This post shows how AI-enabled qualitative analysis can turn a feasibility study protocol into actionable implementation intelligence for researchers and evaluators, and uses the PLOS ONE protocol 'Moving Kindergartens: Protocol for a 10-week feasibility study' as a worked example. The primary keyword for this guide is "AI qualitative analysis for feasibility studies" and the post explains concrete steps (sampling, transcription, thematic coding, fidelity logs, and mixed-methods integration) so research teams can plan data capture and analysis with AI from the start.
Key Takeaways
According to Bandak et al. in PLOS ONE (published August 10, 2026), the Moving Kindergartens protocol defines a 10-week mixed-methods feasibility study across 10 Danish kindergartens to test an intervention supporting daily movement practices and joy of movement (Moving Kindergartens: Protocol for a 10-week feasibility study).
- Bandak et al., PLOS ONE (2026) plan to recruit 10 kindergartens between November 15, 2025 and January 31, 2026 and run the intervention from March 2, 2026 to May 8, 2026.
- Bandak et al., PLOS ONE (2026) estimate approximately 450–650 children aged 3–6 years and 80–120 pedagogical staff across the 10 kindergartens.
- Bandak et al., PLOS ONE (2026) collect mixed data: interviews, participatory observations, implementation logs, surveys including AIM/FIM/IAM measures, accelerometers worn for seven consecutive days, and BOT-2 short-form motor tests.
- Bandak et al., PLOS ONE (2026) state the study will use thematic analysis of interview data and AI-assisted transcription tools, and report that results are expected by December 31, 2026.
What happened: the Moving Kindergartens feasibility protocol in brief
The PLOS ONE protocol describes a 10-week feasibility study designed to test both an intervention and the evaluation methods before a planned RCT, answering sample, acceptability, fidelity, and data collection questions.
According to Bandak et al. in PLOS ONE (published August 10, 2026), the study was developed by co-design between January and December 2025, involving five kindergartens in iterative workshops and two design-experiment phases.
According to Bandak et al. in PLOS ONE (2026), the feasibility phase will recruit 10 kindergartens in the Zealand region (recruitment window: November 15, 2025 to January 31, 2026) with an estimated total of 450–650 children and 80–120 staff, and the intervention runs March 2, 2026 to May 8, 2026.
Bandak et al., PLOS ONE (2026) summarize the intervention elements as: formal project establishment; activity components integrated into daily kindergarten structures; organizational and staff training; and inspirational materials and plans.
Bandak et al., PLOS ONE (2026) write that one objective is to examine feasibility outcomes such as acceptability, recruitment, consent rates, fidelity (via daily implementation logs), and data collection completeness, with progression criteria guiding a move to a full-scale RCT.
Bandak et al., PLOS ONE (2026) state, "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."
Findings snapshot
| Date / Window | Metric | Value | Implication |
|---|---|---|---|
| Aug 10, 2026 | Protocol published | PLOS ONE article by Bandak et al. | Public record for methods and measures |
| Nov 15, 2025–Jan 31, 2026 | Kindergarten recruitment window | 10 kindergartens | Plan for diverse urban/suburban sample |
| Mar 2, 2026–May 8, 2026 | Intervention period (feasibility) | 10 weeks | Short-term test of implementability |
| Estimated March 2026 enrollment | Participants | ≈450–650 children; 80–120 staff; 10 leaders | Defines interview and transcription workload |
| During intervention | Objective activity measurement | Accelerometers worn 7 consecutive days | Requires device management and wear-time QC |
Implications for qualitative researchers and evaluators
Qualitative teams should plan for co-designed instruments and mixed-methods integration because Bandak et al. in PLOS ONE (2026) built the intervention through iterative co-design workshops, design experiments, and reflective meetings.
Bandak et al. in PLOS ONE (2026) expect semi-structured group interviews in each kindergarten and individual leader interviews, which implies transcription of 10 group sessions plus 10 leader interviews and additional parent telephone interviews; teams should budget time and transcription capacity accordingly.
Bandak et al. in PLOS ONE (2026) intend to transcribe interviews with an AI tool and manually correct errors, so researchers should plan for an AI-assisted-first-pass transcription workflow and a human review step to ensure fidelity.
Bandak et al. in PLOS ONE (2026) combine implementation logs, surveys (AIM/IAM/FIM), participatory observations, and accelerometry, so qualitative analysis must be designed to link themes to fidelity and objective measures for mixed-methods inference.
