, automated code suggestions, and cross-site comparisons that align with the thematic analysis approach described by Bandak et al., PLOS One (2026).
Evidano’s core capabilities are summarized on Features.
Problem: Linking fidelity logs, timestamps, and accelerometer events
Solution: Evidano ingests spreadsheets and time-stamped logs, then cross-segments qualitative themes with quantitative measures so researchers can answer questions like which implementation patterns co-occurred with higher accelerometer activity (Bandak et al., PLOS One, 2026).
Problem: Maintaining data security and GDPR compliance
Solution: Evidano encrypts data at rest and in transit and provides role-based access so that sensitive child and staff information from feasibility trials is handled according to legal requirements.
Evidano’s data practices are explained at Data Security.
FAQ: AI qualitative analysis for feasibility studies
How can AI transcription improve turnaround time for interview transcripts?
AI transcription cuts initial transcript generation time from hours to minutes, allowing earlier coding and member checking.
Bandak et al., PLOS One (2026) transcribe interviews with an AI tool (Good Tape) and then manually correct errors, which mirrors a best practice workflow: automated first draft plus human verification.
Can AI thematic analysis be trusted for feasibility outcomes like acceptability and adoption?
AI thematic tools can reliably surface candidate codes and frequency patterns, but human-led validation is required to ensure context and nuance are preserved.
Bandak et al., PLOS One (2026) plan a thematic analysis guided by outcomes of interest and manual review, which is the recommended mixed AI-human approach.
How do you merge daily fidelity posters with qualitative interviews?
You merge fidelity posters and interview data by aligning dates and local agent notes, then cross-tabulating frequency counts with emergent themes.
Bandak et al., PLOS One (2026) collect implementation posters as daily logs during the intervention, creating discrete events that can be linked to interview excerpts and observation notes for rapid triangulation.
Is AI analysis suitable for child-facing research with GDPR constraints?
AI analysis is suitable provided the platform supports encryption, restricted access, and de-identification workflows.
Bandak et al., PLOS One (2026) state personal information will be collected through secure, encrypted survey platforms and handled in compliance with GDPR, which aligns with enterprise-grade AI platforms that offer PII redaction.
Conclusion & Next Steps
The Bandak et al. protocol published in PLOS One (2026) outlines a data-rich 10-week feasibility study across 10 kindergartens that explicitly uses AI transcription and thematic analysis workflows, creating a clear opportunity for AI-enabled qualitative pipelines.
For teams running similar feasibility work, adopt an AI-first transcription step plus rapid thematic triage, then apply manual verification to meet the protocol’s fidelity and progression criteria (Bandak et al., PLOS One, 2026).
If you want to pilot an AI-enabled qualitative workflow that ingests interviews, surveys, and implementation logs and keeps data secure, see Evidano’s Speech-to-Text and Features pages to match capabilities to your protocol.
Ready to speed synthesis for your next feasibility study? Try Evidano for free.
Topics
- AI qualitative analysis for feasibility studies
- AI transcription for qualitative research
- thematic analysis feasibility study
- qualitative coding automation
Keep reading
- Commentary on NewsAI qualitative analysis feasibility studyHow AI-enabled qualitative analysis accelerates feasibility studies, using the PLOS Moving Kindergartens protocol (Aug 10, 2026) as an example. Learn methods and next steps.
- Commentary on NewsAI-enabled Qualitative Analysis: Moving KindergartensHow AI-enabled qualitative analysis can speed synthesis of feasibility studies: practical methods drawn from the Moving Kindergartens protocol, with next-step tools.
- Commentary on NewsTransform Feasibility Studies: AI qualitative analysisAI qualitative analysis accelerates thematic synthesis in feasibility trials such as the PLOS One Moving Kindergartens protocol; practical methods, numbers, and concrete next steps.