This post explains how AI-enabled qualitative research can speed and strengthen realist reviews of adolescent-led interventions that target the fossil fuel industry. The primary keyword for this post is "ai-enabled qualitative research" and the intended audience is qualitative researchers, public health practitioners, and evaluation teams planning realist evidence syntheses. The examples and numbers below are drawn from the PLOS ONE study protocol "Interventions involving young people for health equity targeting the fossil fuel industry’s practices and products" (Deivanayagam et al., 2026).
Key Takeaways
According to PLOS ONE (Deivanayagam et al., 2026), the protocol maps how adolescent-led interventions might reduce health inequities driven by the fossil fuel industry and sets out a realist review using Context–Mechanism–Outcome configurations, with results planned for July 2026. PLOS ONE
- The PLOS ONE protocol reports an estimated 2.5 million deaths annually attributable to outdoor air pollution from burning fossil fuels, cited in the paper’s Introduction (Deivanayagam et al., 2026).
- The PLOS ONE protocol states that 67% of greenhouse gases are attributable to fossil fuel combustion, and the protocol was published on August 13, 2026 (Deivanayagam et al., 2026).
- The review’s youth advisory board comprises six adolescents aged 14–17, and the study start date was October 2024 with an expected end date of April 2027, as recorded in the protocol (Deivanayagam et al., 2026).
What happened and how the protocol works
Answer: The PLOS ONE protocol sets out a realist review to explain how and under what circumstances adolescent-involved interventions counter fossil fuel industry practices to reduce health inequities (Deivanayagam et al., 2026).
According to PLOS ONE (Deivanayagam et al., 2026), the review follows RAMESES standards and five steps: define scope, build initial programme theory, systematic evidence search, selection and appraisal, and extraction and synthesis.
According to PLOS ONE (Deivanayagam et al., 2026), the review will include academic and grey literature with no date, language, or geographic restriction, and will prioritise interventions where adolescent participation maps to Hart’s ladder level five or above.
According to PLOS ONE (Deivanayagam et al., 2026), the team will refine context–mechanism–outcome configurations through workshops with a six-member youth advisory board and a multidisciplinary expert steering group.
Findings snapshot
| Date / Source | Metric | Value | Implication |
|---|---|---|---|
| 2026 (PLOS ONE protocol) | Protocol publication date | Published August 13, 2026 | Signals a registered realist review with public protocol and PROSPERO registration ID 1267252 |
| 2025 (cited in protocol) | Annual deaths from outdoor air pollution | 2.5 million deaths annually | Frames the public health scale of fossil fuel harms to justify equity-focused interventions |
| 2026 (protocol text) | Share of greenhouse gases from fossil fuels | 67% of greenhouse gases | Positions fossil fuel practices as primary climate driver shaping adolescent health risks |
| 2024–2027 (protocol status) | Study timeline | Start October 2024, expected end April 2027; evidence search aimed to complete April 2026; results expected July 2026 | Provides realistic timetable for realist synthesis and dissemination activities |
Implications for qualitative researchers and evaluators
Answer: The PLOS ONE protocol implies realist reviews of complex social interventions benefit from structured theory-building, diverse evidence sources, and stakeholder engagement (Deivanayagam et al., 2026).
According to PLOS ONE (Deivanayagam et al., 2026), using a realist approach prioritises explaining how interventions work in context rather than asking only whether they work, which changes inclusion criteria and appraisal practices.
According to PLOS ONE (Deivanayagam et al., 2026), incorporating a structural racism lens and co-produced initial programme theories with youth advisors increases relevance for interventions aiming to reduce inequities.
According to PLOS ONE (Deivanayagam et al., 2026), realist reviews should extract contextual details (geography, population, delivery mode) and mechanisms to build CMO configurations that can guide adaptation across settings.
How Evidano helps
Problem: large, messy evidence bases slow synthesis
Answer: AI-enabled tools can reduce screening and extraction time by automating document ingestion and thematic indexing.
