Health researchers often need to analyze interview transcripts, photovoice discussions, translated narratives, and open-ended reflections at the same time. AI qualitative research can help teams organize these materials, compare themes across participants, and preserve the language of lived experience without replacing methodological judgment. A November 2026 study in Pakistan provides a useful example: researchers examined how participatory storytelling affected stigma and empowerment among people affected by leprosy. This article summarizes the study and shows how AI-assisted qualitative analysis can support similar research workflows. The findings are research-focused and non-diagnostic.
Key Takeaways
According to the November 2026 study Owning the narrative: Exploring the impact of a creative storytelling intervention on stigma and empowerment among persons affected by leprosy in Pakistan, participatory storytelling was associated with less self-stigma, greater confidence, and stronger individual empowerment, while broader community stigma remained constrained by gender norms, visible disability, and structural barriers.
The study shows why AI qualitative research is useful for complex health studies: researchers can combine interviews and visual-method data, code themes across social-ecological levels, and compare how experiences differ by gender, disability, and social context.
- In 2025, the researchers recruited 17 people affected by leprosy in Karachi, including 16 photovoice participants and 14 people who completed in-depth interviews.
- The 2024 storytelling pilot combined peer support, creative activities, health education, advocacy, and contact-based engagement through the Marie Adelaide Leprosy Centre.
- The study found that the strongest reported effects occurred at the individual level, where participants described movement from shame and concealment toward self-acceptance, openness, and confidence.
- The study reported that all participants described increased confidence, but the authors cautioned that the small, intervention-completer sample and lack of baseline or comparator data limit causal conclusions.
- One participant described the experience by saying, “I was feeling very light in my heart because I have already shared everything, ” illustrating how qualitative quotations can explain mechanisms behind reported change.
How the Pakistan Storytelling Study Used Qualitative Methods
The Pakistan study used interviews and photovoice to understand how a participatory storytelling intervention influenced stigma and empowerment.
According to the November 2026 PLOS Neglected Tropical Diseases study, data collection took place in Karachi during June 2025 after recruitment between May 30 and June 20, 2025. Interviews lasted 60 to 90 minutes, were conducted with live Urdu interpretation, and were audio recorded with consent.
The researchers used purposive maximum-variation sampling to capture differences in gender, age, disability status, time since diagnosis, and social circumstances. Participants also took photographs, selected images that represented their experiences, wrote or developed captions, and discussed the images collectively.
The study analyzed the data thematically using NVivo 14. The researchers combined deductive coding from stigma, empowerment, and Social Ecological Model concepts with inductive codes that emerged from participant accounts. A senior researcher reviewed part of the coded material, and the team refined the codebook through discussion.
The method illustrates an important principle for AI qualitative research: automated pattern detection can accelerate coding and comparison, but interpretation still requires attention to translation, context, positionality, consent, and participant meaning.
Findings Snapshot for AI Qualitative Research
| Date or study detail | Metric | Value | Implication for qualitative analysis |
|---|---|---|---|
| 2024 | Storytelling pilot duration | One year | The intervention combined storytelling with peer support, health education, advocacy, and contact activities. |
| May 30 to June 20, 2025 | Recruitment period | 22 days | Purposive sampling was used to seek variation across participant characteristics. |
| June 2025 | Photovoice participants | 16 people | Visual narratives added participant-led context to interview findings. |
| June 2025 | In-depth interview participants | 14 people | Thirteen interview participants had also taken part in photovoice. |
| November 2, 2026 | Study sample | 17 people | The findings describe perceived effects in a small qualitative intervention sample. |
| November 2, 2026 | Women represented in the sample | 4 of 17 participants | The authors identified limited female representation as a constraint on gender-specific interpretation. |
Implications for Health and Policy Researchers
Health and policy researchers should treat storytelling data as evidence about mechanisms, relationships, and lived experience rather than as a standalone measure of intervention effectiveness.
The November 2026 study found that participants commonly described increased self-acceptance, communication skills, peer solidarity, and confidence. One participant said, “My communication skills are better. I can relate to different stories, and I can convince people better, ” linking the intervention to practical communication and health-promotion abilities.
The study also found that individual empowerment did not automatically produce broad social change. Participants continued to report community misconceptions, gender-related participation barriers, transport costs, economic constraints, and discrimination associated with visible impairments.
AI-enabled analysis can help researchers test these distinctions systematically. A team can create parent themes such as self-stigma, anticipated stigma, enacted stigma, intrapersonal empowerment, interpersonal support, community contact, and structural barriers, then compare their frequency and co-occurrence across participant groups and data types.
The study’s limitations should remain visible in any AI-assisted synthesis. The authors reported a small sample, four women among 17 participants, no baseline or comparator data, possible social desirability bias from interviews conducted at the intervention site, and translation-related complexity. AI summaries should therefore support, not replace, reflexive human analysis.
