AI Qualitative Research Analysis: Lessons From Pakistan

According to the 2026 PLOS Neglected Tropical Diseases 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 movement from shame and concealment toward self-acceptance, confidence, and openness among participants in Karachi.

AI qualitative research analysis can help health researchers organize interview and photovoice data across themes such as stigma, empowerment, gender, disability, and community participation, while researchers retain responsibility for interpretation, consent, and contextual judgment.

• The 2026 PLOS study included 17 total participants, with 16 participating in photovoice and 14 completing in-depth interviews, including 13 who took part in both methods.
• The intervention pilot took place in Karachi during 2024, while recruitment occurred from May 30 to June 20, 2025, and data collection took place during a four-week period in June 2025.
• The PLOS researchers reported that all participants described increased confidence, while broader community change remained limited by misconceptions, gender norms, visible disability, and economic barriers.
• The study found that the strongest reported gains occurred at the individual level, particularly reduced internalized and anticipated stigma and greater intrapersonal empowerment.
• The study reported important limitations, including no baseline or comparison group, four women among the 17 participants, translation between Urdu and English, and possible social desirability bias.

The 2026 PLOS study found that participatory storytelling supported personal empowerment more clearly than broad community-level stigma reduction. The researchers used in-depth interviews, photovoice, thematic analysis, and the Social Ecological Model to examine individual, interpersonal, community, institutional, and structural effects.

The PLOS research team reported that participants described a transition from shame and secrecy to self-acceptance, confidence, and willingness to speak openly. One participant summarized the emotional change by saying, "I have no fear, no shame, not feeling any guilt, " according to the study.

The PLOS study also reported stronger peer relationships and improved communication skills. A female health worker told the researchers, "My communication skills are better. I can relate to different stories, and I can convince people better."

The study did not conclude that storytelling eliminated stigma. The PLOS authors reported that visible disability, persistent community misconceptions, gender restrictions, travel costs, and economic constraints continued to limit participation and wider social change.

For qualitative researchers, the study demonstrates why analysis should connect personal narratives with social context. Coding only for emotions such as shame or confidence would miss the institutional, gendered, economic, and community conditions that shaped those experiences.

Health and policy researchers should design AI-assisted qualitative workflows around traceability, context, and participant protection. The Pakistan study shows that a useful analysis must connect individual accounts to peer relationships, institutional support, community contact, and structural barriers.

• Build a codebook that combines deductive categories from the research framework with inductive codes emerging from participant language.
• Compare themes across methods, such as interviews, photovoice captions, group discussions, and field notes, instead of analyzing each source in isolation.
• Use cross-segment analysis for gender, visible disability, age, employment, diagnosis history, and participation patterns, while clearly labeling small or uneven segments.
• Separate reported experiences from researcher interpretation and from causal claims, because the PLOS study had no baseline or comparator group.
• Protect sensitive health narratives through de-identification, controlled access, and careful review of quotations before publication.

The PLOS researchers used NVivo 14, a preliminary codebook, iterative inductive coding, team review, consensus discussions, and triangulation across interview and photovoice data. AI can support these steps by surfacing candidate themes, comparing coded segments, and retrieving evidence, but researchers should validate outputs against the original transcript and study design.

The 2026 PLOS study shows how participatory storytelling can support confidence, self-acceptance, peer solidarity, and individual empowerment among people affected by leprosy in Pakistan. The study also shows why qualitative analysis must look beyond positive personal accounts to examine gender, disability, community norms, institutional power, and economic barriers.

AI qualitative research analysis can make that work more manageable by connecting transcripts, translations, visual narratives, and segment comparisons in one workflow. Evidano helps researchers analyze qualitative evidence more efficiently while keeping source review and human interpretation at the center.

To analyze interviews, documents, and open-ended responses with AI-assisted qualitative methods, try Evidano for free.