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Evidano’s document ingestion automates transcript and report import, and its thematic and frequency analyses help operationalise the PLOS ONE protocol’s extraction categories (context, mechanism, outcome). See Evidano features for details.
Problem: tracing mechanisms across diverse sources
Answer: AI thematic mapping and co-occurrence networks reveal candidate mechanisms and their contextual links across studies.
Evidano’s thematic analysis and hierarchical coding let teams iterate programme theories rapidly and visualise Context–Mechanism–Outcome links for workshops with youth advisors and steering groups.
Evidano supports secure uploads and collaborative coding so multidisciplinary teams can reproduce the iterative synthesis approach described in PLOS ONE (Deivanayagam et al., 2026).
Problem: translation and PII when using grey literature and non-English sources
Answer: Automated translation and PII redaction reduce manual overhead while retaining analytic fidelity.
Evidano’s translation tools and transcription features are useful when protocols like PLOS ONE (Deivanayagam et al., 2026) require no-language-restriction searches and the team needs to include non-English grey literature.
For secure handling and audit trails relevant to funders and ethics committees, see Evidano data security.
FAQ: ai-enabled qualitative research
What is ai-enabled qualitative research for realist reviews?
Answer: AI-enabled qualitative research uses machine-assisted tools to speed document ingestion, coding, and thematic synthesis while keeping human-led interpretation central.
According to PLOS ONE (Deivanayagam et al., 2026), realist reviews require iterative theory-building and detailed context extraction, and AI tools can operationalise those labour-intensive steps without replacing expert judgement.
Can AI identify Context–Mechanism–Outcome configurations?
Answer: AI can surface candidate CMO elements, but human review must validate causal inferences.
According to methodological guidance cited in PLOS ONE (Deivanayagam et al., 2026) and RAMESES standards, analysts should use AI for pattern detection and then apply retroductive reasoning and stakeholder workshops to refine CMO configurations.
How do I preserve equity and anti-racist analysis when using AI?
Answer: Preserve equity by embedding participatory inputs, prioritising racially minoritised perspectives, and auditing AI outputs for bias.
According to PLOS ONE (Deivanayagam et al., 2026), the protocol explicitly applies a structural racism lens and a youth advisory board, and AI workflows should mirror that by surfacing disaggregated themes and enabling team review.
What are practical first steps for teams adopting AI for a realist review?
Answer: Start by uploading a pilot set of documents, define extraction fields (context, mechanism, outcomes), and run thematic and co-occurrence analyses to generate initial programme theories.
According to PLOS ONE (Deivanayagam et al., 2026), initial programme theories (IPTs) benefit from early stakeholder workshops, so pair AI outputs with a co-production session to validate and refine IPTs.
Conclusion & Next Steps
The PLOS ONE protocol (Deivanayagam et al., 2026) demonstrates how realist reviews can explain how adolescent-led interventions might reduce health inequities driven by the fossil fuel industry.
AI-enabled qualitative research can accelerate the protocol’s five-step realist workflow by automating ingestion, thematic mapping, and cross-source tracing while preserving stakeholder-driven theory refinement.
If your team is preparing a realist review or complex qualitative synthesis, try combining structured co-production with AI-assisted coding to reduce time to insight.
Learn more or get started: Try Evidano for free.
Topics
- ai-enabled qualitative research
- AI qualitative analysis
- realist review qualitative analysis
- youth climate interventions
Keep reading
- Commentary on NewsAI-enabled Qualitative Research: Caregiver EducationHow AI-enabled qualitative research speeds design of caregiver education for autistic children. Read PLOS One findings (Aug 13, 2026) and practical AI-enabled steps.
- Commentary on NewsFaster Insights: AI-enabled qualitative researchAI-enabled qualitative research accelerates analysis of implementation studies like the SAVING Program; learn key stats, quotes, and how Evidano speeds mixed-methods synthesis.
- Commentary on NewsAI-enabled Qualitative Research: SAVING Program CaseHow AI-enabled qualitative research extracts ethical lessons from the SAVING Program (PLOS NTDs, Jul 27, 2026). Methods, quotes, and tools for Indigenous health studies.