How Evidano helps: mapping protocol challenges to AI-enabled solutions
What is Evidano?
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Problem: Large transcription and correction workload
Evidano's speech-to-text features can perform initial transcription and PII-aware redaction, which reduces manual first-pass effort for interview sets like those described by Bandak et al. in PLOS ONE (2026).
Evidano's transcription tools integrate custom dictionaries and allow human review, matching Bandak et al.'s (2026) approach of AI transcription followed by manual correction; see Evidano Speech-to-Text for features.
Problem: Thematic coding across multiple sites and data types
Evidano's AI thematic and cross-segment analysis automates initial code suggestion and frequency counts, which accelerates the Braun and Clarke style thematic analysis Bandak et al. plan to use in PLOS ONE (2026).
Evidano supports uploading transcripts, observation notes, and survey text for integrated analysis and visualizations, which helps researchers connect interview themes to implementation logs and accelerometer-derived measures; see Evidano features.
Problem: Tracking fidelity and linking qualitative adjustments to progression criteria
Evidano can ingest implementation-log spreadsheets and link daily checkbox data to qualitative interview themes, enabling rapid queries such as which themes co-occur with low fidelity on specific days, which helps evaluate the progression criteria Bandak et al. specify in PLOS ONE (2026).
Problem: Stakeholder reporting and plain-language summaries
Evidano can generate extractable summaries and quotes for plain-language reports, matching Bandak et al.'s dissemination plans to produce summaries for participants and the public as described in PLOS ONE (2026).
FAQ: ai qualitative analysis for feasibility studies
How can AI speed thematic analysis in a feasibility study?
+
Answer: AI speeds thematic analysis by generating draft codes, grouping similar quotes, and calculating code frequencies so human analysts focus on interpretation.
According to Bandak et al. in PLOS ONE (2026), the Moving Kindergartens protocol relies on thematic analysis of interviews, and an AI-first coding pass can reduce the manual line-by-line coding time for the approximately 10 on-site group interviews and 10 leader interviews planned in the study.
Can AI transcription be used for parent and staff interviews?
+
Answer: Yes, AI transcription can be used as a first pass but should be reviewed by humans for accuracy and PII handling.
According to Bandak et al. in PLOS ONE (2026), interview recordings in the protocol will be transcribed with an AI-transcription tool and then manually corrected, which is the recommended workflow to balance speed and accuracy.
How should teams plan for mixed-methods integration with AI?
+
Answer: Define linkage points (for example, fidelity logs tied to interview dates) before data collection and ensure timestamps and IDs are consistent.
Bandak et al. in PLOS ONE (2026) collect implementation logs, accelerometer windows, observation days, and interview dates, so planning consistent identifiers and ingestion formats will let AI platforms join qualitative themes with quantitative measures.
Are there ethical or GDPR concerns when using AI tools on interview data?
+
Answer: Yes, data controllers must secure informed consent, store data encrypted, and ensure AI providers do not use data to train external models.
Bandak et al. in PLOS ONE (2026) state that personal information will be collected through secure, encrypted survey platforms and stored on password-protected servers in compliance with GDPR, and teams must mirror those protections when using third-party AI tools.
Conclusion & Next Steps
The PLOS ONE feasibility protocol by Bandak et al. (published August 10, 2026) provides a clear mixed-methods design and specific data collection timelines that qualitative teams can convert into an AI-enabled analysis plan.
Researchers should map interview counts, observation windows, and implementation-log formats up front so AI transcription and thematic workflows reduce manual effort and speed insights.
If you want to pilot an AI-first workflow for a feasibility study like Moving Kindergartens, consider testing a pipeline that combines AI transcription, human review, and thematic automation to tie themes to fidelity metrics.
Get hands-on: Try Evidano for free.
Topics
- AI qualitative analysis for feasibility studies
- qualitative analysis feasibility study
- AI transcription for research
- thematic analysis with AI
Keep reading
- 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.
- Commentary on NewsAI for Qualitative Analysis of Hospital Pharmacy CrisisHow AI speeds qualitative analysis of hospital pharmacy crisis management studies, using LSE 2025 data and practical methods to scale synthesis for researchers.
- Commentary on NewsAI-enabled qualitative analysis: sand mining in GhanaUse AI-enabled qualitative analysis to turn interviews into policy-ready insights on Ghana's illegal sand mining. Read findings, stats, and practical next steps.