Transform Feasibility Studies: AI qualitative analysis

Primary keyword: AI qualitative analysis for feasibility studies. The PLOS One protocol 'Moving Kindergartens' sets out a 10-week, mixed-methods feasibility study of a co-designed movement intervention in Danish kindergartens. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. The payoff for researchers and trial teams is clear: use AI-enabled transcription, thematic coding, and cross-segment analysis to shorten synthesis time, surface implementation barriers, and produce reproducible progression evidence that matches the protocol’s predefined criteria.

Key Takeaways

According to Bandak et al., PLOS One (published August 10, 2026), the Moving Kindergartens protocol describes a 10-week feasibility study across 10 Danish kindergartens that will test co-designed movement activities and implementation strategies to inform a later cluster RCT (PLOS One).

The intervention period runs from March 2, 2026 to May 8, 2026 and will be implemented in 10 kindergartens, aiming to reach an estimated 450–650 children and 80–120 pedagogical staff (Bandak et al., PLOS One, 2026).
Recruitment for the study took place from November 15, 2025 to January 31, 2026 and uses mixed outreach including social media and municipal contacts (Bandak et al., PLOS One, 2026).
The protocol specifies objective measures including 7-day accelerometer wear (AX3) and standardized observation tools (SOPLAY), plus qualitative group and individual interviews transcribed with AI then manually corrected (Bandak et al., PLOS One, 2026).
The authors write, "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, " (Bandak et al., PLOS One, 2026).

What happened and how the protocol measures feasibility

Answer: Bandak et al. (PLOS One, 2026) published a protocol on August 10, 2026 that outlines a mixed-methods feasibility study using co-design, objective activity measures, structured observations, surveys, and interviews.

According to Bandak et al., PLOS One (2026), the intervention was co-designed between January and December 2025 with stakeholders from five kindergartens and tested in iterative design experiments involving 19 pedagogues and 2 researchers.

According to Bandak et al., PLOS One (2026), the feasibility study will collect data from March 2, 2026 to May 8, 2026 using: semi-structured group interviews with staff, individual interviews with leaders, telephone interviews with 4–5 parents, participatory field observations, accelerometer-based activity for seven days (AX3), SOPLAY observations, and BOT-2 short form motor tests.

According to Bandak et al., PLOS One (2026), implementation fidelity will be logged on a daily poster in each kindergarten and the study uses predefined progression criteria (green/amber/red) to decide whether to proceed to a full RCT.

According to Bandak et al., PLOS One (2026), all interviews will be transcribed using an AI transcription service then manually corrected before thematic analysis guided by feasibility outcomes.

Findings Snapshot

Date / Item	Metric	Value (from protocol)	Implication for qualitative synthesis
Published	Protocol publication date	August 10, 2026 (Bandak et al., PLOS One)	Context and methods fixed before data collection; qualitative plan must match protocol endpoints
Intervention	Intervention period	March 2, 2026 to May 8, 2026	10 weeks of implementation, suitable for collecting implementation narratives and logs
Sample	Kindergartens and participants	10 kindergartens; ~450–650 children; 80–120 staff	Sufficient breadth for cross-site thematic comparison if qualitative capture is complete
Recruitment	Recruit period	November 15, 2025 to January 31, 2026	Recruitment notes and consent conversation transcripts are a high-value qualitative data source
Progress	Expected results generation	By December 31, 2026 (Bandak et al., PLOS One)	Synthesis timelines should target interim outputs before end-of-year reporting

Implications for trial teams and qualitative researchers

Answer: Trial teams should plan AI-enabled workflows that mirror the protocol’s mixed methods design to accelerate thematic synthesis and produce reproducible progression evidence.

Prioritize accuracy in consent and recruitment transcripts because Bandak et al. (PLOS One, 2026) record recruitment counts and parental consent rates as feasibility outcomes.
Capture implementation-log images and weekly reminders as structured artifacts, because Bandak et al. (PLOS One, 2026) use a daily poster per kindergarten to quantify fidelity.
Triangulate AI-coded themes from interviews with objective accelerometer data and SOPLAY notes, because Bandak et al. (PLOS One, 2026) pair qualitative adoption outcomes with quantitative fidelity and wear-time metrics.
Plan for iterative feedback: Bandak et al. (PLOS One, 2026) require amber or red progression flags to trigger protocol amendments, so rapid qualitative synthesis shortens necessary adjustment cycles.

