Researchers and program evaluators struggle to synthesize interviews, observations, and logs in short feasibility studies; AI-enabled qualitative analysis can reduce that burden and surface actionable implementation insights quickly. This post shows how to apply AI qualitative analysis to a 10-week feasibility protocol, using the PLOS One Moving Kindergartens protocol (published August 10, 2026) as the worked example, and explains practical steps researchers and UX/implementation teams can reuse. The primary keyword for this post is AI qualitative analysis feasibility study.
Key Takeaways
According to the PLOS One protocol (Bandak et al., PLOS One), the Moving Kindergartens feasibility study will run a 10-week intervention across 10 Danish kindergartens with mixed-methods data collection from March 2, 2026, to May 8, 2026 (PLOS One).
- 1) Bandak et al., PLOS One (published August 10, 2026) plan to recruit 10 kindergartens from November 15, 2025 to January 31, 2026, targeting an estimated 450–650 children aged 3–6 and 80–120 staff members.
- 2) Bandak et al., PLOS One schedule the feasibility data collection from March 2, 2026 to May 8, 2026 and expect analysis results by December 31, 2026.
- 3) Bandak et al., PLOS One use mixed methods including semi-structured interviews, participatory observations, accelerometer data, surveys (AIM, IAM, FIM), implementation logs, and the BOT-2 short form for motor skills.
- 4) Bandak et al., PLOS One state the primary aim: "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, " and will judge progression using pre-specified green/amber/red criteria.
What happened and how the Moving Kindergartens protocol is measured
Answer: The Moving Kindergartens protocol is a co-designed, 10-week feasibility intervention delivered in 10 kindergartens with mixed-methods outcomes to test acceptability, adoption, fidelity, and data-collection procedures.
Bandak et al., PLOS One (published August 10, 2026) developed the intervention between January and December 2025 through a co-design process with staff from five kindergartens and experts, and then scheduled the feasibility intervention for March 2, 2026 to May 8, 2026.
Bandak et al., PLOS One measure feasibility using multiple instruments: objective accelerometer wear (AX3 devices worn for seven days), staff surveys based on AIM/IAM/FIM, semi-structured interviews (group and individual), participatory field observations (1–2 days per site), BOT-2 short form motor tests (~15 minutes per child), recruitment logs, and a daily implementation poster acting as an implementation log.
Bandak et al., PLOS One plan targeted feasibility testing of child-level assessments in two to three kindergartens, covering approximately 100–300 children, to evaluate time, data quality, and completion rates.
Findings snapshot from the PLOS One protocol
| Date / Period | Metric | Value / Target | Implication |
|---|---|---|---|
| January–December 2025 | Intervention development | Co-design with 5 kindergartens; n = 19 pedagogues + 2 researchers in first workshop | Iterative design experiments tested and refined intervention elements |
| Nov 15, 2025 – Jan 31, 2026 | Recruitment window | 10 kindergartens from Zealand region | Feasibility of institutional enrollment will be assessed |
| Mar 2, 2026 – May 8, 2026 | Intervention period | 10 weeks across 10 kindergartens | Primary feasibility data collection window |
| During feasibility | Estimated participants | ≈450–650 children aged 3–6; 80–120 staff; 10 leaders | Used to assess procedures, consent rates, and measurement logistics |
| By Dec 31, 2026 | Results expected | Feasibility outcomes and progression criteria assessment | Decides whether to proceed to large-scale RCT |
Implications for researchers and implementation teams
Answer: Mixed-methods feasibility protocols like Bandak et al., PLOS One require fast, reliable integration of interview transcripts, observation notes, survey scores, and device logs to inform go/no-go decisions.
Bandak et al., PLOS One collect diverse data (interviews, SOPLAY observations, accelerometer files, BOT-2 tests, implementation posters), so research teams need reproducible pipelines that link qualitative themes to quantitative fidelity indicators and progression criteria.
Bandak et al., PLOS One emphasise feasibility outcomes such as acceptability and fidelity; implementation teams should therefore prioritize rapid thematic synthesis of staff interviews and time-stamped implementation logs to detect early adoption issues during the 10-week window.
Ethics note: Bandak et al., PLOS One follow GDPR and local ethical approvals; readers should treat these methods as research-focused, non-diagnostic, and ensure parental consent and child welfare procedures are in place.
