Qualitative Analysis of Leprosy Stigma: AI Research Guide

Qualitative analysis of leprosy stigma must preserve lived experience while making complex patterns visible to health researchers, NGOs, and policy teams. A November 2, 2026 study in PLOS Neglected Tropical Diseases examined how participatory storytelling affected stigma and empowerment among people affected by leprosy in Karachi, Pakistan. The study combined in-depth interviews with photovoice, then used thematic analysis and the Social Ecological Model to interpret change across individual, interpersonal, community, institutional, and structural levels. This article translates those methods into an AI-enabled qualitative research workflow. The goal is not to replace contextual judgment or participant safeguards. The goal is to help research teams organize multilingual transcripts, compare themes across demographic groups, and identify where an intervention produced change or where stigma persisted. The study found the strongest reported effects at the individual level, especially reduced self-stigma and greater confidence, while community-level change remained limited.

Key Takeaways

According to the PLOS Neglected Tropical Diseases study published on November 2, 2026, participatory storytelling in Karachi was associated with reduced self-stigma, greater self-acceptance, and stronger individual empowerment among people affected by leprosy.

The 2026 study included 17 participants, with 16 taking part in photovoice and 14 completing in-depth interviews.
Data collected in June 2025 showed the strongest reported changes at the individual level, including increased confidence, openness, and self-acceptance.
The 2026 study found that peer groups, creative activities, and organizational recognition supported solidarity and communication skills.
The 2026 study reported that community misconceptions, gender norms, visible disability, and economic barriers continued to limit broader social change.
AI-enabled qualitative analysis can help researchers compare themes across interviews, photovoice discussions, genders, disability experiences, and levels of the Social Ecological Model.

What the 2026 Study Shows About Qualitative Analysis of Leprosy Stigma

The 2026 study shows that participatory storytelling was linked most clearly to changes in identity, confidence, and internalized stigma rather than complete community-level stigma reduction.

The research team conducted a qualitative study after a 2024 to 2025 storytelling pilot at the Marie Adelaide Leprosy Centre in Karachi. Recruitment occurred from May 30 to June 20, 2025, and interviews took place from June 2 to June 25, 2025, according to the study methods.

The study combined 60 to 90 minute in-depth interviews with photovoice activities, in which participants created and discussed images representing stigma and empowerment. The researchers analyzed the material thematically using a deductive and inductive codebook, reviewed a subset of coded transcripts, and interpreted findings through the Social Ecological Model.

One participant described the emotional effect of disclosure by saying, "I have no fear, no shame, not feeling any guilt. I’m feeling like, if someone accept his crime in front of someone. I accept all those crimes, I feel lighter and so relaxed." The PLOS study attributed this quotation to participant P06, a man in his 40s.

A second participant connected the intervention with improved communication, saying, "My communication skills are better. I can relate to different stories, and I can convince people better." The PLOS study attributed this quotation to participant P07, a female health worker in her 50s.

The study also reported important limitations. Women represented 4 of the 17 participants, the sample included only people who completed the intervention, and the research had no baseline or comparison group. The findings therefore describe perceived impact and possible mechanisms rather than proving causal effectiveness.

Findings Snapshot: Stigma, Empowerment, and Research Design

Date or study measure	Finding	Implication for qualitative researchers
November 2, 2026	The PLOS study was published as a peer-reviewed research article.	Researchers should distinguish reported qualitative associations from causal claims.
June 2025	The study collected interview and photovoice data during a four-week period.	AI-assisted workflows can help organize a concentrated, multimethod dataset while preserving source context.
2026 study sample	The total sample was 17 participants, including 16 photovoice participants and 14 interview participants.	Small qualitative samples benefit from transparent coding, participant-level comparison, and careful interpretation.
2026 study gender composition	Women represented 4 of the 17 participants.	Cross-segment analysis can expose whose experiences are underrepresented in an intervention dataset.
2026 study background	The study reported Grade 2 Disability among 20.7% of newly diagnosed patients in Pakistan, compared with a global average of 5.5%.	Health researchers should examine how visible disability, stigma, and delayed care appear together in narratives.

Implications for Health Researchers and Program Teams

Health researchers should treat storytelling data as evidence about mechanisms of change, not only as a collection of illustrative quotations.

The PLOS study suggests that a useful analysis should separate at least four related constructs: internalized stigma, anticipated stigma, enacted stigma, and empowerment. Participants described movement from shame and concealment toward self-acceptance, but the study also found that public misconceptions and discrimination continued in wider settings.