How Evidano helps

Problem: Manual transcription and slow coding

Solution: Evidano ingests audio/video and produces AI transcription with customizable dictionaries and PII redaction, reducing the manual correction load described in the protocol workflow.

Context: Bandak et al. (PLOS One, 2026) transcribe interviews with an AI tool then manually adjust errors; Evidano provides an integrated alternative that preserves researcher control.

Problem: Siloed qualitative artifacts (posters, field notes, interviews)

Solution: Evidano centralizes documents, implementation logs, and surveys and runs thematic, frequency, and cross-segment analyses to show which components met fidelity targets.

Context: Bandak et al. (PLOS One, 2026) require daily implementation logs and multi-source observation data; Evidano can ingest images of posters, interview transcripts, and survey sheets into one searchable corpus.

Problem: Slow synthesis for progression decisions

Solution: Evidano’s thematic analysis and AI chat over documents produce extractable themes and direct quotes quickly, enabling the rapid reporting needed for the protocol’s green/amber/red progression review.

For practical next steps see our features page: Evidano features and our transcription details: Evidano speech-to-text.

FAQ: AI qualitative analysis for feasibility studies

How can AI speed thematic analysis in a feasibility trial protocol like Moving Kindergartens?

Direct answer: AI speeds thematic analysis by producing initial transcripts, clustering recurring phrases, and surfacing candidate codes for researcher review.

Supporting detail: Bandak et al. (PLOS One, 2026) transcribe interviews with AI then perform manual correction before thematic analysis; using an integrated AI pipeline reduces hand-off delays and lets researchers focus on interpretation and validity checks.

Is automated transcription reliable enough for interviews in 2026 feasibility studies?

Direct answer: Automated transcription is sufficiently reliable when paired with human review, which is the approach used in the protocol.

Supporting detail: Bandak et al. (PLOS One, 2026) explicitly transcribe interviews using an AI tool and then manually correct errors, a hybrid workflow that balances speed and accuracy.

What qualitative data sources should teams prioritize for AI analysis in this protocol?

Direct answer: Prioritize staff group interviews, leader interviews, parent interviews, implementation posters/logs, and field observation notes.

Supporting detail: Bandak et al. (PLOS One, 2026) specify semi-structured group interviews, implementation logs, and participatory observations as core feasibility data; these are high-value for theme extraction and fidelity assessment.

When will results be available and which progression criteria matter?

Direct answer: Results are expected by December 31, 2026 and progression criteria (green/amber/red) for recruitment, consent, AIM/FIM scores, and fidelity will determine whether the team proceeds to an RCT.

Supporting detail: Bandak et al. (PLOS One, 2026) list specific progression thresholds and state that amber requires amendments and red requires justification before proceeding.

Conclusion & Next Steps

Answer: Use AI-enabled qualitative workflows to match the mixed-methods logic of the Moving Kindergartens protocol and to produce the rapid, auditable synthesis needed for progression decisions.

Practical next step: prepare an ingestion plan for transcripts, posters, observation notes, and survey free-text so qualitative and quantitative signals can be triangulated rapidly as data arrives (Bandak et al., PLOS One, 2026).

If your team wants to operationalize this set-up, integrate AI transcription and thematic pipelines early and test them in one or two sites before full deployment.

Get started and speed feasibility synthesis with an integrated platform: Try Evidano for free.

Topics

AI qualitative analysis for feasibility studies
qualitative analysis of feasibility trials
AI transcription for research
thematic synthesis with AI

Keep reading

Browse all articles

Transform Feasibility Studies: AI qualitative analysis

Key Takeaways

What happened and how the protocol measures feasibility

Findings Snapshot

Implications for trial teams and qualitative researchers

How Evidano helps

Problem: Manual transcription and slow coding

Problem: Siloed qualitative artifacts (posters, field notes, interviews)

Problem: Slow synthesis for progression decisions

FAQ: AI qualitative analysis for feasibility studies

How can AI speed thematic analysis in a feasibility trial protocol like Moving Kindergartens?

Is automated transcription reliable enough for interviews in 2026 feasibility studies?

What qualitative data sources should teams prioritize for AI analysis in this protocol?

When will results be available and which progression criteria matter?

Conclusion & Next Steps

Topics

Keep reading

Company

About

Preview Evidano

Account

Newsletter