How Evidano Supports AI Qualitative Research on Storytelling
Problem: Researchers must synthesize interviews, translated transcripts, and photovoice discussions
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Researchers can ingest transcripts, papers, reports, and other documents, then use thematic, content, frequency, and cross-segment analyses to organize evidence across a study. Evidano also offers translation with a custom dictionary, which is relevant to multilingual interview workflows such as the Urdu-to-English process described in the November 2026 study.
Teams can learn more about Evidano's qualitative research features before designing a workflow for narrative or health research.
Problem: Important themes may be distributed across participant groups
Evidano can support cross-segment analysis by comparing themes across groups such as gender, disability status, age, employment context, or intervention participation.
Researchers can use visualizations such as hierarchical codes and subcodes, word clouds, and co-occurrence networks to inspect relationships between concepts such as stigma, confidence, peer support, and community action. These outputs are aids to interpretation, not substitutes for reviewing source passages.
Problem: Researchers need a traceable way to interrogate a large qualitative dataset
Evidano's AI chat enables researchers to ask questions over their documents and analyses, helping them locate evidence, compare themes, and examine possible contradictions.
A rigorous workflow should ask the system to distinguish participant quotations from researcher interpretation, identify supporting passages, and flag uncertainty. Researchers should then verify important claims against the original transcript or document.
Problem: Sensitive health narratives require strong data governance
Evidano encrypts data and states that customer data is never used to train third-party models, which is relevant when working with stigmatized health conditions and identifiable life histories.
Researchers should still obtain informed consent, remove unnecessary identifiers, follow institutional review requirements, and use Evidano's data security information alongside their own governance procedures.
FAQ: AI Qualitative Research for Storytelling Studies
What is AI qualitative research?
+
AI qualitative research uses artificial intelligence to help organize, code, compare, and interrogate non-numerical research data while researchers retain responsibility for interpretation and study design.
In a storytelling study, AI can help analyze interview transcripts, captions, group discussions, and reports, but human researchers must assess context, translation, ethics, and the meaning of participant language.
How did the Pakistan study measure storytelling intervention outcomes?
+
The Pakistan study explored perceived changes through 14 in-depth interviews and photovoice activities involving 16 participants, with 13 people taking part in both methods.
The researchers used thematic analysis informed by stigma, empowerment, and the Social Ecological Model rather than a quantitative outcome scale.
What did the storytelling intervention change most strongly?
+
According to the November 2026 study, the strongest changes occurred at the individual level, especially in self-acceptance, confidence, openness, and reduced internal or anticipated stigma.
The authors found more limited change in enacted stigma beyond the intervention setting, particularly where community misconceptions, gender norms, visible disability, and economic barriers persisted.
Can AI replace human thematic analysis in health research?
+
AI can accelerate parts of thematic analysis, but AI should not replace human judgment in sensitive health research.
The Pakistan study demonstrates why researchers must examine translation, positionality, consent, participant vulnerability, sample limitations, and the difference between perceived impact and causal evidence.
What should researchers code in a storytelling and stigma study?
+
Researchers should code both outcomes and mechanisms, including self-stigma, anticipated stigma, enacted stigma, identity, confidence, peer support, communication skills, community contact, gender barriers, disability, and economic constraints.
Researchers can organize these codes hierarchically and compare them across interviews, photovoice materials, participant groups, and levels of the Social Ecological Model.
Conclusion and Next Steps for AI Qualitative Research
The November 2026 Pakistan study shows that participatory storytelling can support self-acceptance, confidence, peer solidarity, and intrapersonal empowerment, while broader stigma may require sustained community contact and structural support.
AI qualitative research can make complex storytelling datasets easier to organize and compare, especially when studies combine interviews, visual materials, translations, and demographic segments.
Researchers should use AI to accelerate synthesis while preserving participant quotations, methodological limitations, reflexive review, and human accountability.
Teams analyzing interviews, reports, and open-ended responses can Try Evidano for free to explore an AI-supported qualitative research workflow.
Topics
- AI qualitative research
- AI thematic analysis
- qualitative analysis of storytelling interviews
- healthcare qualitative research
- stigma research
Keep reading
- Commentary on NewsFrom Stories to Evidence: AI Qualitative ResearchLearn how AI-enabled qualitative research can analyze storytelling interventions, stigma, and empowerment through findings from a 2026 PLOS study. Try Evidano.
- Commentary on NewsStudent Voices: AI Thematic Analysis of School FoodLearn how AI thematic analysis can turn student focus groups into actionable food policy insights, using a Northern Benin study as a practical guide.
- Commentary on NewsSmarter Care: Qualitative Analysis in HealthcareLearn how AI-enabled qualitative analysis in healthcare can turn interviews into themes, using the 2026 SYNC-RF protocol as a rigorous research example.