For intervention designers, the 2026 study supports combining storytelling with peer support, health education, repeated community contact, and pathways to economic participation.
For equity teams, the 2026 study shows why gender, visible disability, transport costs, household permission, and work responsibilities belong in the analytic framework.
For qualitative methodologists, the 2026 study demonstrates the value of triangulating interview transcripts with participant-generated images and group discussion.
For policy analysts, the 2026 study indicates that individual empowerment may improve before institutional or community norms change.
For research leaders using AI, the central requirement is traceability: every generated theme should remain linked to the original transcript, speaker, segment, and analytic framework.

How Evidano Helps With AI-Enabled Qualitative Analysis

Problem: Multilingual interviews can make meaning and context difficult to compare

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.

For studies like the Karachi research, Evidano can support transcript ingestion, translation workflows, and thematic comparison while helping teams retain consistent terminology through custom dictionaries. Researchers can learn more about Evidano's translation capabilities.

AI output should support, not replace, translator checks, participant protections, and researcher interpretation when idioms or culturally specific meanings affect the analysis.

Problem: A small but rich dataset contains multiple overlapping themes

Evidano can generate thematic, content, frequency, and cross-segment analyses across interview transcripts, reports, and other research documents.

A research team could compare self-stigma, anticipated stigma, peer support, confidence, gender barriers, and community contact across participant groups, then inspect the source passages behind each pattern.

Problem: Researchers need to connect themes to a conceptual framework

Evidano can help teams organize hierarchical codes and subcodes, such as Social Ecological Model levels, stigma types, empowerment dimensions, and intervention components.

Visualizations such as co-occurrence networks can help researchers inspect relationships between themes, while AI chat over documents and analyses can support targeted questions about where a theme appears and which participant segments describe it.

Problem: Sensitive health narratives require careful data governance

Evidano provides encrypted data handling and states that customer data is never used to train third-party models.

Research teams should still obtain informed consent, remove unnecessary identifiers, restrict access, and review AI-generated outputs before sharing participant quotations or findings.

FAQ: Qualitative Analysis of Leprosy Stigma

What did the 2026 Pakistan study find about leprosy stigma?

The 2026 Pakistan study found that participatory storytelling was associated with reduced self-stigma, greater self-acceptance, stronger confidence, and improved peer connection.

The PLOS study also found that community misconceptions, gender norms, visible disability, and economic barriers continued to restrict broader social change.

How was leprosy stigma analyzed in the study?

The researchers analyzed 60 to 90 minute in-depth interviews and photovoice materials using thematic analysis informed by the Social Ecological Model.

The analysis combined deductive codes from stigma, empowerment, and ecological frameworks with inductive codes that emerged from participant accounts.

What can AI add to qualitative health research?

AI can accelerate transcript organization, coding support, theme comparison, cross-segment analysis, and retrieval of evidence from large or multilingual datasets.

AI does not establish causality or remove the need for reflexivity, ethical review, participant confidentiality, and human interpretation.

Can AI thematic analysis replace qualitative researchers?

AI thematic analysis should assist qualitative researchers rather than replace them.

The 2026 PLOS study illustrates why researchers must interpret metaphor, context, power, translation, and underrepresented perspectives alongside any automated pattern detection.

What were the main limitations of the leprosy stigma study?

The main limitations were the small sample, the underrepresentation of women, the absence of baseline and comparison data, and the inclusion only of participants who completed the intervention.

The PLOS authors therefore presented the findings as perceived impact and possible mechanisms, not as definitive proof that storytelling caused the reported changes.

Conclusion and Next Steps for AI Qualitative Research

The November 2, 2026 PLOS study shows how participatory storytelling can reveal changes in stigma, identity, confidence, and peer connection that may be difficult to capture through surveys alone.

AI-enabled qualitative analysis can make this kind of evidence easier to organize and compare, especially when researchers combine interviews, photovoice discussions, translations, and segment-level analysis.

Responsible analysis still requires human review, ethical safeguards, transparent coding decisions, and attention to voices that are missing or underrepresented.

Researchers who want to move from scattered transcripts to traceable themes can try Evidano for free.

Topics

qualitative analysis of leprosy stigma
AI qualitative research
thematic analysis of health interviews
participatory storytelling research
AI analysis of interview transcripts

Keep reading

Browse all articles