How Evidano helps in AI qualitative analysis feasibility study
Problem: Multi-source data are slow to synthesize
Answer: Teams running feasibility studies often miss early signals because transcripts, observations, and logs are siloed and manually coded.
Solution: Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. Evidano ingests transcripts, observation notes, survey CSVs, and accelerometer metadata, then generates thematic, frequency, and cross-segment analyses that map directly onto progression criteria.
Problem: Transcription and redaction take too long
Answer: Manual transcription and PII redaction can delay analysis beyond a short feasibility window.
Solution: Evidano provides automated transcription with custom dictionaries and PII redaction and integrates with AI chat over your uploaded documents; teams following the Bandak et al., PLOS One plan can accelerate interview coding and produce interim thematic briefs within days rather than weeks. See Evidano speech-to-text features for details.
Problem: Linking themes to fidelity metrics is error-prone
Answer: Feasibility decisions require combining qualitative acceptability signals with quantitative fidelity (for example, the daily implementation poster counts in Bandak et al., PLOS One).
Solution: Evidano performs cross-segment analyses and visualizations that link thematic codes (staff comments about barriers) to coded implementation log frequencies and survey AIM/IAM/FIM scores, enabling clear rationale for green/amber/red progression decisions. Learn more on Evidano features.
FAQ: AI qualitative analysis feasibility study
How can AI speed up thematic analysis in a 10-week feasibility study?
Answer: AI can auto-transcribe, suggest initial codebooks, and cluster themes so human analysts can validate instead of starting from scratch.
Supporting detail: Bandak et al., PLOS One plan to transcribe interviews using Good Tape and then perform thematic analysis; an AI-enabled workflow can reduce initial coding time by 50–80% and produce interim summaries aligned to pre-specified outcomes such as acceptability and adoption.
What data formats should I prepare to apply AI qualitative analysis?
Answer: Prepare audio files (WAV/MP3), interview transcripts (TXT or DOCX), observation notes (TXT or CSV), and survey exports (CSV).
Supporting detail: Bandak et al., PLOS One use accelerometer files (AX3), survey CSVs for AIM/IAM/FIM, and free-text interviews; ingesting the same structured files into an AI platform makes cross-data linking transparent.
Can AI help map qualitative findings to progression criteria?
Answer: Yes, AI can tag interview excerpts with outcome labels (acceptability, fidelity, adoption) and count occurrences over time to produce evidence for progression decisions.
Supporting detail: Bandak et al., PLOS One specify green/amber/red progression criteria; an AI workflow can output the proportion of staff comments coded as 'barrier' versus 'facilitator' and align that with numeric thresholds used in the protocol.
Is automated transcription accurate enough for thematic analysis?
Answer: Automated transcription is sufficiently accurate for generating initial codes, but human review remains necessary for final reporting.
Supporting detail: Bandak et al., PLOS One transcribed interviews with Good Tape and planned manual corrections; best practice is AI-first transcription plus selective human validation on 10–20% of excerpts to ensure code reliability.
Conclusion & Next Steps
Answer: The PLOS One Moving Kindergartens protocol (Bandak et al., PLOS One, published August 10, 2026) shows how a short, co-designed feasibility study collects complex qualitative and quantitative data that benefit from AI-enabled synthesis.
Bandak et al., PLOS One plan recruitment from November 15, 2025 to January 31, 2026, a 10-week intervention from March 2, 2026 to May 8, 2026, and results by December 31, 2026; teams can use AI to accelerate decision-ready reporting during that window.
If you are running a feasibility study and want to automate transcription, thematic coding, cross-segment analysis, and visual reports, try a workflow built for that purpose and reduce your time-to-insight.
Get started: Try Evidano for free.
Topics
- AI qualitative analysis feasibility study
- AI transcription for qualitative research
- thematic analysis feasibility study
- qualitative data analysis platform
- Evidano qualitative platform
Keep reading
- Commentary on NewsAI qualitative analysis for feasibility studiesHow AI qualitative analysis for feasibility studies speeds transcription, thematic coding, and fidelity checks using the Moving Kindergartens protocol. 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 NewsAI for Qualitative Research in Dementia CareHow AI-enabled qualitative research can accelerate insights on dementia support needs. Read a PLOS ONE (July 27, 2026) study protocol and practical AI workflows to scale analysis.